PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310701 (2024) https://doi.org/10.1117/12.3032427
This PDF file contains the front matter associated with SPIE Proceedings Volume 13107, including the Title Page, Copyright information, Table of Contents, and Conference Committee information.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Multi-sensor Application and Image Fusion Analysis
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310702 (2024) https://doi.org/10.1117/12.3029371
Because variability index CFAR (VI-CFAR) and switching variability index CFAR (SVI-CFAR) detectors are affected by the number and location of interference targets and the number of clutter reference cells, a nonhomogeneous environment cannot be recognized accurately, resulting in a detection performance decline in a nonhomogeneous environment. This paper proposes an adaptive censoring CFAR detector (AC-CFAR), which first calculates the position of the transition and then identifies whether the subreference window starting from the transition is in a homogeneous environment. Then, based on the position of the transition and whether the subreference window is in a homogeneous environment, an appropriate method was selected from CA-CFAR, GO-CFAR and OS-CFAR to calculate the detection threshold. Monte Carlo simulation results show that the detection performance of AC-CFAR is consistent with that of VI-CFAR and SVI-CFAR, and near that of CA-CFAR in a homogeneous environment, but its performance is better than that of VI-CFAR and SVI-CFAR in a multitarget environment with a large number of interference targets. In particular, the number of interference targets is uneven on both sides of the cell being tested. In a clutter edge environment with less clutter, the false alarm rate of AC-CFAR is marginally lower than that of VI-CFAR and SVI-CFAR.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310703 (2024) https://doi.org/10.1117/12.3029207
With the development of modern society and the acceleration of urbanization, people are increasingly paying attention to indoor air quality issues. Indoor air pollutants pose a threat to human health, especially significantly affecting the respiratory and immune systems. Currently, the quality of air purifiers on the market varies widely, requiring an effective evaluation system. To study the purification performance of various air purifiers, this research collected and selected ten representative air purifiers and six indicators. The entropy weighting method was used to calculate the weights of operational indicators for some air purifiers on the market. The TOPSIS evaluation model was applied to assess the purification capabilities of each air purifier. The results showed that the applicable area of the air purifier had the greatest impact on its purification ability, while the price had the least influence. This study provides a basis for selecting suitable air purifiers and is of significant practical importance in promoting the sustainable development of air purifiers. It enhances the understanding of air purifiers' performance and facilitates their practical application, ultimately contributing to better indoor air quality and human health.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310704 (2024) https://doi.org/10.1117/12.3029213
This study utilizes numerical simulation methods to explore the influence of air purifier placement on the distribution of indoor pollutants. With the continuous acceleration of urbanization, indoor air quality has been receiving increasing attention. As a commonly used indoor air treatment device, the placement of air purifiers may significantly affect the dispersion and removal of pollutants. In this research, a numerical model is established based on fluid mechanics principles and differential equations to simulate indoor airflow and pollutant transport under different placement scenarios. Quantitative analysis of air purifier efficacy in different positions is conducted using finite difference and Jacobi iteration methods. The study reveals the correlation between placement positions and indoor pollutant concentration distribution, providing practical recommendations for optimizing air purifier placement strategies.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310705 (2024) https://doi.org/10.1117/12.3029167
Hydrogen sulfide (H2S) detection with high selectivity and fast response is of great significance due to its strong toxicity both to the environment and humans. In this paper, the design, fabrication, and characterization of a hydrogen sulfide gas sensors with a good temperature uniformity, highly selectivity and fast response is presented. Response tests show a fast response time of 100ppm H2S with 2s at 350 °C operating temperature, and the limit of detection (LOD) is 134 parts-per-billion (ppb) in ambient conditions. Selectivity tests indicated that these sensors have poor respond to interfering analytes such as hydrogen, methane, carbon monoxide, ammonia and sulfur dioxide and the selectivity coefficients of H2S are greater than 88. Silver-based hydrogen sulfide sensor offers advantages such as remarkable potential for mass production due to their ease of manufacturing, good performance, and significant selectivity.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310706 (2024) https://doi.org/10.1117/12.3029385
Multi-sensor network joint detection is a newly emerging interdisciplinary detection method that has been developing rapidly in recent years. Compared with traditional single sensor detection, it can enhance the robustness and reliability of the entire system by using multi sensor network track-to-track association technology in solving problems such as targeting, detection, and positioning. It can also improve target accuracy, expand system time, and improve sensor coverage Advantages such as improving the information utilization rate of the system. This article proposes a multi sensor track association algorithm based on Convolutional Neural Network(CNN). Through three steps of constructing, initializing, and training the neural network, a multi sensor track association model based on CNN is established, which solves the problem of automatic track association under the background of multi-sensor network detection. Simulation experiments on multiple sets of data are conducted, through data proof, the intelligent method of using neural network algorithms can effectively improve the track association of multiple sensor stations.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310707 (2024) https://doi.org/10.1117/12.3029115
In this paper, based on the fractal theory, the surface of the sensor split ring is collected and reconstructed and the surface parameters are calculated. The surface topography acquisition test bench is set up, and the surface topography is acquired at any position of the sensor loading ring by holding the mobile mechanism and white light interferometer. The acquired surface topography is reconstructed and the data points are output through the lower computer. We take a cross-section of the three-dimensional surface topography of each loading ring, import the data points into MATLAB, and use the wavelet variation method for noise elimination, based on the structure-function method. Meanwhile, we use the procedure to get the discretized data points of the combined surface and the principle of least squares linear regression of the results of each data point to obtain the fractal parameters and scale parameters. Collecting the surface morphology of different loading rings of the sensor and calculating the fractal dimension and scale parameter of the bonding surface is of great significance for the development of the optimization of the sensor bonding surface at the microscopic level.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310708 (2024) https://doi.org/10.1117/12.3029233
Aligning aspects and related viewpoints for aspect-specific sentiment polarity categorization is the goal of Aspect-Based Sentiment Analysis (ABSA), a fine-grained sentiment analysis endeavor. Dependency tree-based graph neural networks have been employed extensively in ABSA tasks recently due to their ability to communicate rich syntactic structural information. However, it is still difficult to know how to use the dependency tree's syntactic structure information, external sentiment knowledge, and semantic information to their maximum potential. For ABSA challenges, we suggest a novel multi-information fusion graph convolutional network (MIFGCN) model. First, we mine information about the syntactic structure of sentences with the help of dependency trees, and at the same time, we use the contextual affective knowledge of a specific aspect to fully exploit the syntactic dependency of the sentence; Secondly, the self-attention mechanism helps us acquire the sentence's attention score matrix and helps the model understand the sentence's global semantics; we then combine the constructed matrices to complete the fusion of multiple information, and finally update the node representations via a multilayer graph convolutional network. The methodology was validated by performing experiments on three widely used datasets with satisfactory results.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310709 (2024) https://doi.org/10.1117/12.3029308
The monitoring of telemetry data of spacecraft in orbit is of great significance for fault detection and early warning. The existing spacecraft monitoring methods are mainly based on rule knowledge and do not make good use of historical data, especially for multi parameter system anomalies. In this paper, a method of anomaly detection based on long-short term memory network(LSTM) which has memory effect is proposed for spacecraft, especially for dynamic parameters. Firstly, a set of telemetry data preprocessing methods are proposed. Secondly, for the modeling of complex system, Pearson correction coefficient method is proposed to reduce the dimension of telemetry parameters. Then, for dynamic parameters, the modeling methods of LSTM neural network are proposed, and the process of anomaly monitoring is given. Finally, using the historical telemetry data of a system, the modeling effect of neural network is analyzed. The results show that the estimated value of the model is consistent with the measured value, and the abnormal changes of the system can be found effectively.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070A (2024) https://doi.org/10.1117/12.3029224
Multi-focus image technology can be used to fuse a fully focused image by using multiple photos taken of the same scene at different focuses. The existing multi-focus image fusion methods have some common problems, such as large computation effort, incorrect estimate of focusing area, unclear fusion boundaries and edge contour loss, etc. To address these problems, an end-to-end fusion framework for multi-focus image fusion is proposed in the paper. Then, to obtain more information from source images, three parallel dilation convolutions are used to extract features from different scales in the paper. In addition, the manually designed fusion rules are replaced by an adaptive attention mechanism in the feature fusion stage. Finally, the final fusion results are reconstructed by convolution modules. The proposed method is better than other existing ones in terms of subjective visual effects and objective quantitative evaluation, according to experimental results.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070B (2024) https://doi.org/10.1117/12.3029144
In response to the need for brain tumor image segmentation, which involves segmenting it into three different regions based on the degree of tumor lesions, this paper addresses several issues with the U-Net model, such as limited feature extraction accuracy and unclear region segmentation. To tackle these challenges, we propose a multi-scale aggregation U-Net segmentation algorithm that incorporates an attention mechanism. The proposed algorithm follows a two-step process: first, it conducts feature extraction and up-sampling after each layer's down-sampling in the U-Net architecture, and then iteratively aggregates the feature map with the up-sampled map. Second, we introduce residual blocks in the encoding stage to address the issue of gradient vanishing during downsampling. Finally, we incorporate channel attention mechanisms across layers in the decoding stage to direct the network's focus on the relevant regions, thus improving the segmentation accuracy of lesion regions. We conducted simulation experiments using the BraTs2021 training set, achieving Dice coefficients of 0.927, 0.861, and 0.867 for the segmentation of the whole tumor, core tumor, and enhanced tumor images, respectively. These results surpass those of most existing brain tumor segmentation models.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070C (2024) https://doi.org/10.1117/12.3029299
Automatic code comment generation is an important research topic in software engineering, which aims to help developers understand the source code. However, this task is challenging due to the issues of long dependencies, source code structure information, and out-of-vocabulary (OOV) words. In this paper, we propose HCCM, a novel neural network model that uses three encoders to generate natural language comments for Java methods. The proposed model incorporates three novel techniques: (1) the S-SBT method to encode the abstract syntax tree of the source code; (2) a pointer generation network to copy OOV words from the source code; and (3) a convolutional neural network to capture local features of the source code tokens. We evaluate our model on a state-of-the-art large-scale Java dataset and show that it outperforms the existing methods on several metrics such as BLEU, METEOR, and ROUGE.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070D (2024) https://doi.org/10.1117/12.3029093
With the development of agriculture, agricultural CO2 emissions account for an increasing share of global CO2 emissions. However, there is still no uniform prediction standard for agricultural CO2 emissions, so understanding and monitoring agricultural activities play a crucial role in the prediction of CO2 emissions. In this paper, eight indicators affecting rural CO2 emissions are selected to predict CO2 emissions through ordinary linear regression, random forest regression, and GBDT prediction models, and experiments prove that the model in this paper still has good prediction results for complex data.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Sheng Wu, Zechen Hu, Nian Jiang, Yifeng Huang, Lulu Li, Fan Xu, Jie Shang, Deyan Hu, Yang Liu
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070E (2024) https://doi.org/10.1117/12.3029370
Flexible MEMS products can possess unique characteristics such as high stretchability, low modulus, easy deformation, good biocompatibility, and affordability, which have greater potential and application value than traditional sensors. In this paper, we fabricate a flexible MEMS temperature sensor based on inkjet printing technology and the new sensing material PEDOT: PSS, and design the matching external acquisition circuit. For the sensors designed in this paper, we analyze them experimentally from the perspectives of substrate, line width, temperature sensitivity, and fitting equation, respectively. The results show that the sensors designed in this paper are in good agreement and have high temperature sensitivity, and the TCR are kept around -0.6%. Meanwhile the exponential equation is the best fitting equation for the sensor in this paper, with the best fitting effect and the highest fitting stability.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070F (2024) https://doi.org/10.1117/12.3029178
To meet the requirements of high temperature resistance, fast response, and stable temperature measurement in neutral beam injection systems and other environments, this paper proposes a simple fiber optic temperature sensor packaged in a copper casing structure. Temperature can be accurately measured quickly and effectively shielded against external forces by this sensor. With the temperature range of -25 to 250°C, transient thermal response simulation and experimental testing of the sensor show that the packaged temperature sensor has a sensitivity of 11.2pm/°C, linearity of up to 0.996, and a response time t63 of 0.75s. Comparative tests demonstrate that the thermal response of the fiber optic grating sensor surpasses the packaged thermocouple sensor. Furthermore, the sensor can withstand impact from both lateral and longitudinal external forces, demonstrating excellent stability.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070G (2024) https://doi.org/10.1117/12.3029298
Aiming at the problem of unmanned multi-sensor cooperative control technology, in-depth research is carried out in terms of multi-sensor fusion method based on Extended Kalman Filter (EKF), optimal path planning method of A* algorithm, and decision making control strategy, which successfully realizes the vehicle environment sensing, intelligent path selection, and safe decision making execution through the use of advanced sensor fusion, optimal path planning, and intelligent decision making technology methods. The feasibility of the proposed multi-sensor cooperative control technology method is verified in simulation experimental platform, simulation scenario and actual road test, and the experimental results show that the method is effective.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070H (2024) https://doi.org/10.1117/12.3029402
In this paper, an interface circuit based on aircraft consumption sensor is proposed. Sinusoidal AC excitation signal with a peak value of 10V± 20% to the ground and a frequency of 4000HZ±10HZ is applied to the consumption sensor, and the excitation signal is monitored. At the same time, the envelope signal with a maximum amplitude of 1.2-1.3V output by the consumption sensor is collected. The envelope number is demodulated by diode detection circuit, proportional amplifier circuit and hysteresis comparator circuit, so as to realize the monitoring of aircraft engine fuel consumption. The pilot can manage aircraft fuel according to the consumption. The method has been verified by practical engineering.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Hong Liu, Songlin Luo, Hongyun Fei, Jinghang Li, Weijian Lai
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070I (2024) https://doi.org/10.1117/12.3029138
Due to the nonlinear property of asynchronous information between sensors, it is difficult to effectively control the data loss problem when fusing them, therefore, we propose a privacy-oriented fusion method for the asynchronous information of AC and DC screen tributary sensors. The asynchronous information characteristics of the AC/DC screen branch sensors are analyzed in terms of timestamp deviation, data consistency, data noise and interference, data discontinuity and data uncertainty, etc. With the help of nonlinear equations describing the asynchronous information of the AC/DC screen branch sensors, the original asynchronous information is fused and filtered in a recursive form, and the state vector estimates and covariance values of the asynchronous information collected by the AC/DC screen branch sensors are fused with the help of the RBF neural network. Then, the estimated values of state vector and covariance matrix are calculated in the RBF neural network to perform interactive multi-model fusion on the asynchronous information queue. In the test results, the data loss rate is stabilized within 3.0%.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070J (2024) https://doi.org/10.1117/12.3029244
Due to the supervised model data labeling is more complex and cumbersome, this paper adopts unsupervised Auto- Encoder network for defect detection. In addition, for the problem that the convolutional neural network does not have high accuracy in detecting defects on metal surfaces, a defect detection method based on the PoolFormer reconstruction model is proposed. Firstly, according to the type of defects, the defect-free image with superimposed similar morphological noise is used to train the reconstruction model, so that the model has the ability to repair; secondly, the defective image is input into the model for repairing; finally, the residuals between the reconstructed image and the defective image are calculated, and the defect detection and localization can be realized. The experimental results show that the method is able to detect many types of metal surface defects, and the detection accuracy reach more than 98%.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070K (2024) https://doi.org/10.1117/12.3029164
Image classification has always been a classic research topic in the field of image processing. In recent years, the development of deep learning has triggered a new wave of artificial intelligence research, further promoting the development of computer vision related technologies. The leaf image recognition method based on deep learning has become a research hotspot, such as convolutional neural networks that are good at solving image recognition problems, such as LeNet-5, AlexNet, VGGNet, GoogLeNet, ResNet, DenseNet and other neural networks, constantly refreshing their achievements in classification tasks. Most deep learning networks focus on optimizing network structure, while ignoring the complementarity of different receptive fields. Based on this, this article focuses on the complementarity between global and local features of images, and proposes the FGL network model. FGL extracts image features from both large and small receptive fields, and combines their complementarity to propose a hierarchical fusion module, which enhances the extraction of effective image features and improves classification accuracy. FGL achieved better results in CIFAR10, CIFAR100, and SVHN. Reached 96.8%, 84.2%, and 97.9% respectively. FGL has the following advantages: it is an end-to- end network; More feature information can be extracted under the same data conditions.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070L (2024) https://doi.org/10.1117/12.3029432
In order to understand the comprehensive intelligent warning system of the power grid, a research on the comprehensive intelligent warning system of the power grid based on multi-source data fusion has been proposed. From the perspective of big data applications, this paper proposes to establish a comprehensive intelligent warning system for power grid dispatch and monitoring by integrating multi-source application data such as EMS system, fault recording system, OMS system, meteorological monitoring system, and adopting a certain data algorithm model. This system can achieve functions such as monitoring and analysis of power transmission and transformation equipment, defect warning, power grid risk warning, and fault alarm analysis, assist dispatchers in power grid monitoring and fault handling, and effectively improve the level of power grid regulation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070M (2024) https://doi.org/10.1117/12.3029216
Dissolved oxygen is an important parameter for monitoring the water quality in the ocean. This study focuses on the research of compensation calibration methods for optical dissolved oxygen sensors, which possess advantages such as good robustness and high stability. Considering the issue of data drift caused by various environmental factors affecting optical sensors, the study specifically targets the drawbacks of multi-point nonlinear coupled compensation calibration methods. An optimized quantitative algorithm model is designed to simplify the operation process and enhance the accuracy of dissolved oxygen monitoring. The deviation between the reference value and the calibrated value of the sensor is within ±4μmol•L-1, and the goodness of fit reaches 0.99956.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070N (2024) https://doi.org/10.1117/12.3029270
To better ensure the safe and stable operation of substations, it is crucial to carry out effective operation and maintenance. This article introduces the application of infrared temperature measurement technology and provides an explanation of the handling of an abnormal event in the infrared temperature measurement of a 500 kV voltage transformer in a substation. It analyzes the causes of the abnormality and explores relevant operation and maintenance experience providing reference for similar situations involving voltage transformer abnormalities.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070O (2024) https://doi.org/10.1117/12.3029383
This paper is developing thermal conductivity gas sensors based on MEMS technology, proposing different driving modes and analyzing their characteristics. Firstly to analyze the principle of thermal conductivity gas sensors. Secondly, introduce the software and hardware designs in the driving modes of constant voltage, constant current, and constant temperature. Perform the experimental research on the relationship of sensor concentration with signal, response time, and characteristics affected by temperature in three driving modes. The experimental result shows that gas concentration measurement can be achieved in three different driving modes. But the linearity, response time, and temperature characteristics of the sensor are different. Driving modes can be selected according to actual application requirement. This paper provided technical support for developing MEMS thermal conductivity gas sensors.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070P (2024) https://doi.org/10.1117/12.3029223
In order to avoid serious losses caused by automotive fires and achieve early warning of automotive fires, this system compares the process and products of automotive fires, and uses point type smoke detectors, point type temperature detectors, and cable type linear temperature detectors to monitor several parameters with obvious fire characteristics in the early stage of fire occurrence. The system utilizes D-S evidence theory to fuse and analyze multi-sensor data to achieve the judgment of the same target. The accuracy and reliability of the system's early warning have been verified through early warning experiments on automotive fires.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070Q (2024) https://doi.org/10.1117/12.3029158
Limited by the nature of traditional convolutional neural networks such as local prior and parameter sharing, the ability of image restoration to cope with complex semantic environments and large-scale hole repair needs to be improved. In recent years, transformer network architectures based on self-attentive mechanisms have performed well in NLP and high-resolution visual tasks. Compared with traditional CNNs, it is more effective in long-range feature migration applications, but there is high computational complexity in directly using the self-attention mechanism in high-dimensional image tasks. To address this problem, this work improves on the self-attention mechanism by using a linear attention mechanism with gating, a dense feature reasoning module (DFR) embedded in the middle of the U-Net style network, and feature fusion of different codec layers through jump connections. Comparative experiments on publicly available datasets (Paris Street View, CelebA-HQ, Places2), qualitative analyses and quantitative evaluations demonstrate the ability of the approach to reduce computational complexity and to perform well for the repair of broken images with complex semantics of largescale holes.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070R (2024) https://doi.org/10.1117/12.3029156
During the entire electronic system data transmission process, sensors can be used to capture information, and more importantly, isolators can be used to ensure the integrity of data transmission. For a long time, optocoupler isolators have been used to achieve electrical isolation. With the progress of sensing technology and the rapid development of the semiconductor industry, using giant magnetoresistance isolation technology to achieve electrical isolation is more conducive to chip integration. This article first introduces the giant magnetoresistance effect, the explanation of its theoretical model, and the areas that still need to be studied. Then, the principle and working process of the giant magnetoresistance isolator are discussed with its structure as the core. Finally, the development direction of giant magnetoresistance isolation devices is prospected.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070S (2024) https://doi.org/10.1117/12.3029147
At present, high altitude meteorological observation is experiencing rapid development. The China Meteorological Administration alone has deployed over 100 radiosonde stations nationwide, releasing more than 7,000 radiosondes each month. With such a significant application of meteorological services on such a large scale, there is an urgent need for the calibration of radiosonde sensors. This paper, focuses on the preparation of the national calibration standard, Calibration Specification for Digital Radiosonde, Drawing on relevant WMO and national standards and specifications, a series of calibration experiments were conducted. The calibration process of the sonde's temperature, pressure, humidity, and other meteorological elements was comprehensively studied. Additionally, the sonde sensor calibration system was analyzed, and an evaluation method for uncertainty was provided. Through careful analysis, the factors that affect the results of each calibration item were identified. Finally, detailed calibration results and uncertainty evaluations for each calibration item were presented. The enhanced content is now more coherent, engaging, and aligned with the core message of the article. This study will serve as a crucial technical foundation for the application and calibration of radiosonde meteorological services. By doing so, it will significantly contribute to the accurate evaluation of weather conditions, climate monitoring, atmospheric remote sensing, and other scientific research activities. Additionally, it will facilitate the exchange of international detection data, further enhancing its importance and impact.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070T (2024) https://doi.org/10.1117/12.3029353
Due to the photosensitive properties of toxic and harmful gases themselves and the complexity of the specific gas composition in enclosed spaces, the reliability of the detection results of target gas content is difficult to guarantee. Therefore, a method for detecting toxic and harmful gas content in enclosed spaces based on fiber optic SPR gas sensors is proposed. Using wavelength modulated fiber optic SPR sensors as specific data acquisition devices, guided by detection requirements, combined with the theoretical basis of evanescent wave vector and Maxwell equation equality, the fiber optic SPR sensors are modulated to obtain reliable basic data. The Lorentz line shape is selected as the absorption spectrum line for the toxic and harmful gas to be tested. By calculating the drift of the resonance wavelength, the content of the toxic and harmful gas medium to be tested can be determined. In the test results, the error of the detection results remained stable within 3.0ppm, indicating high reliability.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070U (2024) https://doi.org/10.1117/12.3029172
This article reports the development of a novel sensor based on fiber-optic fluorescence biosensing technology for detecting alpha-fetoprotein (AFP), a key biomarker for liver cancer screening. The sensor utilizes the fluorescence resonance energy transfer (FRET) effect and constructs a fluorescence immunoassay system on the surface of the optical fiber, using the sandwich method with dual antibodies. This approach leverages the immune response to quench the fluorescent microspheres with the Gold nanoparticles (AuNPs). By precisely quantifying the difference in light intensity before and after quenching, it establishes a direct correlation between the reduced light intensity and AFP concentration. The sensor boasts a broad detection range of 10–10,000 ng/mL and offers advantages such as compact size, affordability, and ease of operation, thus presenting a promising new method for AFP detection. Extensive experimental tests have been conducted to confirm the sensor's performance, demonstrating its high sensitivity and reliability under laboratory conditions. This research provides an innovative tool and method for liver cancer-related research and clinical applications, which is expected to promote further development in the field of liver cancer diagnosis.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Haoyu Xiong, Yanxiao He, Xinghong Zhang, Cirui Liu
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070V (2024) https://doi.org/10.1117/12.3029166
Optical voltage sensors are widely applied in the grid due to their excellent resistance to interference, low cost, small volume, and simple structural design. We explore the effect of FBG spectral parameters on sensor performance through simulation and measurement on the PZT-FBG voltage sensing experimental platform. The experimental results indicate that, for the sensor to function properly, the selection of the reference FBGs' center wavelength should not be located in the sensor's invalid region, and is recommended to be not within the range of -0.009nm to +0.066nm around the sensing FBG.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070W (2024) https://doi.org/10.1117/12.3029114
This paper focuses on civil aircraft inerting system performance test flights and the sensor applications therein. This paper encompasses the objectives, test parameters considered, sensor selection and installation, methods employed in the flight test, and subsequent data analysis for the inert system performance flight test.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070X (2024) https://doi.org/10.1117/12.3029183
In wireless sensor networks (WSNs), the limited energy and uneven energy consumption of nodes pose challenges that can impact the overall network lifespan. To address the issue of uneven energy distribution in large-scale wireless sensor networks during operation, a clustering routing algorithm based on evolutionary game theory for energy balance is proposed. This method adjusts the service areas of nodes by observing the profits obtained by cluster members, aiming to reduce and balance the energy load among clusters, thereby prolonging the network's lifetime. Firstly, sensor nodes are clustered using the K-means method based on their energy levels. Then, an evolutionary game is employed to balance clusters based on their profits, striving to achieve energy balance among clusters and enhance the overall network's effective operational time, ultimately improving network performance. Experimental results indicate that compared to the LEACH protocol, PEGASIS routing protocol, energy-efficient clustering algorithm based on game theory (GEC), and the optimal clustering algorithm based on evolutionary game theory for wireless sensor networks (OCEG), the KEGT algorithm can better balance node energy consumption and extend network lifetime.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070Y (2024) https://doi.org/10.1117/12.3029381
Traditional engineering safety evaluation methods based on single sensor data fusion often have low reliability and lack the ability to comprehensively consider multiple factors, resulting in incomplete evaluation results. This study innovatively proposes a multi-source fusion model generation method, which combines advanced artificial intelligence algorithms and considers both structured monitoring information and unstructured detection information. Firstly, based on the structural characteristics of the building, a multi-source fusion system is constructed based on the target layer, location layer, and fusion layer. Before data fusion, the preprocessed multi-source data needs to be stored in the same type of database for physical fusion, and then input into the fusion model. Then, feature extractors based on bidirectional long short term memory network (BiLSTM) and coupled BiLSTM with adaptive weighted average method (AWAM) were constructed to achieve text vectorization and feature extraction of multi-source data. Then, by introducing the Bhattacharyya distance to improve the D-S evidence theory, multi-source heterogeneous data fusion is achieved, and the fusion result is the overall safety status of the building. Finally, the accuracy of this algorithm was verified through engineering examples, providing a new algorithm for engineering safety evaluation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131070Z (2024) https://doi.org/10.1117/12.3029323
When underwater detection is carried out, the bionic side-line sensor array will be affected by obstacles in the water. At present, most of the bionic side-line sensor arrays adopt the uniform distribution layout, which has certain limitations. The layout optimization of the bionic side-line sensor array has become one of the difficult problems to be solved. In this paper, aiming at the layout problem of the bionic side-line sensor, an optimization layout of the bionic side-line sensor array based on Bayesian estimation is proposed. Based on the theory of Bayesian estimation, the objective function is derived based on the information gain of the airfoil carrier in the flow field environment. The objective is searched under the framework of heuristic algorithm, and the flow velocity sensor array is optimized. The results show that the flow velocity sensors are mostly distributed in the head of the airfoil carrier.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310710 (2024) https://doi.org/10.1117/12.3029159
The pressure sensor signal processing system for UHPLC pump is composed of power management module, signal conditioning module and digital control module. It can realize Wheatstone bridge output sensor signal acquisition, linear compensation, analog output into digital output, improve the consistency, stability and accuracy of the existing series UHPLC pump master cylinder and auxiliary cylinder pressure detection.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310711 (2024) https://doi.org/10.1117/12.3029302
In the transmission gear strain test, in view of the narrow space of the closed transmission gear box, the operating environment is full of oil, and the characteristics of the sensor power supply and signal extraction caused by rotating motion are difficult, this paper determines the sensor location scheme in the area near the keyway through force transfer analysis and finite element analysis, and solves the problem of limited number of sensors in the transmission gear strain test. Finally, by finite element simulation, the failure mode recognition and early warning of the transmission gear based on the strain characteristics of the keyway are established.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310712 (2024) https://doi.org/10.1117/12.3029386
In recent years, the innovation of wearable medical devices and flexible smart healthcare systems has benefited from the rapid development of flexible electronics, Internet of Things, and Internet health. In this work, a flexible capacitive proximity and pressure dual-mode sensor, which can be used for health detection, is proposed to be fabricated by dispensing printing combined with transfer printing. Sensor performance is strongly influenced by the material of its dielectric layer. A low concentration of graphitic carbon nitride (GCN) doping into polyvinylidene difluoride (PVDF) yields a composite material with a low dielectric constant, and the ideal doping ratio is found. The sensor's fork finger electrodes were prepared using dispense printing technology, and the GCN/PVDF dielectric layer was printed on them. The electrodes on the substrate were transferred to the dielectric layer using the composite material's characteristics. While ensuring the transfer printing effect, the sensor is guaranteed to have high sensitivity, fast response and large detection range, and has good performance in both contact and non-contact systems, and wireless data transmission is realized, indicating its great potential for application in medical monitoring.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310713 (2024) https://doi.org/10.1117/12.3029109
With the continuous improvement of smartphone configurations and performance, the accuracy of built-in sensors in smartphones has also been significantly enhanced. The collection, analysis, and application of smartphone sensor signals have become increasingly important. In this paper, we start with several common sensors in smartphones and design and develop a signal collection and storage tool based on the built-in sensors of smartphones. Using this tool, sensor signals are collected in different motion states and various scene positions, and then undergo data processing and analysis. Through the analysis of signal data, it can be observed that the signal characteristics of smartphone sensors exhibit significant correlations with different motion states and scenes. By perceiving the signals, it is possible to determine the pedestrian's motion state and scene location, which can be applied to various smartphone-based practical applications.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310714 (2024) https://doi.org/10.1117/12.3029127
With the acceleration of modern life, the quality and safety of shoe storage have become increasingly important. This article introduces a smart shoe cabinet system based on multiple sensors, aiming to improve the environmental quality of shoe storage. The system uses STM32F103C8T6 microcontroller to achieve the main control function. It utilizes infrared photoelectric sensors, air quality sensors and temperature and humidity sensors to achieve automatic detection and control of ammonia, dust, and temperature and humidity in the cabinet. When ammonia, humidity, and dust concentration exceed the standard, the system can automatically operate the ventilation and purification device to avoid odors. The system also has an automatic backlight function. It uses an infrared sensor to detect the status of the cabinet door. When the cabinet door is open, it can automatically execute the backlight function, making it easy for people to choose their favorite shoes. Experimental results show that the system can effectively improve the environment inside the shoe cabinet and enhance the quality of stored shoes.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310715 (2024) https://doi.org/10.1117/12.3029219
Gas sensor is one of the most important sensors in coal mine gas monitoring system, through which the monitoring system accomplishes real-time monitoring of underground gas concentration, and the accuracy of the output signal of the gas sensor plays a crucial role in the performance of the whole monitoring system and the safe production of the coal mine. However, the gas sensor has been in the harsh environment of high temperature, high dust, high humidity and strong interference for a long time, and is prone to failures such as impact, periodic interference, jamming, deviation and drift, which cause the gas sensor to have leakage and false alarm accidents. At present, it is necessary to carry out regular cleaning, calibration and other maintenance work by hand, and the existing method is to manually disassemble the gas concentration meter, use nitrogen to blow the gas concentration meter sensor for a long time, and then install the test machine after the gas concentration meter sensor is clean, which brings a large amount of manpower and financial consumption and reduces the work efficiency due to the scattered testing points. This paper will propose to solve the shortcomings of the existing technology, in cleaning the gas concentration meter sensor without disassembling the original instrument, using heating and dehumidification of nitrogen for cleaning, with high efficiency and safety performance, but also improve the reliability of the sensor as well as the service life.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Instrument Performance Detection and System Design Optimization
Yifeng Li, Lihui Zhang, Baohui Li, Zhao Jin, Xiaoyang Wei, Xichen Geng, Haixia Wang, Ke Jiang, Yan Xu, et al.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310716 (2024) https://doi.org/10.1117/12.3029132
In this paper, the necessity of the study on EEG variation features under +Gz acceleration is first proposed. Then a test is carried out on a new model of human centrifuge, and the parameter, energy percentage change of each frequency band of EEG signal under +Gz acceleration is analyzed on account of the method of periodogram parameters to study the change features of EEG under +Gz acceleration. At the same time, the feasibility and use of the value of monitoring and warning G-LOC by using the energy percentages change-this parameter are made analyzed and evaluated.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310717 (2024) https://doi.org/10.1117/12.3029391
This paper mainly studies the use of ultrasonic testing, combined with the ultrasonic amplitude method, to visualize the internal cavity of reinforced concrete so that it can directly judge the size and shape of defects. Through the ultrasonic detection of concrete beams with defects, the amplitude value in the detection result is extracted and processed to make it a characteristic value reflecting the characteristics of the detection area. And by using the phenomenon that the defect background area will produce shadows due to the time difference of diffraction of ultrasound, the characteristic value is visualized, and the imaging effect map of the reinforced concrete beam is obtained. The imaging result mainly has two parts: black and white. Black is a low energy area, there are defects in this area, and white is a high energy area, there is no defect in this area. The results show that using the amplitude as the visualized eigenvalue can realize the imaging problem of reinforced concrete defects. In the imaging results, the abscissa errors of the black-shaded areas are 1%, 0.9%, 4.7%, and 4.8%, and the ordinate errors are 0.7%, 1.9%, 7.5%, and 16.6%. The diameters of the shaded areas are 4.21 cm, 3.34 cm, 4.42 cm, and 3.79 cm, respectively. Therefore, it can better reflect the damage of each area of the reinforced concrete beam and visualize defects.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310718 (2024) https://doi.org/10.1117/12.3029431
Natural disasters have incurred damages and economic losses in many countries. Post-disaster response requires an efficient and prompt damage detection. Although the deep learning-based approach has been emerged as an alternative to the conventional structural health monitoring, the understanding of representations for damage detection is lacking. To this end, we design a pre-training task based on a Seq2Seq model to learn high-quality representations by reconstructing acceleration accelerations. We evaluate the Seq2Seq model using a real-world dataset of shake table tests on a 2-story timber building. It is found that the Seq2Seq model outperforms the baseline in terms of reconstruction error and the capability of distinguishing representations for different damage states.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310719 (2024) https://doi.org/10.1117/12.3029101
Through the collection and storage of massive data, the paper analyzes the pressure of capacity, rate and delay brought by cloud computing, and points out the necessity of edge computing in industrial Internet. The characteristics and application value of edge computing are studied. The design scheme, networking principle and realization method of the new bus of intelligent instrument based on edge computing are presented. Experiments show that the combination of edge computing equipment and new bus communication technology reduces the difficulty and deployment cost of network collaborative manufacturing and 5G smart factory environmental state data collection, analysis, and control system design, giving full play to the real-time and flexibility of edge computing equipment, and providing reference for the development of industrial Internet and China's digital economy.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071A (2024) https://doi.org/10.1117/12.3029245
Color reproduction of 3D printing is affected by several factors including materials, morphology, viewing conditions, etc. In this paper, color prediction model based on multi-layer BP neural network was proposed for color reproduction of photosensitive resin for 3D printing. In such model, three main factors, the digital color values, the background factors for measurement and the thickness of protected layer for measurement, were chosen to work as the main control factors. Ceramic camera calibration plate and 50% neutral grey blocks were selected as the measurement background, which facilitated to control and analyse the impacts of the background on the measurement. And clear translucent blocks of different thickness, 2mm, 4mm, 6mm and 8mm, were deposited on the 3D printed color blocks surfaces, which facilitated to analyse the impact of light scattering on the measurement and color appearance. Three evaluation methods, the mean absolute error (MAE), the coefficient of determination(R2), and the average color difference(ΔE*ab), were used to evaluate the performance of prediction model. It shows that the prediction model based on multi-layer BP proposed in this paper has a higher prediction accuracy. Furthermore, the protected layer thickness and background factor both have obvious effects on color reproduction of 3D printing according to the weight of each factor
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071B (2024) https://doi.org/10.1117/12.3029320
With the continuous evolution of enterprise cloudification and digitalization, cloud-native technologies such as microservices and containerization have gradually become industry standards. However, the rapid iteration of microservices applications presents new challenges to system stability, putting pressure on maintenance personnel. This paper focuses on the open-source Prometheus monitoring ecosystem and designs a monitoring and alerting system that adapts to distributed large-scale cluster monitoring and multi-tenant management, providing an integrated monitoring solution for IT infrastructure, microservices, and containers. The system has been successfully deployed in real production environments by China Mobile Group. Through this system, maintenance personnel can quickly identify issues in business systems and provide high availability services.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071C (2024) https://doi.org/10.1117/12.3029168
To address the low accuracy of existing algorithms for detecting foreign object debris (FOD) on airport runways, a FOD detection algorithm is proposed using improved YOLOv7. Firstly, the SimAM attention mechanism is integrated into the ELAN module of YOLOv7, which can extract the feature information of small targets more effectively without adding the network parameters while inferring the 3D attention weight for the feature map. Secondly, the PANet structure in YOLOv7 feature fusion network is replaced by BiFPN structure to realize multi-scale feature fusion and cross-scale connection between different layers. Eventually, the bounding box Loss function of YOLOv7 is replaced with SIOU Loss for the purpose of improving the accuracy and speed of bounding box regression. The improved algorithm is tested on the selfmade FOD dataset, as well as the experimental results depict that the average accuracy rate is 93.5%, which is 4.8% higher than that before the improvement, and satisfactory experimental results are obtained, which can meet the FOD detection tasks of a large number of small targets.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071D (2024) https://doi.org/10.1117/12.3029396
The scale of China's high-voltage and UHV transmission lines is expanding day by day, and the important components of UHV lines, namely insulator strings, are prone to breakage and self-explosion, which makes the operation of UHV transmission lines have great potential safety hazards. Through the real-time online monitoring of the insulator string of the UHV transmission line, the operation and maintenance personnel are notified in time after the abnormality is found, which can effectively improve the operation reliability and economy of the UHV line. In this paper, we analyze and compare the obvious advantages of various traditional temperature measurement technologies and flexible temperature sensors compared with traditional methods, and propose and introduce an online temperature monitoring system of insulator string temperature with flexible temperature sensing technology combined with modern communication technology, so as to improve the operation and maintenance status of power system network and further improve the automation degree of power grid inspection.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071E (2024) https://doi.org/10.1117/12.3029452
In response to the issues of low reliability and poor prediction accuracy in traditional building structure settlement monitoring, a method for building settlement monitoring based on multiple sensors and Radial Basis Function (RBF) neural network is proposed. Building settlement information is collected and wirelessly transmitted using various sensors and hardware devices, including GPRS communication modules. The monitoring data collected by sensors are compared and analyzed to determine the settlement status of the building. An RBF neural network prediction model is constructed for potential settlement points. Additionally, the structural parameters of the RBF neural network are optimized using the leapfrog algorithm. Experimental results demonstrate that this method can accurately assess potential building structure settlements in real-world environments with small prediction errors. The maximum relative error is 4.83%, indicating good predictive capabilities.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071F (2024) https://doi.org/10.1117/12.3029375
The damage factor, a crucial parameter in assessing the integrity of concrete structures, is determined and validated using the constitutive relationship of concrete and the principle of energy equivalence. The theoretical relationship between Fiber Bragg Grating (FBG) strain sensors and crack monitoring in concrete structures is derived and verified based on the principle of fiber optic sensing. Experimental findings demonstrate that FBG sensors can accurately detect and track crack formation and propagation. The approximate quantitative relationship obtained through theoretical derivation and physical experimentation falls within the acceptable error range for practical engineering applications. Finally, a crack development model for concrete structures is established, and the plastic damage model is employed to derive a dimensionless damage value that can be represented by the measurable crack width.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Yan Guo, Jia He, Huifang Zhang, Kai Zeng, Laigang Wang, Zili Chen, Yan Zhang
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071G (2024) https://doi.org/10.1117/12.3029189
Nitrogen is an important nutrient for the yield formation of winter wheat, and the rich spectral and texture information of UAV ultra-high resolution imagery provides an important technical approach for nitrogen accurate prediction. In this study, based on the spectral and texture features extracted from UAV remote sensing images of winter wheat during the key growth stages (jointing stage, booting stage, flowering stage, and filling stage), the LASSO method was introduced to screen feature variables to eliminate the collinearity among the feature variables, and ridge regression, least-squares regression, and LASSO regression were used to construct the nitrogen prediction model in winter wheat plants. When the regularization parameter λ took the value of 0.08, 17 sensitive feature variables such as Nir, RERDVI, NGBDI, con_G, ent_R, mean_R, and mean_Nir were screened out. Based on the screened sensitive characteristic variables, the nitrogen prediction models established by the three methods of ridge regression, least squares regression, and LASSO regression all achieved significant differences at the 0.05 level. The accuracy of the three nitrogen prediction models was highly consistent with R2 of 0.76, 0.77, and 0.78, respectively, and the RMSEs of 3.55g/m2, 3.79g/m2, and 3.79g/m2, respectively. This indicates that the LASSO feature screening method introduced in this study not only makes the model concise but also the model constructed by the sensitive variables screened by LASSO is robust and provides technical support for precise monitoring and management of nitrogen in smart agriculture.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071H (2024) https://doi.org/10.1117/12.3029248
Passive jamming technology based on metasurface is a hot topic in the field of electronic countermeasures. Currently, the existing research mainly focuses on the feasibility of false target deception from the level of jamming technologies. However, the effect of false target deception has not been given attention. For SAR jamming methods, the imaging quality of false targets will directly affect the deception effect of the image, which also determines the effectiveness of the jamming method. In this paper, a passive jamming method for intrapulse intermittent modulation by metasurface is studied. This method uses metasurface to perform intrapulse intermittent modulation of SAR-emitted radar signals. By calculating the imaging indicators such as resolution and sidelobe ratio of the pseudo-target imaging effect, the deception effect of the jamming method on the SAR system using the RD imaging processing algorithm is analyzed. As the order and intermittent modulation frequency of the false target increase, the quality indicators such as the resolution and sidelobe ratio of the false target will gradually decrease. Simulation experiments verify the correctness of the research conclusions.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071I (2024) https://doi.org/10.1117/12.3029184
Navigation signals are one of the most crucial components of the Global Navigation Satellite System (GNSS), acting as a hub among satellites, users, and ground control systems. Conducting space signal quality assessments and monitoring the navigation system are essential means to ensure the normal functioning of navigation system capabilities such as positioning, speed measurement, and timing. These assessments not only provide high-quality services to users but also offer theoretical support for navigation system design and technical validation. In scenarios lacking prior information, it is necessary to estimate parameters such as the initial value of the carrier phase and carrier frequency to achieve signal demodulation and recover the pseudocode for subsequent capture and tracking, thus enabling signal assessment in non-cooperative settings. Existing methods for parameter estimation, particularly under conditions of low signal-to-noise ratios and the presence of interference, do not provide satisfactory accuracy and fail to meet the requirements for capture and tracking. This paper introduces a method for estimating the parameters of QPSK signals, utilizing image information combined with unsupervised clustering algorithms. Simulations show significantly improved estimation accuracy under low signal-to-noise ratio conditions. This method can also be applied to the estimation of signal modulation characteristic parameters and eye diagram parameters, providing important technical support for signal quality assessment.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Tianxue Man, Jianwei Mao, Yongjun Lai, Weifang Sun
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071J (2024) https://doi.org/10.1117/12.3029231
Rapid and accurate detection of surface cracks on high-speed railway concrete slabs is of great significance for maintaining the safety and reliability of railway structures. However, existing crack detection methods suffer from segmentation insufficiency and weak anti-interference capabilities. In this paper, a novel automated detection method based on image semantic segmentation is proposed to achieve segmentation detection and quantitative analysis of surface cracks on high-speed railway concrete track slabs. First, the crack images are preprocessed to enhance the crack edge features through white balance and filtering. Then, an image-driven semantic segmentation network CBAM-U-Net is utilized for pixel-level crack detection on the sampled crack images. The network reduces the computational effort and improves the accuracy mainly by improving the ‘skip connection’ information interaction mechanism of the U-Net network and introducing CBAM blocks. Finally, by counting the pixel number of the segmentation area, the crack can be quantitatively evaluated. The experimental result demonstrates the effectiveness of the proposed method, with an average Dice coefficient of 73.35%. This method provides a new strategy for automated crack detection on high-speed railway concrete track slabs.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071K (2024) https://doi.org/10.1117/12.3029326
In the existing target detection algorithms, it has not been improved according to the characteristics of bridge surface damages, and the detection accuracy of bridge apparent diseases under complex background is low. To enhance the accuracy of concrete bridge surface damage detection in complex backgrounds, a bridge surface damage detection method based on the improved YOLOv8 algorithm is proposed. Firstly, addressing the characteristics of densely distributed damages and significant variations in damages scales, the network structure of YOLOv8 is modified by embedding the CBAM (Convolutional Block Attention Module) attention module into the detection layer. Experimental results demonstrate that the improved YOLOv8 model exhibits significant improvements in precision, recall, average classification accuracy, and other metrics compared to the original model. The overall mean average precision increased by 1.23%, indicating a more precise and real-time detection of bridge damages.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071L (2024) https://doi.org/10.1117/12.3029152
In response to the problems of high leakage rate, untimely detection, and high maintenance cost in mine drainage pipelines, a mine drainage pipeline leakage location system was designed based on the acoustic detection method. The position of the leakage point was calculated through cross correlation algorithm based on the time difference of the sound signal, which can effectively reduce the maintenance cost of the mine drainage pipeline, timely detect pipeline leakage, and achieve accurate positioning of the leakage point, reducing disaster risk. The mine drainage pipeline leak location system designed in this article integrates acquisition probes and digital filters, adopts cross correlation analysis algorithms, and provides online leak location services. Tests have shown that the drainage pipeline leakage location system can accurately locate pipeline leakage points in different scenarios.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071M (2024) https://doi.org/10.1117/12.3029145
In response to the limitations of traditional industrial robots, which can only perform fixed-point palletizing tasks with low actual gripping accuracy and high failure rates, a 3D vision-based robot palletizing system was designed. This system focuses on the pallets containing workpieces and installs the camera in a manner similar to having eyes in the hands. To improve the robot's gripping accuracy, the Shape-NCC (Normalized Cross-Correlation) rotation-invariant template matching algorithm is used to identify target images, overcoming the problem of the traditional NCC algorithm being unable to find targets after image rotation. Using depth images, the system obtains the three-dimensional coordinates and rotation angles of the pallets in the target images, and communicates this position information to the robot via TCP. The robot then adjusts its grip position based on this information and ultimately completes the palletizing task automatically according to the palletizing strategy. Field experiments demonstrate that the system can achieve high-precision palletizing, with position errors within ±5mm and angle errors within ±1.7°. When operating at the highest speed in automatic mode, the palletizing speed reaches 70%, meeting the precision and speed requirements of industrial palletizing systems.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071N (2024) https://doi.org/10.1117/12.3029118
It's important to measure the force used during fingertip manipulation without affecting the natural sense of touch when digitizing the skills of experienced craftsmen. However, most force sensors need to be placed between the skin and the objects which can interfere with the natural skin sensation. Here, we developed a wearable fingertip force sensing system that can monitor fingertip force without affecting tactile sensation. The system measures the changes of blood volume in the fingertip by photoplethysmography (PPG) to obtain the fingertip force during manipulation. A hemodynamics model of fingertip blood flow was established, and variations in fingertip blood vessel diameter under force conditions were simulated and analyzed. The scalability of the hemodynamics model is verified by experiments with different operating contact angles. This work sheds new light on areas such as digitization of the skills of experienced people and human-machine interaction.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071O (2024) https://doi.org/10.1117/12.3029229
In the automated production process of cigarettes, it is inevitable to encounter some malfunctions on a certain production line, and each malfunction will affect the quality and output of cigarette products. In order to ensure the quality of cigarette products, this article designs a warning function based on PLC and iFIX operating software on the cigarette production line. By analyzing historical and real-time data, a warning model is established using the process capability index CPK and setting warning thresholds. Intelligent warnings are given for unqualified data or other problems, and presented in the form of interface prompts. Transforming fault handling into pre warning, reducing losses caused by faults, ensuring stable quality and flow of each process (section) during the tobacco production process, uniform moisture and temperature of tobacco products, and meeting process requirements. The product is always in a high-quality state. The warning system studied in this article will be able to effectively solve quality problems that arise during tobacco production.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071P (2024) https://doi.org/10.1117/12.3029319
The collision or penetration overload signal measured by the general accelerometer may encounter problems such as signal overlap and multi-layer signal adhesion. This paper designs a novel piezoelectric accelerometer with the characteristics of mechanical filtering and switching. The structure and working principle of this accelerometer are described in the paper, and its output characteristics are obtained through experiments. The experimental results show that the output signal of the new piezoelectric accelerometer has the characteristics of less high-frequency interference signal and no signal adhesion, which are conducive to the information extraction of collision and penetration multi-layer target by the flying carrier.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Kuixu Ma, Jinyan Du, Zeqi Liu, Shengxin Li, Chuanlin He
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071Q (2024) https://doi.org/10.1117/12.3029260
In addressing the issue of gradually attenuating amplitude of underwater acoustic signals received by hydrophones, this paper presents a feedforward digital automatic gain control (AGC) system based on a table lookup method. This approach reduces significant computational load associated with logarithmic operations, multiplication, and floating-point arithmetic. The system was simulated using MATLAB software, and the results indicate that, compared to the commonly used binary search-based digital AGC systems, the feedforward digital AGC system based on the table lookup method exhibits faster control speed, smoother output signals, and a noticeable reduction in signal transients. Finally, a comparative validation of the two algorithms was conducted on Field Programmable Gate Array (FPGA), confirming the applicability and outstanding performance of the feedforward digital AGC system based on the table lookup method in practical engineering applications.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Huijun Yang, Haonan Li, Yimin Liu, Yi Song, Sennan Wang
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071R (2024) https://doi.org/10.1117/12.3029181
Pulse system pseudo-code phase modulation fuze is a typical compound modulation radio fuze. The fuze uses narrow pulse sampling, range gating, pseudo-random code correlation detection technology, which has a strong range resolution ability. In this paper, a predictive deception jamming technology is proposed to solve the problem that the jamming signal of the conventional fuze lags behind the target echo. The pseudo-code sequence of the fuze signal is obtained by reconnaissance, and the model parameters are estimated by combining the pseudo-code M sequence model. A jamming sequence is generated whose phase lead fuze signal during pulse duration. The fuze signal is jammed in time domain, frequency domain, modulation domain and power domain, and the jamming signal can enter the distance gate of the fuze signal in advance, so that the fuze starts in advance. The simulation results show that the jamming technology can counter the pulse system pseudo-code phase modulation fuze and has good jamming effect.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071S (2024) https://doi.org/10.1117/12.3029454
Ballistocardiography (BCG) is a non-contact method of detecting cardiac activity that measures changes in external pressure caused by heartbeats and arterial blood circulation. In this study, BCG signals were collected using a micro-bend fiber sensor along with Electrocardiography (ECG) as a reference signal. A heart rate detection algorithm based on autocorrelation and a dual-threshold J peaks detection algorithm were proposed to achieve real-time detection of heart rates and accurate detection of J peaks. Additionally, signals from six healthy adult subjects were collected to evaluate the effectiveness of the algorithms by comparing the differences between ECG and BCG in heart rate detection and ECG R-peaks and BCG J peaks detection. Results showed that the accuracy of the autocorrelation-based heart rate detection algorithm reached 99.77% and the accuracy of the dual-threshold J peaks detection algorithm reached 98.03%.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071T (2024) https://doi.org/10.1117/12.3029235
The sensor measurement parameters of liquid rocket engine (LRE) ground test are key indicators reflecting the engine's working performance, and parameter prediction is of great significance for engine performance evaluation and fault diagnosis. In response to the difficulty in predicting parameters due to the large range of parameter fluctuations under changing operating conditions, the thrust parameter is taken as the prediction target, a prediction model combining long short-term memory network (LSTM) with self attention mechanism has been established, to explore the long-term and short-term variation patterns of multivariate sensor time series. To maximize the predictive ability of the network, Bayesian optimization algorithm is used to optimize the hyperparameters combination of the model. The experiment shows that this method can predict changes in thrust parameters, with a root mean square error (RMSE) of 0.93% in the test set, and has strong accuracy and application value.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071U (2024) https://doi.org/10.1117/12.3029264
The Photoplethysmography (PPG) stands as a fundamental measurement in wearable devices for human physiological parameters. This signal is susceptible to interference from external environmental factors during measurement of human physiological parameters. Prior research has addressed this issue predominantly through discrete wavelet transform (DWT) based approaches, yielding some success. However, the signals processed by these methods are often not smooth enough or have distortions, subsequently undermining confidence in the accuracy of derived physiological parameters. To mitigate this issue, this paper introduces a novel algorithm integrating DWT with Savitzky-Golay (SG) filtering to reduce noise on PPG signals. Specifically, the algorithm initially employs DWT on the original PPG signal for signal decomposition, and the preliminary denoising signals are subsequently obtained using soft thresholding on these decomposed signals. After that, a grid search algorithm is adopted to optimize the parameters of the SG filter, aiming to realize the smoothing of PPG signals. The final denoising PPG signal can be obtained from the output port of the SG filter. Finally, the algorithm combining DWT and MA filtering is compared with our proposed algorithm, and the experimental results show that the proposed method not only effectively reduces the noise interference, but also preserves the original features of the signal, which verifies the effectiveness and advancement of the proposed algorithm.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071V (2024) https://doi.org/10.1117/12.3029250
This system develops an image processing module based on the comprehensive experimental platform of electrical specialty, and completes the digital circuit design of the image acquisition module. It can transmit and store the collected images to the upper computer to meet the needs of other subsequent image processing. For example, character detection is an application of image processing. This module uses FIFO (first in first out) chip as the bridge between microprocessor and image sensor to solve the difficulty that the image processor frequency is too high, which makes the image sensor and microprocessor frequency mismatch. Finally, it meets the functional requirements of the experimental platform microprocessor for image acquisition, storage and transmission.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071W (2024) https://doi.org/10.1117/12.3029149
Machine learning methods can automatically extract inherent structural features in data, thus widely used for vibration feature extraction. However, it is very challenging to make a balance between generalizability and diagnostic accuracy on the extracted features. The variational autoencoder describes the observations in the latent space in a probabilistic way, so that the extracted latent space features have a good generalization ability. This paper develops the Binary Variational Autoencoder (BVAE), dedicated to describing the machine condition information carried by the vibration signals in a probabilistic way. The BVAE maps vibration signals into a latent space to extract machine condition information and binarizes them, resulting in a compact machine condition hash (MCH). The effectiveness of the developed method was verified using the Case Western Reserve University bearing data set. The results show that the machine conditional hash extracted by the BVAE can balance low dimensionality and high discriminability, achieving a diagnostic accuracy over 99%.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071X (2024) https://doi.org/10.1117/12.3029136
The existing face anti-spoofing (FAS) models have demonstrated high performance on specific datasets. However, for practical applications in real-world systems, it is essential to broaden the FAS model's capability to handle data from unknown domains, going beyond achieving strong results on a single baseline. Leveraging the remarkable capabilities of visual deformation models in discerning discriminative information, our exploration focuses on employing these models for recognizing facial presentation attacks in unexplored domains. To fulfill this objective, we introduce a groundbreaking Vision Transformer named DAA ViT, seamlessly integrating feature extraction and classification functionalities. Notably, we employ the Affine Consistent Module to fortify the geometric transformation stability. Simultaneously, the integration of a Deformable Attention module directs the model's focus towards crucial facial regions, thereby enhancing the extraction of FAS-related features. Our DAA ViT model demonstrates superior performance compared to contemporary techniques across publicly accessible face anti-spoofing datasets. We outperform existing methods in various aspects, including attack detection across diverse types, generalization proficiency, and other pertinent metrics. This substantiates the efficacy of our devised model framework and the integrated modules.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071Y (2024) https://doi.org/10.1117/12.3029137
In order to solve the problems of the difficulties in feature extraction and low recognition accuracy for rolling bearing fault signals, a bearing fault diagnosis method based on Subtraction-Average-Based Optimize (SABO) optimizing Variational Mode Decomposition (VMD) parameters and using Kernel Limit Learning Machine (KELM) for fault classification is proposed. Firstly, a mathematical behavior based subtractive average search strategy is adopted and using minimum envelope entropy as fitness value to adaptively optimize the parameters of variational modal decomposition VMD, obtaining the number of modal components Κ and penalty factor α the best combination. Then, take the optimized values [Κ, α] of the parameters and the index values of the minimum envelope entropy fitness back into VMD to get the most suitable IMF. Meanwhile extract the 9 time-domain indicator features from the IMF to construct fault feature vectors. Finally, the KELM rolling bearing fault diagnosis classifier is be established. The effectiveness of the algorithm was verified using vibration data of the rolling bearing.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071Z (2024) https://doi.org/10.1117/12.3029191
Due to the privacy nature of student dormitories, video surveillance cannot be implemented. Smoking inside the dormitory is an important factor causing air pollution and fire hazards. Currently, there is no good solution to this problem. To address this issue, this study focuses on detecting key para-meters such as CO, TVOC, and PM2.5. It uses the KNN algorithm for multi-sensor data fusion to achieve smoking behavior warnings and alarms. The relevant data can be uploaded to the cloud platform using LoRa wireless technology for inspection by management personnel. The data can also provide strong sup-port for fire prevention. The smoking monitoring and alarm system studied in this paper can effectively monitor the air quality inside the dormitory, detect smoking behavior on time, and prevent fires and other safety accidents while protecting students' privacy. This system has high practical value and bro-ad application prospects.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310720 (2024) https://doi.org/10.1117/12.3029220
In the marine environment, the active sonar sends out the specific detection acoustic signal that is the input signal[1]. The detection acoustic signal changes over time and space and has a propagation loss during the propagation process. This propagation process can be thought of as a system. It is very important to find the output signal of the system. Since the energy of the signal is higher than the background noise, the conventional method is to find the maximum value according to the signal energy, but this method has certain shortcomings. This paper uses the method of Hilbert transform[2,3,4,5,6] to get the variable envelope. Then we find the rising edge and falling edge of the signal in the envelope. At last we find the starting point of the signal by the pulse width of the input signal.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310721 (2024) https://doi.org/10.1117/12.3029151
Several measuring instruments, including CCD photography stations and velocity-coordinate measuring equipment, were arranged at various distances in the ballistic range. To ensure consistency and accuracy, the coordinates of each instrument need to be unified into the ballistic range coordinate system. This paper presents a new method that utilizes a high-precision total station for measuring and positioning, establishing a spatial benchmark system for the ballistic range. The three-dimensional coordinate values of all the equipment's datum points were obtained through the total station and the measuring equipment. The transformation matrix, derived from the coordinates of three non-collinear points in the calibration system, is used to convert between the two coordinate systems. The 3D coordinate transformation process is implemented using the Rodrigues matrix, resulting in direct calculation formulas for the seven parameters. The calibration bracket was used to calibrate all the measuring equipment in the ballistic range, ultimately leading to the establishment of a 1,000-meter benchmark system for light weapons. Experimental results indicate that the spatial benchmark system, based on the total station, effectively eliminates errors caused by human operation and achieves a spatial coordinate precision of less than 15mm. The method's simplicity and efficiency render it suitable for 3D coordinate transformation at any given angle.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Hailun Jia, Lei Cao, Kang Xie, Jiajun Wu, Zhenjia Li, Xuan Cao, Guojie Tu
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310722 (2024) https://doi.org/10.1117/12.3029092
With the development of distributed fiber optic sensing, the recognition of different vibration modes has become increasingly important. In this paper, a distributed external-heterodyne φ-OTDR system is used for outdoor vibration acquisition and mode recognition. In the event recognition experiment, feature vectors are obtained using the Variational Mode Decomposition (VMD) algorithm. Support Vector Machine (SVM) is then used to classify the input feature vectors accordingly. Through this experimental method, it is possible to accurately identify five types of vibrations: stepping, tapping, wind blowing, passing subway, and passing car. Compared to traditional methods, the accuracy has improved from 72.50% to 91.25%, demonstrating promising application prospects.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310723 (2024) https://doi.org/10.1117/12.3029428
In the context of thermal fusion tubing operations in biopharmaceutical manufacturing, we are currently researching an instrument designed to autonomously carry out tubing connections, thereby reducing manual intervention and effectively preventing contamination. The device is centered around the STM32 as its core control chip, featuring a multi-axis control module and motor speed regulation to drive the moving components. Additionally, we have implemented a temperature control module utilizing a fuzzy self-tuning PID control method for more precise temperature regulation of the blades. To enhance user experience, a human-machine interface has been incorporated, supporting functions such as three-level authorization and parameter settings. Following the completion of device assembly, performance testing was conducted, revealing a maximum temperature deviation of 2.3°C. The sealing and sterility criteria are in compliance with the design requirements, demonstrating that the device meets the demands for automated thermal fusion tubing connections in aseptic tubing transfer systems.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310724 (2024) https://doi.org/10.1117/12.3029142
The Shock Pulse Method (SPM) has been widely applied in the diagnosis of rolling bearing faults and proven to be an efficient and concise approach. The limitations of the SPM approach, which requires the use of specialized SPM sensors, hinder its development. To address this issue, this paper proposes a fault diagnosis method for rolling bearings by integrating Multipoint Optimal Minimum Entropy Deconvolution Adjusted (MOMEDA) with SPM. The MOMEDA method is employed to identify periodic impulse components in the signal and construct an optimal filter for extraction. Subsequently, the SPM method is applied for quantification and diagnosis of faults in rolling bearings. The effectiveness and superiority of the proposed method are validated through extensive simulations of bearing fault signals and publicly available bearing fault signal datasets.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310725 (2024) https://doi.org/10.1117/12.3029294
There are a lot of noise signals for the early fault signals of rolling bearings, the fault feature extraction is inconvenient and the signal feature is weak and difficult to extract, process the extracted complex information using improved and optimized maximum correlation kurtosis deconvolution. The filter length L is optimized by grid search method with energy entropy as the standard function; The number of convolution periods T conforming to the characteristics of each fault is calculated by the empirical formula; The parameter optimization of shift number M is determined by experimental iteration. The improved empirical wavelet transform is applied to the filtered signal, and the adaptive selection of the number of modal components is proposed for feature extraction and fault analysis. Experiments show that the combination of parameter optimization maximum correlation kurtosis deconvolution method and improved empirical wavelet transform method can effectively analyze display the frequency and determine the fault status based on it.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310726 (2024) https://doi.org/10.1117/12.3029122
This article is based on the design and implementation of a PLC based urban rail transit screen door control system. This system uses PLC as the control core, and monitors the status and position of the screen door in real-time through sensors, achieving control commands such as opening, closing, and pausing the screen door. This system uses configuration software, which can achieve real-time monitoring, control instructions, alarm information, historical data, parameter settings, interface design, and data analysis of the system. By designing and implementing the system, the safety and stability of urban rail transit platforms can be improved, ensuring the safety of passenger travel.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Xiaoheng Zhang, Chuancai Wang, Zongtao Chi, Jidong Li
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310727 (2024) https://doi.org/10.1117/12.3029287
A temperature-adaptive Fiber Bragg Grating (FBG) demodulation system based on a long-wavelength Vertical-Cavity Surface Emitting laser (VCSEL) is designed to reduce power consumption and cost in this paper. The temperature-adaptive FBG system is described in detail through the sections of VCSEL characterisation and selection, selection of the methane absorption peak wavelength and matching with the laser scanning wavelength range, selection of the fiber grating wavelength and matching with the laser scanning wavelength range, and calculation of the FBG wavelength change. The experimental results show that the system has an effective scanning wavelength range of 3.7 nm in the operating environment of 10~40°C without temperature control, and it has the characteristics of low power consumption, low cost and miniaturisation, which can be used as a sensing node in wireless sensing networks.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Intelligent Communication Technology and Software Security
Shuang Zheng, Linmeng Tang, Jun He, Zhentao Wu, Chao Liu, Linhong Fang, Zhanzhong Li
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310728 (2024) https://doi.org/10.1117/12.3029096
This article examines the optimal layout of wireless sensors in shield tunnels by analyzing the network model of sensor nodes in a linear layout with multi-hop transmission mode, considering the mesh topology’s characteristics and energy dissipation. The study identifies the conditions for the lowest energy consumption in the linear layout and proposes practical engineering guidance schemes for wireless monitoring sensor nodes in shield tunnels under different requirements.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310729 (2024) https://doi.org/10.1117/12.3029102
For ocean remote sensing, target positioning over large areas of sea surface can be challenging, and traditional methods that rely on control points data may not be applicable in such cases. AIS data are commonly used as auxiliary data source of ocean remote sensing, which contains a wealth of attribute information of target. High-precision position information for a large number of targets is provided by the AIS equipped with differential GPS. AIS can be used as dynamic control points on the sea surface to contribute to target positioning in remote sensing image, meeting the on-orbit real-time positioning requirements of ocean remote sensing. This paper proposes a method for on-orbit target positioning and identification through the data fusion of optical image and AIS data. Firstly, the target position information provided by AIS is the broadcasted position over a period of time, while remote sensing image provide the instantaneous captured position. Therefore, it is necessary to calibrate the two types of data in terms of time and space. Then, the grid matching algorithm is used to establish the corresponding relationships between the same targets from the two different datasets, thereby achieving data fusion. Finally, target positioning is achieved over large areas of sea surface. In addition, the identification of target can also be facilitated by remote sensing image with the aid of AIS data, enabling precise positioning of abnormal target while obtaining their image information. In this paper, 5-meter resolution Jilin-1 satellite image and AIS data are used as data sources. The results show that, compared with the original data, the positioning error values calculated by this method are between 5-20 meters, with a reduction of over 70% in the RMSE value.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072A (2024) https://doi.org/10.1117/12.3029165
This study explores the application of a path planning algorithm based on Q-learning and eligibility traces in autonomous task execution for Unmanned Surface Vehicles (USVs). The algorithm aims to provide secure path planning for USVs in dynamic unknown environments, taking into account obstacles, potential threats, and multiple constraints. Initially, a detailed Markov Decision Process (MDP) model was designed. Subsequently, the introduced Q-learning and eligibility trace algorithm demonstrated significant advantages in path planning, utilizing the Upper Confidence Bound (UCB) strategy for action selection. Finally, simulation experiment results indicate that, compared to traditional Q-learning methods, the algorithm can more effectively plan paths for USVs, avoid threat areas, and achieve faster convergence.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072B (2024) https://doi.org/10.1117/12.3029324
A direction of arrival estimation method based on short time fractional Fourier transform (STFRFT) is proposed for wideband non-stationary radar and communication integration signals based on phase modulation. This algorithm utilizes the aggregation characteristics of integration signals in the fractional Fourier transform domain and the rotation characteristics of fractional Fourier transform (FRFT) to transform wideband non-stationary signals in the original time-frequency domain into narrowband non-stationary signals in the fractional Fourier transform domain, thereby obtaining a time-invariant fractional Fourier transform domain steering vector, and using the MUSIC algorithm for DOA estimation, effectively avoiding the impact of focusing error on the estimation results. The simulation results demonstrate the effectiveness of the proposed algorithm.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Zhendong Wang, LiChen Xiong, Junling Wang, Dahai Li
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072C (2024) https://doi.org/10.1117/12.3029105
In recent years, the ubiquity of mobile devices has witnessed a concomitant surge in malware attacks, with Android platforms emerging as predominant targets. The inherent open-source architecture of the Android operating system inadvertently paves the way for the proliferation of malevolent applications. Conventional malware detection methodologies, which predominantly hinge on manual feature extraction and juxtaposition against feature repositories, are notably resource-draining. Furthermore, an over-reliance on singular features often obfuscates the demarcation between benign and malevolent applications. To address this lacuna, this study propounds an innovative Android malicious code detection paradigm, amalgamating multifarious features with the prowess of deep learning. By decompiling APK (Android application package), we extract three static features: Opcode (operation code), API (application program interface) call, and Permission (permission). We use the N-Gram method to process the operation code to improve the extraction efficiency, filter out effective permissions to improve the classification accuracy, and select APIs related to permissions to increase the logic between features. After encoding, we input them into DNN for classification. Experiments on a dataset containing 8008 applications show that using multi-features and deep learning networks can significantly improve the accuracy of malware detection, verifying the superiority of this method in detecting malicious code.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072D (2024) https://doi.org/10.1117/12.3029125
Advanced Persistent Threat attacks(APT) are targeted attacks launched by professional hacker organizations using advanced techniques, resulting in significant harm. Therefore, there is an urgent need to detect APT malware and trace their associated organizations. This paper proposes an improved Transformer-based method for APT malware detection and attribution. In terms of detection, dynamic behaviors of APT malware are extracted, and an information filtering gate mechanism is applied to reduce redundant feature noise in the original Transformer model. A contrastive learning constrained model is used for information filtering, self-training, and optimization. In terms of attribution, static features of APT malware samples are extracted, global features of sequence data are established using the Transformer model, local features are constructed using Incremental Dilated Convolutional Neural Network, and features are fused using attention mechanism. This method outperforms the baseline methods.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072E (2024) https://doi.org/10.1117/12.3029238
In this paper, we investigate the performance for a mixed dual-hop free space optical-underwater wireless optical communication (FSO-UWOC) system, in which a source transmits information to a destination through a multi-aperture relay. In addition, a selection combining and a transmitting aperture select- ion protocols are adopted at the relay to process the received and transmitted signals. Considering two different types of detection techniques, and a decode-and-forward scheme, the analytical expressions for the average bit error rate are derived based on the Meijer’s G-function and Fox’s H-function for the considered system over Gamma-Gamma and mixture Exponential-Generalized Gamma fading channels. In addition, the accuracy of the derived analytical expressions is verified with Monte-Carlo simulation results.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072F (2024) https://doi.org/10.1117/12.3029387
In order to solve the problem of low positioning accuracy of single RSSI feature location algorithm, the multi-layer perceptron (MLP) fingerprint matching algorithm is enhanced through a combination with Round-Trip Time (RTT). The traditional MLP fingerprint matching algorithm based on multi-layer perceptron only uses the feature of RSSI, and the obstacles in the location space are easy to interfere with the RSSI signal and impact the accuracy of positioning. In order to solve the above problems, the MLP fingerprint matching algorithm based on multilayer perceptron is improved in this paper, RTT is added as the second eigenvalue, regression is used to predict the distance of unknown nodes from the Access Point (AP) as well as the input sequences of Received Signal Strength Indicator (RSSI) and Round-Trip Time (RTT). The predicted outcomes are then subjected to a weighted fusion process, following which the coordinates of the sample nodes are determined through mathematical calculations based on the sample output. The improved algorithm solves the interference problem at the same time. The location accuracy is further improved.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Yong He, Lin Lu, Hanjie Yuan, Guangxian Ye, Tianhang Jiang, Liang Chen, Haiao Tan, Gaofeng Liao, Yanchao Zeng, et al.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072G (2024) https://doi.org/10.1117/12.3029318
In order to solve the problem of insufficient computing power of edge computing equipment, this paper draws on the lottery ticket hypothesis theory, through unstructured global pruning of the network and using the pruning network of the previous stage to sparsely distill the pruning network of the current stage, while maintaining the network sparsity. At the same time, the heuristic information of the pruning network of the previous stage is used to help the pruning network recover the parameters that were wrongly pruned, and then the two are combined to obtain the output network of the current stage, so that the unstructured pruning network is obtained after several rounds of iteration. Then it is pruned by structured filter to enable the network to combine the advantages of structured pruning and unstructured pruning, so as to take into account the accuracy and acceleration effect of the network. It is verified on the yolov7 algorithm. The accuracy is almost unchanged compared with the method before pruning, and the speed is improved by more than 45 %, which has achieved very good performance.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072H (2024) https://doi.org/10.1117/12.3029272
Recommendation technologies are facing new challenges in mobile environments due to the complexity of user behaviors in dynamic contexts. In this paper, we focus on the integration of internet content access with user natural behaviors, and propose a context-aware collaborative recommendation paradigm for user spatial activities in mobile environments. In the proposed approach, potential user behavior patterns with contexts and preferences are discovered from historical logs. Then, temporal activity prediction and service recommendation tasks are performed according to the target user’s real-time behavioral contexts using an improved collaborative filtering algorithm. Analysis and experiments indicate that our approach can effectively improve the quality of service recommendation in mobile computing environments.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072I (2024) https://doi.org/10.1117/12.3029155
With the development of technology, the application of positioning techniques has become increasingly widespread. However, in indoor or specific situations, due to the complexity of the environment, it can be challenging to apply outdoor positioning techniques. Therefore, research on indoor positioning techniques is highly necessary. Ultra-Wideband (UWB) technology, as an indoor positioning method, can address many indoor positioning scenarios. However, when facing obstacles, it can still lead to non-line-of-sight (NLOS) situations, resulting in less accurate positioning. To address this issue, this paper proposes an approach that combines Discrete Wavelet Transform (DWT) and Convolutional Neural Networks (CNN). Firstly, it extracts coefficients from Channel Impulse Response (CIR) signals using DWT. Subsequently, these coefficients are input to a CNN to explore deep features, ultimately distinguishing between Non-Line-of-Sight (NLOS) and Line-of-Sight (LOS) signals based on these features. Experimental results demonstrate that this method achieves better classification accuracy compared to other approaches.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072J (2024) https://doi.org/10.1117/12.3029373
To improve the accuracy of autonomous driving, a fusion algorithm is needed for vehicle localization. I propose the Extended Kalman filter fusion model, which has been experimentally proven to be more powerful. The paper compares three algorithms, namely linear regression, decision tree, and Kalman filtering, on their effectiveness in fusing GPS and IMU sensor data for prediction using the KITTI dataset. The results show that Kalman filtering provides the best prediction performance. Additionally, the article evaluates the noise resistance capabilities of the Kalman filter and finds that it performs well in dealing with noise. However, I note that Kalman filtering still needs improvement in dealing with highly nonlinear systems and determining noise covariance. To address these issues, it is recommended modifying the values of variance, noise covariance, state covariance, and dt. The paper briefly introduces the Unscented Kalman filter and proposes possible different solutions and ideas. In conclusion, experts, policymakers, and the general public need to continue exploring and developing better solutions to the vehicle localization problem in the rapidly developing field of autonomous driving.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072K (2024) https://doi.org/10.1117/12.3029190
With the proliferation of home Internet devices and the looming specter of IPv4 address depletion, Internet Service Providers (ISPs) are resorting to large-scale Carrier-Grade Network Address Translation (NAT) deployments as a viable solution. While IPv6 addresses offer a long-term remedy, the coexistence of IPv6 and IPv4 remains a short-term reality, underscoring the continued significance of NAT. Software-Defined Networking (SDN) is renowned for its flexible management and configuration features. Integration of NAT functionality within SDN controllers streamlines the process of NAT traversal. This paper introduces the service framework of two operational modes tailored for common NAT application scenarios. The modes encompass intranet-to-extranet operation and intercommunication between different intranets. In our proposed framework, controllers and switches assume dual roles as proxy servers and NAT gateways, ensuring the network delivers efficient services while seamlessly adapting to evolving 5G core network demands.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Shasha Shi, Qingsong Zhou, Jialong Qian, Shujie Shi
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072L (2024) https://doi.org/10.1117/12.3029148
Intelligent radar is an important topic in the field of cognitive electronic warfare, and the application of reinforcement learning in intelligent radar anti-jamming decision-making has been a recent research focus. This paper proposes an antijamming matrix model composed of multiple radar configurations and anti-jamming patterns, and analyzes the path planning problem in radar anti-jamming decision-making using the Q-Learning algorithm. Simulation experiments demonstrate that using reinforcement learning allows the model to plan paths based on the environment autonomously and select the optimal path to achieve the best anti-jamming state ultimately.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072M (2024) https://doi.org/10.1117/12.3029110
The multifunctional radar (MFR) possesses robust anti-jamming capabilities, and effectively jamming with it is an urgent problem that needs to be addressed. This paper first analyzes the process of cognitive radar antagonism and subsequently constructs a jamming decision system with cognitive abilities based on real battlefield environments. An algorithm based on proximal policy optimization (PPO) is employed for the jamming decision algorithm to determine the optimal jamming strategy. Through simulation experiments, it has been demonstrated that the PPO-based jamming decision algorithm can learn the most effective jamming strategy in dynamic game conditions between radar and jammers. It exhibits faster convergence speed compared to traditional strategy gradient methods.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072N (2024) https://doi.org/10.1117/12.3029217
At present, the increasingly complex electromagnetic environment, the coexistence of multiple constellations and the complexity of interference signals such as adjacent frequency signals faced by mobile terminals pose a serious challenge to their navigation application experience. In this paper, the influence of adjacent frequency interference signal on GNSS positioning performance was deeply studied, and a GNSS adjacent frequency interference conducted test system was developed based on the adjacent frequency sensitivity test method. According to the system, the interference signal generator is used for simulating noise signals of adjacent frequency of GNSS satellite signals, and the carrier-to-noise ratio degradation of a tested device before and after scrambling is tested, so that the quantitative evaluation and analysis of the anti-interference performance of all GNSS modes and frequency bands supported by a mobile terminal are realized. The test results showed that the measurement accuracy of the proposed test system is better than 0.1 dB.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072O (2024) https://doi.org/10.1117/12.3029346
Fiber Bragg gratings have attracted extensive attention and research in the field of fiber optic sensors due to their low cost, ease of processing and improvement, and excellent sensing performance. They have been applied in temperature sensing, gas concentration sensing, bending sensing, and other fields. By means of weak fiber doping, polymer fiber manufacturing, parallel distribution of gratings, and manufacturing of microstructured fiber gratings, functions such as phase shifting, temperature compensation, temperature insensitivity, ultra-high temperature sensing, and bio-absorbable materials can be achieved.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072P (2024) https://doi.org/10.1117/12.3029304
In response to the problem of spectral leakage during step response testing of DC current transformers, a DC electronic transformer testing platform is developed to synchronously collect standard source signals and tested transformer signals. After sampling is completed, the discrete sampling values are algorithmically processed. After interpolation processing of the sample signal, the amplitude and gain of the main frequency component and sub frequency component, as well as the amplitude of the main frequency component, are analyzed. The relationship between the amplitude of the main frequency signal and the amplitude of the original signal changes with the ratio of the sampling frequency to the frequency of the original signal.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072Q (2024) https://doi.org/10.1117/12.3029182
Compared with static QR codes, dynamic QR codes have outstanding advantages such as information redefinition and re coding, and their application scenarios and methods are more flexible and varied. In order to further improve the information security threshold of this type of QR code and expand its value-added service functions, this article proposes a novel dynamic QR code technology with anti-replication properties, provides the generation method of this QR code, and compares and analyzes several typical generation algorithms, including UUID, data encryption, digital watermarking, etc., after experimental testing, the information security of this technology in the application process can be effectively improved. At the same time, potential security risk factors during the dynamic QR code generation process were analyzed, and information security protection measures based on multiple combinations of data encryption, dynamic keys, and identity verification were proposed. This technology can be widely applied in fields such as anti-counterfeiting of product packaging information, information traceability, and value-added services.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072R (2024) https://doi.org/10.1117/12.3029300
The imperative of addressing the growing need for enhanced capacity, efficiency, and rapid communication in space networks has emerged as a critical subject within contemporary communication technology. This paper presents a novel approach, referred to as the lightweight satellite-borne terahertz (THz) communication space information-centric network (LSICN), which aims to effectively utilize the efficient transmission benefits of the information-centric network (ICN) and accommodate the specific attributes of high-speed, high-capacity communication in THz networking. This study provides an overview of essential technologies that address the aforementioned difficulties. These technologies encompass THz channel modeling, network topology reconstruction, lightweight routing techniques, and lightweight robust access control. Finally, several developmental directions for the LSICN are discussed.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072S (2024) https://doi.org/10.1117/12.3029433
In response to the unified monitoring challenges throughout the entire lifecycle of data production, collection, transmission, storage, utilization, sharing, and disposal within the industrial Internet environment, we proposes a comprehensive, lifecycle-oriented method for anomaly detection in data security. Tailored to diverse task scenarios, the approach employs a combination of multidimensional dynamic data behavior baseline analysis and a feature repository for anomaly behavior detection. This method offers a solution for data anomaly detection that spans the entire lifecycle, providing comprehensive coverage, precise management, accurate detection, and ease of implementation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Yongqing Liu, Qiang Li, Yanbin Jiao, Youyong Chen, Ming Cheng
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072T (2024) https://doi.org/10.1117/12.3029328
In the cloud computing environment, network terminal data has the characteristics of large quantity and real-time changes. In order to ensure the security of network terminal data, a network terminal data security protection system is designed in the cloud computing environment. The system includes hardware modules such as intrusion detection, vulnerability scanning, and cloud security management, which can ensure that only authorized users can access data and achieve recognition and prevention of malicious behavior. On the basis of hardware design, a hybrid encryption algorithm is adopted to encrypt network terminal data, further improving system performance and security, and protecting data security in cloud computing environments. The experimental test results show that the system has a low false alarm rate, a high malicious attack blocking rate, and a malicious attack detection rate, which can effectively ensure the security of network terminal data.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072U (2024) https://doi.org/10.1117/12.3029173
As known that fast cyclic redundancy check aided successive cancellation List (fast CA-SCL) decoding algorithm of polar codes can realize the fast decoding function by using different types of bits. Aiming at the problems of high complexity and large delay of fast CA-SCL decoding algorithm, an optimal design scheme of adaptive list fast CA-SCL decoding (ALF-CA-SCL) decoding algorithm is proposed. In ALF-CA-SCL algorithm, an optimization strategy for flexible change of list length is designed, which can ensure the reliability of decoding and reduce the unnecessary decoding complexity or system transmission delay. Simulation results show that the proposed algorithm can enhance the system efficiency of by 3 to 6 times compared with fast CA-SCL algorithm, under the condition of equivalent error performance.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072V (2024) https://doi.org/10.1117/12.3029363
With the rapid development of the power grid, multiple transmission lines in the same tower are widely used, which can reduce the comprehensive cost and the demand of the line corridor, but also increase the probability of power outage maintenance operators mistakenly boarding adjacent live lines, resulting in electric shock casualties. In view of this situation, this paper puts forward a kind of anti-error boarding device installed on the pole tower, which has the function of wireless communication and background management system. When the line is live, the anti-error boarding device is locked, which can effectively prevent the operator from straying into the live side. When the line has a power outage maintenance task, the device is unlocked. The device forces operators to work in accordance with established safety procedures, which can effectively avoid safety accidents and provide safety guarantee for power maintenance operators.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Chanjuan Tang, Rong Tian, Bingjie Liu, Bingxin Tian, Fan Yu, Jiuchun Ren
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072W (2024) https://doi.org/10.1117/12.3029263
To address the challenges of wiring operation and maintenance in substations and the security issues associated with wireless data acquisition in smart grid environments, we have developed a secure wireless data acquisition system for substation monitoring. This system integrates 5G, short-range wireless communication, Internet of Things (IoT) technology, and video processing to establish a secure and unified access model. The system comprises an intelligent gateway deployed at the wireless network boundary, equipped with hardware encryption cards for terminal authentication, data encryption, and information security. The gateway seamlessly integrates with the IoT system architecture, encompassing perception, edge computing, transport, and service layers. A security access module for the terminal is introduced in the design, taking into account the security constraints in the substation environment. This module ensures encrypted data transmission between the gateway and the terminal, providing a secure access solution for video and sensors.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072X (2024) https://doi.org/10.1117/12.3029146
In order to realize real-time monitoring and online control of industrial process control, a multi-state monitoring and feedback control system based on optical fiber sensor network is designed. The system is composed of frequency sweep laser, fiber demodulation module, PC processing module, fiber sensor network and state control unit. A multi-state monitoring algorithm is proposed, which combines the FBG wavelength response values at each point of temperature and strain with weights, and then maps and models with four common state anomalies, and then gives feedback adjustment parameters through state analysis. In the experiment, the temperature field inside the tank and the stress field outside the tank are collected, and the online detection of the strain 0-5000με and the temperature 30-150°C is calibrated. The results show that the mean value of the corrected strain sensitivity is 0.499pm/με and the mean value of temperature sensitivity is 7.425pm/°C. The feedback control has the ability to adjust the state fluctuation online, and the feedback time of different abnormal types is different. The deviation of temperature and strain wavelength after correction in four cases is less than ±1°C and ±50με The feasibility of the system is verified.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072Y (2024) https://doi.org/10.1117/12.3029091
There has been a growing interest in developing machine learning algorithms that can handle non-Euclidean data. We introduce a causal generating process between parent nodes and child nodes based on multivariate tensor regression. Additionally, we propose a two-stage causal discovery approach involving regularized generalized canonical correlation analysis and greedy hill-climbing search. By utilizing numerical representation in the shared Euclidean subspace, we are able to more accurately discover causal relationships between heterogeneous non-Euclidean variables. The effectiveness of the algorithm is demonstrated using a dataset of mixed functional and compositional data, as well as empirical research conducted on real-world industrial sensor data.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072Z (2024) https://doi.org/10.1117/12.3029210
Fueled by the capabilities of artificial intelligence and cloud computing, the development trend of future networks towards intelligence and marginalization is becoming increasingly evident. The knowledge-driven learning model as the basis of future network intelligence, fully utilizes various direct and indirect knowledge and automatic learning of knowledge variable values to achieve minimum resource cost and optimal communication capability. Correspondingly, security of the future wireless network faces new challenges. Traditional security schemes are generally composed of encryption, authentication, access control, and other modules. These schemes often require complex and centralized management systems, which are vulnerable to impersonation attacks, distributed denial of service attacks, and other network attacks. In recent years, blockchain technology has become a powerful tool for solving the above-mentioned problems due to its decentralized and tamper-resistant characteristics, that will effectively enhance wireless network defense capabilities. Many recent studies have explored using blockchain-based solutions in wireless networks to enhance the security capabilities of wireless networks by implementing distributed identity authentication, hierarchical access control, data security sharing, privacy protection, and other techniques. But the performance of blockchain has always been a fatal issue. This paper investigates the existing blockchain-based wireless network security solutions and sorts and categorizes them. Targeting the Characteristics of knowledge-driven wireless networks, this paper designs a partitioned and layered blockchain security architecture, and conducts experiments and security analysis on the architecture, the architecture can improve the transaction processing speed to a certain extent.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310730 (2024) https://doi.org/10.1117/12.3029134
To estimate the three-dimensional position and velocity of a moving target in multistatic radar system, this paper proposes an efficient localization algorithm using time delay, Doppler shift, and angle of arrival as observations. This algorithm contains three stages. In the first stage, a rough estimate is obtained by introducing redundant parameters and combining the weighted least square method. Then, the rough value is refined based on the constraint relationship in the next stage. Finally, the revised result from the previous process serves as the initial value for the Quasi-Newton method, which iteratively refines the estimate to achieve higher accuracy. Simulations show that the proposed algorithm maintains sufficient estimation accuracy when locating the far-field moving target and the performance can achieve the Cramér-Rao Lower Bound (CRLB) under higher noise levels.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310731 (2024) https://doi.org/10.1117/12.3029214
Adaptive modulation and power control technology is an important technique in carrier communication, which can achieve a good balance between improving communication system performance and rational resource allocation. Because the delay and fading of each channel in the communication system are different, in this process, the selection of modulation mode needs to consider channel fading, transmission power, reception signal to noise ratio and other factors. This article studies an adaptive modulation and power control algorithm based on signal-to-noise ratio, with signal noise ratio as an important parameter. It can adaptively select modulation methods and transmission power based on channel conditions, thereby improving communication system performance without increasing channel capacity and system complexity. The research results indicate that after optimizing the algorithm in this article, the performance has been significantly improved in terms of error rate, throughput, and communication delay.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310732 (2024) https://doi.org/10.1117/12.3029099
In complex indoor environments, achieving satisfactory pedestrian localization using a single positioning technique proves challenging. For instance, Ultra-Wideband (UWB) positioning encounters non-line-of-sight errors in intricate indoor settings, while Pedestrian Dead Reckoning (PDR) technology with inertial sensors is susceptible to cumulative drift errors over time. Consequently, this paper introduces the Unscented Kalman Filter (UKF) algorithm to integrate UWB technology with PDR technology. The improved PDR-derived pedestrian localization information is employed as the state vector for the UKF algorithm, and the positioning information obtained through enhanced UWB technology serves as the observation vector for the UKF algorithm. This combined approach effectively corrects pedestrian position information, ultimately yielding more accurate pedestrian locations. Research results indicate that the proposed algorithm achieves a root mean square error of 3.64 centimeters. In comparison to a standalone UWB algorithm, this method demonstrates superior positioning accuracy in complex environments.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310733 (2024) https://doi.org/10.1117/12.3029253
Multi-target DOA estimation by single vector hydrophones is strongly influenced by environmental factors. To further improve the accuracy of azimuth estimation. Azimuth of target sound source can be computed by single vector hydrophone. Receive the radiated noise emitted by multiple ships using a single vector hydrophone. Apply the Hilbert transform to the received sound pressure signal, followed by Fast Fourier transform (FFT) to obtain the multi-target line spectrum. Utilize cross-spectrum goniometry to compute the azimuth of each ship at every frequency point. And then the azimuth of each target is obtained by frequency analysis. Finally, the multi-target time azimuth diagram is drawn by scatter plot.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310734 (2024) https://doi.org/10.1117/12.3029403
As an important equipment in the power system, the safe operation of the transformer directly affects the safety of the power grid. Winding deformation is a common cause of transformer faults. The monitoring of winding deformation is an important research content in transformer condition monitoring. However, there is currently no effective monitoring method for transformer winding deformation. With the rise of distributed optical fiber sensing technology, the optical fiber sensing technology based on Brillouin scattering technology is used to complete the real-time monitoring of winding deformation by laying optical fiber outside the winding wire. The optical fiber composite wire model and the built-in optical fiber 35 kV winding model were prepared under laboratory conditions. Four kinds of direction deformation were applied to the wire model to explore the feasibility of the sensing technology. The winding model was artificially deformed, and the Brillouin frequency shift curve of the optical fiber before and after deformation was compared. The effectiveness of distributed optical fiber sensing technology in measuring winding deformation was successfully verified.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310735 (2024) https://doi.org/10.1117/12.3029379
To reduce the impact of transmission line icing on the safety of power grid, this article proposes a transmission line icing thickness detection technology based on distributed optical fiber sensing and Φ-OTDR. Firstly, the fundamental physical characteristics changes of transmission line and the frequency characteristics changes of internal signal under transmission line icing are analyzed. Secondly, this article analyzes the distributed optical fiber sensing signal to obtain the phase difference of Ray-leigh backscatter (RBS) signal by Φ-OTDR. By performing a fast Fourier transform on the phase difference of RBS signal during vibration, we can observe the natural frequency of transmission line. On the basis of the natural frequency relationship before and after icing, transmission line icing thickness can be calculated. Finally, simulation results demonstrate the effectiveness of the proposed technology.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310736 (2024) https://doi.org/10.1117/12.3029215
Non-contact vital sign health monitoring based on FMCW millimeter wave radar has received widespread attention because it can unobtrusively provide information about individuals' physical and mental states. Particularly, by continuously measuring a person's instantaneous heart rate over time, the activity level of the autonomic nervous system can be estimated. However, existing studies on non-contact measurements using millimeter wave radar typically focus only on heart rate variability under a single posture. This paper proposes a non-contact vital sign monitoring algorithm that integrates behavior recognition and heartbeat signal reconstruction. The algorithm utilizes millimeter wave radar to identify three common postures in daily life: standing, sitting, and lying down. Subsequently, it non-intrusively measures the heartbeat waveforms and conducts HRV analysis from the reconstructed heartbeat waveforms. In the study, the errors in HRV of RMSSD were 3.5ms for the sitting posture, while it is 5.8ms in the lying position, and 10.9ms in the standing posture.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310737 (2024) https://doi.org/10.1117/12.3029126
This article presents an improved method for denoising point clouds that combines the DBSCAN clustering algorithm and filtering. Firstly, a LiDAR is deployed in the target acquisition area to collect initial point cloud data. Then, the improved DBSCAN clustering algorithm is used to classify the point cloud data while removing scattered data points, resulting in a preliminary denoised point cloud dataset. Finally, the improved bilateral filtering algorithm is applied to process the preliminary denoised point cloud dataset, resulting in accurate point cloud data.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310738 (2024) https://doi.org/10.1117/12.3029437
At present, most of the monitoring systems for track circuits in China are implemented using electromagnetic communication principles, but they are more susceptible to electromagnetic signal interference than other track circuit monitoring systems. So preventing electromagnetic interference is particularly important.
This article studies a track circuit axle counting monitoring system based on fiber optic sensing technology, which realizes the monitoring of whether the track is occupied through this system. The system collects and outputs data through a fiber optic regulator, and the analog-to-digital conversion circuit processes the data transmitted by the fiber optic regulator and the voltage data of the track circuit to output the corresponding wavelength and voltage, which are finally displayed on the terminal display. Finally, through system simulation, verify the purpose that the system aims to achieve.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Qiang Sun, Jiangsheng Yu, Zhenliang Chen, Xi Zhang, Qihao Zhong
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310739 (2024) https://doi.org/10.1117/12.3029135
In order to improve the three-dimensional positioning accuracy of sensor to converter station inspection robots in unknown environments, a three-dimensional positioning algorithm for converter station inspection based on multi-sensor filtering was studied. Construct a motion information sensing model for the inspection robot in the converter station based on correcting multiple sensors, and use laser radar sensors and IMU sensors to respectively sense the three dimensional coordinate information, angular velocity, and acceleration information of the inspection robot in the converter station; Use the multi sensor correction method based on neural networks to correct the drift error of perceptual information; Through the inspection 3D positioning algorithm based on Kalman filter, the corrected perceptual positioning information is fused and filtered, and the 3D coordinates of the inspection robot in the converter station are estimated to complete the auxiliary work of the inspection 3D positioning in the converter station. In the experiment, the algorithm can locate the dynamic three-dimensional coordinates of the inspection robot in the converter station, and the mean square error of the positioning results is less than 0.05.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Artificial Intelligence and Information Recognition Technology
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073A (2024) https://doi.org/10.1117/12.3029141
Failure of wind turbine blades is a major problem affecting the sustainable and healthy development of wind power generation, and also hides huge safety hazards and environmental problems. In order to detect the faults of wind turbine blades, this paper proposes a wind turbine blade fault identification and detection method based on the improved YOLOv5s algorithm. Firstly, a variable convolutional network is used to replace the ordinary convolutional network in the feature extraction network of the original YOLOv5s, which makes the model lightweight and maintains good detection accuracy; secondly, the Wise Iou loss function is used to solve the imbalance problem of the defect categories in the dataset and to make the target detection model converge; lastly, tests are carried out in the dataset of the wind turbine blades and the experimental results are compared with those of the other datasets. The experimental results show that the algorithm is effective in detecting defects. The experimental results show that the detection accuracy of the algorithm reaches 93.6%, which verifies the effectiveness and accuracy of the improved YOLOv5-based algorithm.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Wenhao Xian, Qingjie Qi, Yingjie Liu, Changbing Chen, Jie Liu
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073B (2024) https://doi.org/10.1117/12.3029376
In mining environments, communication is blocked and the environment is complex, making autonomous detection of robots much more difficult. However, due to the dangerous and harsh working conditions, inspection and emergency rescue in mine is one of the key areas in which robots are urgently needed to replace manual labour. In this paper, an intelligent robot with multi-sensor system is established for daily inspection and emergency rescue tasks in complex environment in coal mine. Furthermore, in order to achieve accurate localization of robot in the environment, a multisource data fusion localization method based on improved particle filtering and VIO is developed, and experimental results show that the proposed algorithm has good performance.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073C (2024) https://doi.org/10.1117/12.3029157
Estimating human body pose and shape from a single-view image has been highly successful, but most existing methods require a model with a large number of parameters that are difficult to run on low performance devices. Light weight networks are struggle to extract sufficient information for human pose and shape estimation, making accurate prediction challenging. In this paper, we propose a lightweight model for predicting human body shape and pose parameters of a parametric human body model. Our method comprises a lightweight multi-stage encoder based on Litehrnet and Shufflenet, and a decoder composed of cascaded MLPs based on human kinematic tree, which achieves comparable performance to HMR while the model size is only one-ninth of HMR. In addition, our model can achieve an inference speed of 19.2 times per second on the Qualcomm Snapdragon 888+
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073D (2024) https://doi.org/10.1117/12.3029265
In recent years, there has been significant development in research on methods for autonomous driving decision-making based on deep reinforcement learning, including Deep Deterministic Policy Gradient (DDPG) , Proximal Policy Optimization (PPO) , and others. Reinforcement learning strategies based on proximal policy optimization often suffer from poor performance due to getting trapped in local optima and inefficient learning. To address the challenges of proximal policy optimization in autonomous driving, we propose an autonomous driving decision-making algorithm based on adaptive curiosity mechanism and experience replay. Firstly, we introduce a mechanism for adaptive curiosity adjustment based on episode length to address the issue of local optima in proximal policy optimization. By incorporating curiosity mechanisms, the algorithm's exploratory nature is enhanced. Additionally, to ensure safety, we impose constraints on the curiosity coefficient using variations in episode length. Secondly, to overcome the low sample utilization and inefficient learning in PPO, we combine it with an experience replay mechanism, enabling faster learning of superior policies and improving learning efficiency. In simulation experiments, our algorithm efficiently explores a better and safer driving strategy.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073E (2024) https://doi.org/10.1117/12.3029150
Data obtained from depth camera scans of the human body often includes noise, and registering consecutive frames can lead to errors due to inevitable non-rigid movements during scanning. To address this, we propose a method for 3D human body reconstruction based on human joint points. Initially, the Kinect DK sensor captures data from different angles, which is then preprocessed to extract the main body point cloud. Subsequently, segmented human body data, combined with pose-related joint points, guides the point cloud data of the body's surface. Using an enhanced iterative closest point algorithm, we achieve precise registration of the main body point cloud, resulting in an accurate 3D human body model. Experimental results show that this method rapidly generates realistic, finely detailed, and accurately dimensioned 3D human body models.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073F (2024) https://doi.org/10.1117/12.3029143
As a simple and effective way of exercise, running is favored by people. At the same time, people are paying more and more attention to the correctness and standardization of running posture. Traditional posture recognition methods rely on the experience of professional coaches and manual evaluation, but this method is not only time-consuming and laborious, but also subjective. In response to this problem, this study aims to explore a running posture recognition method based on bone node detection technology to provide accurate and real-time posture evaluation for runners. First, by studying the runner's running video, and using deep learning methods to detect bone nodes. Then, a runner's posture recognition model is established to identify different running postures by analyzing the spatial relationship and dynamic characteristics between skeletal nodes. The experimental results show that the method can identify the running posture efficiently and accurately with a variety of latest methods on multiple data sets. This study provides a feasible posture assessment method for runners, which is of great significance for improving running effect and preventing running injury.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073G (2024) https://doi.org/10.1117/12.3029154
In order to realize the high-precision requirements of robotic multi-layer multi-pass welding and to improve the accuracy of weld bevel information recognition, a system based on laser vision for three-dimensional weld bevel recognition and reconstruction is established. Through the line structure optical sensor connected to the welding gun at the end of the welding robot, the welding seam is collected, and the noise generated by the reflections of the weldment and transmission interference is effectively reduced by threshold segmentation, adaptive selection of the region of interest, joint filtering processing, extraction of the center line and refinement of the collected data; Through the processed data still exists a small part of the existence of interference noise, affecting the subsequent recognition accuracy, the point-line projection method will be processed to obtain smooth image information; In its difference calculation, to obtain the feature point mutation information, to realize the accurate extraction of feature points; Through the transformation relationship between coordinate systems, the transformed data information is obtained, followed by computational solving to obtain the characteristic information of the 3D weld seam; The position calculation of the sensor's first frame of light bar information is carried out through the acquisition of the conversion relationship to scan at the optimal position, and the sensor and robot are controlled to acquire at the optimal parameters to obtain the highly reproducible 3D weld bevel's morphology. The experimental results show that the average error of bevel width and height after weld recognition is 0.1607mm and 0.1592mm, which meets the accuracy requirements of robot welding; Meanwhile, the reconstructed 3D weld bevel morphology has high reducibility, which provides a reference for realizing intelligent and high-precision autonomous welding.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073H (2024) https://doi.org/10.1117/12.3029163
Butt joints and angle joints exist in all types of industrial production and are often taught for mass production, while the efficiency of teaching is greatly reduced for small batches and frequent changes in the welding environment. Aiming at the problems of small-lot and other production, a 3D camera-based fast identification system for common weld seams is proposed, which is able to quickly identify the weld seam position information. In this paper, based on the 3D large field of view camera and welding robotic arm, first measure the actual accuracy of the 3D large field of view camera, and then calibrate the camera by hand and eye, the calibration error is within the usable range, and finally propose a rapid identification algorithm based on the point cloud weld to identify the weld starting point. Experimental verification shows that the position error is less than 2.79mm to meet the welding process requirements.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073I (2024) https://doi.org/10.1117/12.3029140
Existing deep learning algorithms usually process only a single detection task in environment perception, which cannot meet the driving needs of driverless vehicles. To this end, a new multi-task environment perception network is designed, which can simultaneously complete vehicle detection and lane line detection; Taking YOLOv8 as the backbone network and integrating the latest C2f module, the efficient extraction of image features is realized; the neck section adopts BiFPN (Bidirectional Feature Pyramid) structure for better feature fusion and semantic preservation; in loss calculation, αIoU is fused to improve the detection accuracy; based on semantic segmentation, the UCC module is utilized to design an efficient lane line detection branch. Comparison experiments show that the average vehicle detection accuracy reaches 80.0%, and the IoU of lane line detection is 27.10%, which is better than other multi-task perception algorithms in terms of comprehensive performance.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073J (2024) https://doi.org/10.1117/12.3029309
Aiming at the problem of poor fitting effect of key points of the driver's mouth and eyes during driver fatigue monitoring, a convolutional neural network PFLD-rep based on improved PFLD was proposed. First, the backbone network is structurally re-parameterized, which can not only retain multi-scale parameters but also achieve the calculation speed of a single branch; then introduce the idea of heat map regression to the auxiliary network to improve the spatial expression ability of the network in the mouth and improve fitting. Effect; Add the opening angle of the eyes and mouth to the loss function, and replace the original L2_loss with Wing_loss loss to increase the network's attention to mouth deformation; later, a high-precision comprehensive fatigue judgment criterion will be determined through experiments. The final experimental results show that the IPN value of the PFLD-rep algorithm in the 300W data set reaches 3.68. The algorithm also has a high fitting effect in faces with large deformations, and can be implemented when vehicle-mounted hardware equipment requirements are low. Higher precision monitoring effect.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073K (2024) https://doi.org/10.1117/12.3029327
Wearable sensors have become essential platforms for research on human activity recognition (HAR) due to their advantages such as compact size, low power consumption, and non-invasive nature, ensuring continuous and privacy-conscious data acquisition. In this paper, a HAR architecture using Machine Learning (ML) technique based on data collected from wearable sensors is proposed to perform high performance for accurate recognition of human activities in real-life scenarios. To address the challenge of accurately distinguishing similar forms of daily activities, a feature library consisting of 55 feature functions has been constructed, and the Maximum Relevance Minimum Redundancy (mRMR) algorithm is employed to select the most informative and relevant features for activity classification. Experimental results indicate that the combination of data from multiple sensors and the dynamic selection of features significantly improve the performance of the HAR system, as they provide a more comprehensive and diverse set of information. The numerical results show that the human activity recognition framework proposed in this paper can achieve an accuracy of 98.53% on the self-collecting dataset.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073L (2024) https://doi.org/10.1117/12.3029448
Embodied intelligence is an emerging research field aimed at enabling intelligent agents to interact and collaborate with their environment in real-time. Large Language Models (LLMs) play a crucial role in the research and application paradigm of embodied intelligence. By utilizing LLMs as controllers, the powerful language processing capabilities can be leveraged to achieve planning and control of intelligent agents. This paper introduces and combines the open-source program PromptCraft released by Microsoft and the AirSim drone simulation platform to specifically describe how to construct a collaborative drone system using LLMs as controllers. The performance and effectiveness of the system are validated through experiments and case studies. By elucidating these findings, we gain deeper insights into the research and application paradigm of LLMs in the field of embodied intelligence. This provides valuable references and guidance for future intelligent agent design and development.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073M (2024) https://doi.org/10.1117/12.3029179
In this paper, the problem of parameter estimation and imaging of ground accelerated moving targets with frequency modulated continuous wave synthetic aperture radar (FMCW SAR) is studied. First, a fourth-order moving target echo model is established in FMCW SAR system, and the coefficient estimation of the azimuth signal based on adaptive local polynomial Fourier transform (ALPFT) is proposed. Secondly, the range migration term is corrected by generalized Keystone transform and Hough transform. Finally, by compensating the high-order Doppler phase and azimuth resampling the edge moving targets, all moving targets in the scene can be focused well. Simulation results verify the feasibility and effectiveness of the proposed method.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073N (2024) https://doi.org/10.1117/12.3029388
Based on the flexible pressure sensor, the pin sensor with pressure data as the monitoring quantity was developed by integrating the CC2530F256 ad hoc network communication module. The use of low-power technology to design software programs reduces the power consumption of the hardware system and improves the battery life of the hardware system. The effectiveness and reliability of the pin sensing monitoring system are verified by experiments, which makes it possible to monitor the pin status online. The sensor monitoring system has the advantages of low power consumption, low cost, small size, high reliability, and online monitoring. It can be widely used in the defect monitoring of insulator string pins of UHV transmission lines, and improve the level of digital operation and maintenance of UHV lines.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073O (2024) https://doi.org/10.1117/12.3029090
In this paper, a new azimuth resampling algorithm is proposed to eliminate azimuth spatial variability for high-speed diving forward-looking line array synthetic aperture radar (HDFLLA-SAR). Specifically, this algorithm utilizes least square fit (LSF) method to describe the relationship between azimuth space-variant phase and azimuth space-variant component, and compensates for azimuth spatial variability through resampling interpolation. Simulation experiments validate the effectiveness of the proposed algorithm.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073P (2024) https://doi.org/10.1117/12.3029232
The technique of electromagnetic spectrum map-ping enables the revelation of spatial distribution patterns within the electromagnetic environment. Precise visualization of the location information of electromagnetic spectrum signals contributes to enhancing spectrum utilization efficiency and system robustness. This technique finds wide applications in the fields of communication, navigation, radar, and other systems related to positioning and signal processing. It serves as a crucial means for modeling and simulating complex electromagnetic environments, playing a vital role in ensuring the accuracy and reliability of electromagnetic environment modeling and simulation. In this paper, we first introduce the technical background and knowledge related to electromagnetic spectrum mapping, analyzing the principles and current research status of electromagnetic spectrum mapping technology both domestically and internationally. Subsequently, we delve into a comprehensive analysis of high-precision electromagnetic spectrum mapping techniques based on sparse sampling, emphasizing potential solutions. Finally, we summarize the challenges and future directions faced by current electromagnetic spectrum mapping techniques, providing insights into their prospective trends and applications.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073Q (2024) https://doi.org/10.1117/12.3029267
This research aims to address the issue of fall detection in the elderly using a wearable device-based fall detection system. Data is collected through acceleration sensors and barometric pressure sensors. After applying certain algorithms to the dataset, it was found that a single machine learning algorithm had poor generalization ability for fall detection. To improve classification accuracy, attempts were made to use ensemble learning algorithms for training and validation of the fall detection dataset. By employing Bagging and GBDT ensemble learning algorithms, the generalization ability of the model was successfully enhanced. On the validation set after 0.2 cross-validation, our model achieved an average accuracy of 99.28%, significantly improving the model's high performance and strong generalization ability.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073R (2024) https://doi.org/10.1117/12.3029139
Building a powerful country in transportation is a major strategic decision made based on national conditions, focusing on the overall situation and facing the future. The identification of potholes has important applications in the field of reducing accident rates as well as geological exploration and autonomous driving. In this paper, based on 301 road pictures, the training samples of the model are increased by data augmentation method. After normalization and standardization of the augmented training data, the random weighted sampling method is adopted as the training input of the model. In this paper, the VGG16 model is adopted as the classification model of road images, and the model parameters of lmageNet 1000 data set are taken as the feature extraction layer of the model in the way of transfer learning, and the model is trained on the modified classification layer. Two indexes, F1-score and Kappa coefficient, were used to evaluate the model. The model F1-score fluctuates around 0.5 and is higher than 0.4, and the Kappa coefficient is close to 0.6 in most cases. This shows that the model trained in this paper has high generalization ability and classification accuracy.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073S (2024) https://doi.org/10.1117/12.3029288
This paper innovatively constructs a Grey Wolf optimized support vector regression model (VMD-GGO-SVR) based on variational mode decomposition to deal with the complexity of traffic flow data, which model realizes efficient complex prediction in multidimensional data processing. Firstly, the vehicle flow data is decomposed by variational mode decomposition (VMD), and then the support vector regression model (GWO-SVR) is constructed by Grey Wolf optimization algorithm. The experimental results show that the VMD-GGO-SVR model has improved by 73.89% in the goodness of fit R index, and performs well in both the training set and the test set, which proves that it has a significant effect in optimization. Through its own classification function, the model splits and solves the complex data with characteristics, and combines them into the final prediction result.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Changcheng Wang, Fan Yang, Kan Zeng, Peng Fan, Lisi Chen
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073T (2024) https://doi.org/10.1117/12.3029170
To enhance the capability of assessing and forecasting the spatial-temporal situation of nonlinear moving targets, a nonlinear moving target tracking method based on LightGBM gradient boosting decision tree is proposed. The LightGBM model is used to learn the features of the target trajectory, establish the mapping relationship between the incremental target trajectory motion and the input features, and realize the high accuracy forecast of the nonlinear motion target trajectory. The experimental results show that the method is significantly better than the Kalman filter model in terms of prediction accuracy and prediction robustness by predicting the future points of the trajectory of a typical precision-guided weapon guided bomb and comparing the prediction results with the Kalman filter model. On each track of the test set, the mean absolute errors of the predictions of the LightGBM model in azimuth, altitude and oblique distance are 4.27%, 4.33% and 5.43% of the predictions of the Kalman filter model, respectively, and the mean square deviation are 4.11%, 4.24% and 5.21% of the predictions of the Kalman filter model. The importance of the features is analyzed by the SHAP method, and it is found that the derived features of target trajectory motion increments predicted by Kalman filter model contributed most to the model forecasts.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073U (2024) https://doi.org/10.1117/12.3029230
Intelligent condition monitoring of electromagnets in high-voltage circuit breakers is crucial for the safe operation of power systems. In this study, a hybrid two-phase approach is proposed, aiming at intelligently identifying key feature points in electromagnet current signals by a modified one-dimensional U-Net model, as well as determining the operating state of electromagnets based on the location and magnitude of these key feature points. In the first data-driven phase, an improved U-Net model applicable to time series is introduced for the intelligent identification of key features in the electromagnet current signal. In the second knowledge-based phase, the operating state of the electromagnet is accurately identified based on the position and size of the key feature points by exploring the motion mechanism of the electromagnet. The experimental results show that the proposed method can effectively identify the key points, and the recognition success rate is close to 100%. The proposed method can realize the adaptive identification of various electromagnet faults with only a few fault samples. Therefore, the proposed method paves the way for robust state identification of electromagnets and enjoys the merit of strong anti-interference.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073V (2024) https://doi.org/10.1117/12.3029307
This paper proposes a new variable step-size adaptive filtering algorithm based on the LMS algorithm and compares its performance with Least Mean Squares(LMS), Normalized Least Mean Squares(NLMS), Modified Sigmoid- LMS(MLMS) and Regularized NLMS(RNLMS) algorithms. The results indicate that compared to the other comparative algorithms, this algorithm can more effectively improve the signal-to-noise ratio of the filter output. Furthermore, within a wide input signal-to-noise ratio range, this algorithm can consistently enhance the filter signal-to-noise ratio output, effectively addressing the problem of inconsistent filtering effects caused by the input signal-to-noise ratio sensitivity in algorithms such as NLMS algorithms.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Zizhan Zhang, Guihe Qin, Yao Feng, Guofeng Wang, Kunpeng Wang
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073W (2024) https://doi.org/10.1117/12.3029218
With the popularity of intelligent connected vehicles, OTA(over-the-air) is widely used in Automotive ECU(electronic control unit) firmware update. Compared with the method of updating the whole package, incremental update technology solves the problem that upgrade package is too big to be downloaded efficiently. As one of the most popular OTA incremental update algorithms, traditional BSDIFF algorithm has insufficient operating efficiency in both BSDiff and BSPatch processes. In order to further improve the running efficiency of BSDIFF algorithm, this paper designs F&F-BSDIFF algorithm, which uses Fibonacci Search to traverse suffix array and uses FL2(fast lzma2) to compress and decompress Patch files. At the same time, according to the characteristics of the three blocks of Patch files, this paper only optimizes the compression mode of ctrl block and extra block, but retains the compression mode of diff block, to improve the compression efficiency and compression ratio of Patch files. Through our experiments, F&F-BSDIFF algorithm is more efficient in both BSDiff and BSPatch processes, and generates a smaller Patch file. Therefore, it is more suitable for automotive OTA upgrade.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073X (2024) https://doi.org/10.1117/12.3029153
With the development of new power systems, the level of automation and unmanned operation in substations continues to rise. The changes in the status and fault conditions of various electrical equipment are receiving increasing attention. Isolating switches, as crucial components widely used in substations, require vigilant status monitoring. The closing and opening operations of isolating switches encompass all switch-type devices, making their intelligence and predictive capabilities key aspects of substation automation. In practical production, the mechanical status of switch devices during the closing operation is unpredictable. There is a lack of effective monitoring and analysis methods to ensure that the closing operation is in a stable and normal mechanical state. Particularly, there is a deficiency in accurate and reliable judgment criteria for various types of knife switches and switch-type mechanical structures, whether they are fully closed or open. Traditional visual judgment methods are unreliable and ineffective in assessing the operational effectiveness. this document cited a method based on integrated MEMS micro-nano sensors, analyzing its technical challenges and methods. It suggests that for these monitoring systems, MEMS resistive pressure sensors and temperature sensors can be employed to monitor pressure and temperature during the opening and closing of isolation switches. A "double confirmation" method is proposed for comprehensive determination. Regarding the high-voltage resistance of sensor components, using modified silicon dioxide materials, along with insulation resin coatings and ceramic insulation structures, can enhance the components' resistance to high voltage. For electromagnetic interference resilience, a dual-function electromagnetic interference-resistant structure based on a metasurface is recommended. Integrating these components and communication devices can lead to the design of a high-voltage substation isolation switch monitoring system with both high-voltage resistance and electromagnetic interference resistance.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Kun Li, Pu Yan, Shuo Feng, Wenjun Liu, Aiguo Wang, Benqi Lu
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073Y (2024) https://doi.org/10.1117/12.3029116
Medical splint is a widely used conservative treatment method for fractures, offering numerous advantages such as low risk, reduced pain, and cost-effectiveness. However, the absence of pressure detection capability in traditional splints poses several limitations and challenges in the management of bone fractures. To address this issue, an innovative intelligent medical splint integrating pressure signal acquisition and cloud storage capabilities has been developed. The intelligent medical splint incorporates resistance strain gauges as pressure sensors, enabling accurate measurement of clamp pressure values. An amplification circuit is employed to enhance the accuracy of sampled signals. Simultaneously, the integration of database systems and internet cloud technology allows for the storage of collected pressure values in the cloud. These values are presented to users through a user-friendly graphical interface accessible via various devices such as computers and mobile phones. This ensures convenient access to patient data anytime and anywhere. To guarantee the long-term stability of the equipment, a watchdog circuit is implemented, significantly enhancing its reliability. Extensive human wearing experiments and rigorous testing have validated the functional efficiency and notable advantages of this design, demonstrating its compatibility with the requirements of fracture patients.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131073Z (2024) https://doi.org/10.1117/12.3029208
Path planning is a key technology to realize the autonomous navigation of mobile robots. The Informed-RRT* algorithm is the current path planning algorithm that solves the high sampling efficiency in complex environments, but it also suffers from long planning times and redundant turns in complex environments. For this reason, a multi-strategy optimization Informed-RRT* algorithm is proposed, the first is to introduce the WOA algorithm during the operation of re-selecting the parent node so that the new node can find the selection of the optimal parent node in the search radius, to improve the efficiency of the search, and the second is to select a suitable Bessel curve to interpolate and optimize the generated paths, to make the generated feasible paths smoother and with fewer redundant turns. In the algorithm validation, the McNamee wheeled robot is modeled using the joint simulation platform of ROS and GAZEBO, and the improved Informed RRT* algorithm is encapsulated into the ROS-based path planning algorithm, and the experimental results show that the proposed algorithm outperforms the existing algorithms in terms of the average planning time, the planning length, and the success rate of the planning, and it provides a new feasible solution for the path planning in the complex environment.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310740 (2024) https://doi.org/10.1117/12.3029274
This paper presents a study on emotion management for solitary elderly individuals using voice signal analysis technology. The research encompasses the collection of training samples, voice analysis employing specific algorithms, and the statistical output of results, all seamlessly integrated with a router. The outcomes are transmitted to the cloud, providing accessible data for family members, community hospitals, and relevant stakeholders. The key focus lies in the extraction of vocal features, specifically resonance peaks and Mel-Frequency Cepstral Coefficients (MFCC), for effective emotion recognition. The classification of emotional states is achieved through the application of the k-Nearest Neighbors (KNN) algorithm. This comprehensive system not only ensures efficient emotion analysis but also facilitates continuous monitoring, offering valuable insights into emotional trends over time. The integration of cloud storage and real-time accessibility by caregivers and healthcare institutions demonstrates the practical utility of the proposed approach in enhancing the emotional well-being of elderly individuals living alone.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310741 (2024) https://doi.org/10.1117/12.3029175
Image inpainting aims to recover the missing regions in an image and reconstruct a satisfactory restoration result with high quality. To solve the problem that the existing image inpainting methods do not deal with the information of missing and non-missing regions flexibly, and the global and local restoration semantics are inconsistent, we design a three-stage restoration model for the different semantic information required for restored regions at different scales, which utilizes different sizes of receptive fields to provide better image details at multiple scales, including global and local, and ensures semantic consistency of contextual information. Experimenting with our method on three popular publicly available image drawing datasets, the results show that this paper's method outperforms current restoration models.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310742 (2024) https://doi.org/10.1117/12.3029262
Because there is no uniform calibration method of particle size threshold for particle size identification fire detectors in high-speed trains, this paper proposes to establish a simulation model based on the particle Mie scattering theory, and calibrate the particle size threshold using DEHS aerosol. Because the number of fire detectors in high-speed trains is large and the installation locations are scattered, resulting in complex wiring and susceptibility to vibration and electromagnetic interference, this paper investigates the application of Internet of Things (IoT) technology and low-power technology in high-speed trains. After the prototype design, ground test and prototype train test, the feasibility of the program is proved.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310743 (2024) https://doi.org/10.1117/12.3029209
By constructing a coordinated operation system combined with artificial intelligence scheduling algorithms, the application practice and collaborative operation of manned and remote-controlled submersibles are achieved. This article summarizes the key technologies of collaborative operation between remote-controlled submersibles and manned submersibles. It includes data fusion and intelligent scheduling algorithms for collaborative work platforms, as well as task planning and path optimization methods. The research on artificial intelligence scheduling and task planning in this article provides technical support for more collaborative operations of remote-controlled and manned submersibles. The experimental results show that the task scheduling algorithm based on artificial intelligence scheduling can quickly complete the allocation of detection tasks under preset conditions. Based on each task point, the optimal route allocation in unit space can be obtained, which fully verifies the effectiveness and robustness of the artificial intelligence scheduling scheme. This provides technical reference and planning ideas for future self-developed remote controlled submersible and manned submersible collaborative operation systems.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310744 (2024) https://doi.org/10.1117/12.3029192
Exposure time adjustment is currently the main method for increasing the dynamic range of infrared imaging systems. In view of the difficulty of measuring targets with rapidly changing radiation characteristics, an automatic exposure control method for infrared focal plane detectors was proposed. Firstly, through radiation calibration experiments, the influence of exposure time was studied, and an improved non-uniform correction method was proposed to adapt to changes in different exposure times. On this basis, an integration time prediction method was proposed based on the calibration formula, and the optimal exposure time was predicted based on the current target gray value. A threshold is set to determine whether to adjust the exposure time. Finally, simulation experiments verify the effectiveness of the algorithm. When the target radiation temperature changes continuously, the method can automatically adjust the exposure time to ensure that the output gray value is always in the valid range.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310745 (2024) https://doi.org/10.1117/12.3029212
Under the condition of the small sample[1,2,3,4,5], it is no longer possible to simply use the mean and variance of all the data to remove outlier values. Method of hampel is simple and rough in small sample, it will be greatly affected by the outlier value that once enters the middle 50% of all the data. Method of boxplot[6,7,8] will cause the interquartile range (IQR) to be too large and make the outlier value become normal. In order to solve the above problems, this paper improves the method of boxplot by using the median to eliminate the outlier value in the middle 50% of all the data. Then we use the remaining data to calculate the mean value and variance. At last by use of the 3δ principles of method of hampel, we eliminate the outlier values and obtain the true and non-outlier values. The effect of the algorithm of this paper is useful and ideal by data simulation. It can be applied to engineering practice.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Han Zhang, Zhimin Shao, Jiejian Han, Yanheng Zhao, Tao Yang, Wei Wang
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310746 (2024) https://doi.org/10.1117/12.3029317
The Internet of Things is a rapidly growing field that promises to revolutionize how we interact with and control devices in our environment. As the number of Internet of Things devices increases, the need for efficient and intelligent ways to manage devices becomes increasingly important. However, the heterogeneity and scale of Internet of Things devices pose significant challenges to the effective integration and management. Semantic technology provide a solution by enabling devices to understand and interpret user intentions more accurately. In this study, an improved semantic model was designed based on related concepts and application of semantics in perception and execution for the Internet of Things. The proposed semantic frameworks was highlighted in enabling device-to-device communication and data aggregation, facilitating a holistic understanding of user needs. The importance of open standards and interoperability was also emphasized in realizing the full potential of semantic technology in the Internet of Things. The understanding and control of Internet of Things devices can be improved based on semantic technology, leading to more efficient and user-friendly systems.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310747 (2024) https://doi.org/10.1117/12.3029123
The traditional AGV(Automated Guided Vehicle) magnetic circulation method has the problem of discontinuous magnetic field detection, which seriously affects the subsequent lateral PID adjustment process of the vehicle. This article proposes a magnetic field based control algorithm which takes the total spatial magnetic field intensity detected by multiple magnetic navigation sensors as the measurement value, the total multi-channel magnetic field intensity when the magnetic navigation sensor is located directly above the magnetic guidance path as the standard reference peak, and the difference between the standard reference peak and the measurement value as the lateral position deviation. The lateral position deviation output by this method is a continuous quantity, and the vehicle can achieve continuous adjustment of lateral control values based on the position deviation during driving. The spatial magnetic field distribution pattern of the magnetic guided orbit indicates that the total difference in magnetic field strength in the near-field area near the center of the magnetic guided orbit increases sharply with the increasing deviation distance. This pattern can ensure that the PID adjustment response speed in the near center area is faster, and can enable vehicles to quickly return to the center of the magnetic guided orbit when deviation occurs in the near center area.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume Fourth International Conference on Sensors and Information Technology (ICSI 2024), 1310748 (2024) https://doi.org/10.1117/12.3029193
With the development of the Internet of Things (IoT) and the new generation of Artificial Intelligence, wearable sensors for smart healthcare have been widely developed in recent years. In this paper, we propose to use PDMS polymer elastomers doped with carbon quantum dot (CQD) nanoparticles to prepare triboelectric nanogenerators (TENGs) for wearable self-powered sensors. PDMS, as an elastomer, is characterized by durability, flexibility, and flexibility for wearability. By studying and analyzing the influence mechanism of CQD fillers on the sensor performance, it is concluded that CQD can increase the charge sites within PDMS and enhance the charge storage and transfer capability of PDMS, thus improving the output performance of TENG. The self-powered sensor prepared by TENG can be used to capture the joint movements of the human body and can be connected to the host computer through the Bluetooth module to realize the IoT-based smart medical system. The TENG, as a sensor module of this system, has the advantage of realizing self-powering without the trouble recharging of traditional batteries.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.