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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260901 (2023) https://doi.org/10.1117/12.2677767
This PDF file contains the front matter associated with SPIE Proceedings Volume 12609, including the Title Page, Copyright information, Table of Contents, and Conference Committee listings.
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.
International Conference on Computer Application and Information Security
Proceedings Volume International Conference on Computer Application and Information Security (ICCAIS 2022), 1260902 (2023) https://doi.org/10.1117/12.2672160
The traditional wireless network works in a single channel, and only one transmission path is generated by routing, which not only limits the network capacity and system throughput, but also easily generates collision conflicts when the traffic is large, and cannot provide good network performance. This paper optimizes the backbone MESH network from the perspective of multi-channel and multipath, and proposes an AOMDV routing protocol MM-AOMDV (Multi channel Multi metric AOMDV) based on multi-channel and multi-metric. Simulation results show that the MM-AOMDV protocol has better end-to-end delay, throughput and delivery rate network performance than the original protocol while the node density and traffic volume increasing.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260903 (2023) https://doi.org/10.1117/12.2671732
Protocol Reverse Engineering (PRE) is of great significance to the research of cyber security and it is helpful to understand protocol specifications. There has been many researches on PRE but most of them need additional manual analysis, which is not available for private and unknown protocols. We propose a protocol state analysis and annotation method, which extracts the feature information of binary-based protocol data through an auto-encoder model. Moreover, density-based clustering algorithm is only used to distinguish protocol types in existing studies, we propose an improved algorithm and apply it to protocol state analysis. Finally, we apply alignment algorithm to get state information and do annotation. We run simulation to verify the effectiveness of proposed method and prove its feasibility in private and unknown protocols. The results of clustering algorithms are compared to show the improvement. Then the application of proposed method is summarized based on the simulation results, which provides a novel idea for the protocol analysis.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260904 (2023) https://doi.org/10.1117/12.2671839
An improved RRT* algorithm is proposed to solve the problems of poor goal orientation, low space utilization and many inflection points in the path planning of Automated Guided Vehicle (AGV) transportation. The algorithm adopts the approach sampling and restricted sampling strategies. First, the approach sampling method improves the sampling efficiency and reduces the path search time; then, the sampling area is reduced by limiting sampling, so as to improve the probability of sampling points falling in the path neighborhood and shorten the path length. On this basis, the redundant points of the path are trimmed according to the greedy algorithm, and the curvature of the path is optimized using the cubic B-spline smoothing method to obtain the driving track that meets the requirements of AGV running stability. Finally, through MATLAB simulation and comparative analysis, in the same environment, compared with the RRT* algorithm, the improved RRT* algorithm reduces the time of path search by 61.59% and the path length by 8.6%, which verifies the effectiveness of the improved RRT* 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260905 (2023) https://doi.org/10.1117/12.2671737
With the great changes brought about by digitization, traditional security threat detection capabilities have been greatly challenged. Traditional threat detection technologies are based on signatures, rules and manual analysis, and there are serious lags and blind spots in security visibility. Unknown attacks cannot be detected and are easily bypassed. Multi-scale user behavior fusion analysis uses artificial intelligence methods and spatiotemporal feature engineering to associate multisource heterogeneous user behavior feature data to realize threat detection of multi-modal and multi-scale 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260906 (2023) https://doi.org/10.1117/12.2671803
The image processing method is used to extract the target trajectory and signal features. This paper improves the traditional image processing method Hough transform, uses the Canny operator to detect the contour, and improves the traditional Hough transform by decomposing the signal features and time iteration. It can extract irregular trajectory targets and extract signal frequency domain features. At the end of this paper, experimental data proves that the improved Hough transformation method can meet the stable extraction of irregular curve trajectories and cross trajectories, and can also perform feature localization and feature extraction on feature signals.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260907 (2023) https://doi.org/10.1117/12.2671824
Position bias: The same item in different positions affects the user’s preferences, especially for items that are usually more difficult to see in the backward position. Standard double robust (DR) estimator in recommendation systems is widely used due to its accuracy and robust properties. However, the conventional DR estimator was doubtful of its highperformance variance. In this paper, we examined how to reduce the variance of the current DR estimator. Our main goal is to optimize the existing double robust estimation by the self-normalization method to reduce the variation. Our mathematical deduction shows that the self-normalized double robust estimation (SNDR) has less variance. The subsequent experimental steps demonstrate the low variance property of SNDR with both figure demonstration and data analysis.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260908 (2023) https://doi.org/10.1117/12.2671826
Laying power cables in existing tunnels can not only save land resources, but also improve the utilization rate of urban space. At the same time, it also has important practical significance for expanding the construction and development space of urban power grid. Therefore, in order to assess the safety risk level of cables laid in the built tunnels, the safety risk assessment index system of laying cables using existing tunnels is established, which contains 19 evaluation indexes, involving 8 sub-systems such as cable tunnel structure, lighting system and power supply system. Finally, the fuzzy analytic hierarchy process (AHP) method is employed to evaluate the safety risk of a power cable laying project in an existing tunnel. The results show that the risk level of laying cable trench in the built tunnel is low, and the feasibility of laying power cable in the built underground traffic tunnel is also 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.
Zheru Cai, Zhongwei Chen, Jiao Wu, Jingchu Wang, Kai Cheng, Shu Li, Yizhen Sun
Proceedings Volume International Conference on Computer Application and Information Security (ICCAIS 2022), 1260909 (2023) https://doi.org/10.1117/12.2671829
As an active defense network security tool, honeypots can lure attacks and capture attack information. However, traditional honeypots can only wait for intrusion passively, and honeypots with network traffic traction function can not realize real-time optimization of diversion strategy based on attack information. Based on the survey of honeypot traceability and current situation of diversion, this paper carries out the research of network traffic traction method based on attack detection and network traffic load balancing. Through five steps of configuring network traffic traction strategy, obtaining attack alarm, comprehensive attack research and judgment, load balancing diversion, and log capture feedback, this method effectively enhances honeypot traceability and improves the level of active network security protection, and introduces the application scenario of this method with portal websites as an example. The effectiveness of the method is tested by comparing various indicators before and after the application of the 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090A (2023) https://doi.org/10.1117/12.2671832
To solve the problem that the current Quality of Experience assessment of online gaming cannot reflect the real Quality of Experience of online gaming, we choose multi-dimensional influencing factors to create a dataset of the Quality of Experience of Honor of Kings and propose a weighted neighborhood classifier based on fuzzy neighborhood rough sets for the existing neighborhood classifier shortcomings. First, the concept of fuzzy neighborhood similarity is proposed in this paper. Moreover, weighting the distances through the fuzzy neighborhood similarity can distinguish the differences between samples, which improves the decision-making of the neighborhood classifier. Then, combining the fuzzy neighborhood rough sets and neighborhood classifier can improve the anti-noise performance of the neighborhood classifier. Finally, the proposed weighted neighborhood classifier based on fuzzy neighborhood rough sets has fully experimented on several UCI datasets and Honor of Kings Quality of Experience datasets. Our method is compared with the state-of-the-art methods to demonstrate our method’s superiority in classification accuracy under different class 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090B (2023) https://doi.org/10.1117/12.2671836
Radio frequency signal information of a wireless terminal is based on inherent differences in hardware. It has uniqueness, time-invariance, independence and robustness. Therefore, it is also called the radio frequency fingerprint of the wireless device. It can be used for authentication and security access of the wireless terminal to enhance the security protection capability of wireless communication. However, the existing radio frequency fingerprint authentication technology is facing the problem of lack of corresponding identification when the radio frequency information acquisition module is linked with network management equipment. This paper studies a mapping technology between WiFi radio signals and MAC addresses based on GNU Radio stream labels, and establishes the corresponding relationship between the radio signal identification and the network layer identification by using the steps of signal collection, burst signal detection, burst location stream label creation, stream label transmission and update, and the mapping between burst signals and MAC addresses. The feasibility of this technology is verified by experiments.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090C (2023) https://doi.org/10.1117/12.2671843
Based on the articles published on journal Physical Review E (PRE), the influence of academic groups is evaluated by social networks analysis and the multi-attribute decision making method TOPSIS. At first, co-citing network established by considering the citing relationship among articles, and then the academic groups are detected by using community detection algorithms on co-cited network. After that, the index system for evaluating the influence of academic group is proposed, and finally a multi-attribute decision making method TOPSIS is used to evaluate the influence. The proposed method provides a new insight into analyzing the influences of academic groups, and can comprehensively describe academic groups’ influence.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090D (2023) https://doi.org/10.1117/12.2671862
Night is an inevitable scene for surveillance video. Due to the high image resolution, complex background, uneven illumination, and similarity between the target and the background of hawk-eye surveillance video, it is difficult for previous trackers to apply the tracking of a tiny object in such scenes. In this regard, this paper proposes to combine an online automatically and adaptively learning spatio-temporal regularized tracking algorithm with an efficient and effective low-light image enhancement algorithm to improve tracker performance. We constructed a new benchmark that includes 41 night surveillance sequences captured by Hawk-Eye cameras at night. Exhausted experiments have been conducted on this dataset, and the results show that by combining the two methods, the original algorithm can obtain better results in this dataset, and can meet the real-time object tracking, which contributes to the application of tiny object tracking in eagle-eye surveillance video at night.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090E (2023) https://doi.org/10.1117/12.2671850
All users have access to the details of all transactions through the public ledger thanks to the distributed characteristics of the blockchain. However, attackers may infer the identities of the parties through detailed transaction data, and impair the privacy of users. Among these data, the transaction value is one of the most important transaction data. Therefore, for the privacy protection during blockchain transactions, this paper, based on the homomorphic encryption technology, enabled the committer peer to update the ledger during the transaction without knowing the balance of the parties’ accounts and the transaction value. Meanwhile, the zero-knowledge proof scheme was introduced. It was proved by interval range that the committer peer can verify the validity of the transaction without knowing the transaction 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090F (2023) https://doi.org/10.1117/12.2671852
Data security has always been one of the public concerns, and homomorphic encryption technology, as one of the effective means to ensure data security, has always been a hot topic of academic research. Traditional machine learning is trained in a batch environment. In practice, data owners tend to outsource data and model training tasks to third-party clouds with huge computing resources, but data outsourcing carries the risk of privacy leakage. Therefore, in order to prevent this situation, an effective method is to encrypt the data before the outsourcing, and the third-party cloud trains the machine model of the ciphertext data. This method has special requirements for encryption algorithms which should support computation directly on the ciphertext data. This paper presents a novel data flow computing privacy protection framework based on the homomorphic encryption algorithm CKKS and the flow data processing engine Flink, called SDPPF (Streaming Data Privacy Protection on Flink). The proposed framework supports the functions of data stream encryption, decryption and ciphertext computing, and expands the functions of vector point multiplication and array sum operation on the basic simultaneous operation supported by the original CKKS algorithm. This paper also selects a classical machine learning algorithm: KNN algorithm, combined with the homomorphic encryption algorithm CKKS to realize the privacy protection machine learning 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090G (2023) https://doi.org/10.1117/12.2671854
At present, ultrasound is the most widely used in prenatal diagnosis. The accurate acquisition of fetal standard plane is very important in prenatal diagnosis. However, the recognition of fetal standard planes (standard versus non-standard) is a challenging task, mainly because of the need to simultaneously recognize several key anatomical structures. In this paper, we propose a novel method termed mask guided attention (MGA) to integrate global and diagnostic region cues to recognize the fetal standard plane, imitating the sonographer’s diagnostic mode. In addition, to further mine key anatomical structures, an innovative attention mining (AM) module is designed to improve the MGA. Utilizing the clinical dataset, we demonstrate that MGA significantly improve the performance of fetal standard plane recognition tasks.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090H (2023) https://doi.org/10.1117/12.2671857
Object detection, as one of the key technologies of service robots, is becoming increasingly important. For this reason, this paper proposes an improved YOLOv5s-L algorithm based on YOLOv5s for service scenarios such as hotels and shopping malls. With the introduction of Ghost series modules, light weight is realized by reducing the number of parameters and calculations of the network. And different compression ratios for Ghostconv modules are compared. To optimize the algorithm, a large-field contextual feature integration module and the coordinate attention mechanism are introduced, which help to enhance the ability to gain information about small objects in the scene and increase the sensitivity to information such as the position and direction of the target. A qualitative analysis was carried out for the Ghostconv modules with different compression ratios, and it was concluded that there is a large amount of redundancy in the deep features of YOLOv5s. The algorithm’s effectiveness was verified using two data sets, PASCAL VOC2007 and PASCAL VOC2012, and experiments indicate that our improved algorithm outperforms other compared 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090I (2023) https://doi.org/10.1117/12.2671868
In this paper, we design a deep reinforcement learning algorithm based on graph neural network to solve the problem of cooperation control of multiple UAVs. Our algorithm can control multiple UAV swarms to complete package delivery tasks in an unexplored area under partial observation. Since each UAV has only a limited observation space and a small range of communication, we propose a reinforcement learning algorithm based on graph neural network, which can process multiple graphs simultaneously time and aggregate the feature vectors of the neighbor agents to address the cooperative issue of heterogeneous multi-agent coordination. We conduct a couple of ablation experiments to prove the effectiveness and performance characteristics of our 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090J (2023) https://doi.org/10.1117/12.2671874
Current research on Rate-Splitting Multiple Access (RSMA) focuses mostly on the case where the base station is fixed, and the use of UAVs as base stations for wireless communication is growing. The article introduces RSMA, a new type of non-orthogonal multiple access technique, to study the uplink transmission optimization problem of UAVs as base stations, and designs an algorithm based on the Augmented Lagrangian Method (ALM) and the Artificial Fish Swarm Algorithm (AFSA), which adds to the dynamic step size and field of view strategy, as well as the memory behavior of artificial fish. To solve the optimization problem further under the constraints of linear equations, a correction factor is introduced to the algorithm to constrain the behavior of the artificial fish. Finally, we simulate UAV-assisted uplink communication using RSMA, and the results demonstrate that this scheme has higher throughput than Orthogonal Multiple Access (OMA) and Non-Orthogonal Multiple Access (NOMA), which is 11.60% higher than NOMA.
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.
Qiyang Shi, Zhehui Wang, Jun Zhang, Chuang Sun, Zhenhong Jia
Proceedings Volume International Conference on Computer Application and Information Security (ICCAIS 2022), 126090K (2023) https://doi.org/10.1117/12.2671889
Accurate state-of-health (SOH) monitoring of lithium-ion batteries plays an increasingly crucial role in the prognostic and health management (PHM) of batteries. Aiming at the shortcomings of the deep extreme learning machine (DELM) that the input weights and offsets are generated randomly and it is difficult to set parameters, a method combining intelligent search algorithm and DELM is proposed. First, we present a method based on improved symbolic regression algorithm to extract health indicators (HIs) from the discharging process curves of the batteries. Then, ISSA is proposed by combining the Tent mapping and dynamic weight factors to increase the search space of initial algorithm, and selfadaptive differential evolution strategy is used to jump out of the temporary optimal path. Finally, the optimized regression model is used to implement SOH monitoring. Compared with other data-driven methods, the method proposed in this paper can effectively reduce the error of SOH prediction.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090L (2023) https://doi.org/10.1117/12.2672134
Opinion evolution dynamics in social networks are fast becoming a critical aspect of social network analysis. One of the challenges in seeing the dynamics is to reach a predefined opinion consensus. A hybrid opinion dynamic model generally includes two types of agents, they are leaders and followers. However, some agents may show cognitive dissonance behavior due to the contradictions of opinions. The contradiction greatly affects the evolution of opinions and relationships. This paper proposes a hybrid opinion dynamics model based on cognitive dissonance (HODCD) to incorporate bounded confidence effects in traditional approaches. This model also provides a process to update the opinions and network of agents. Simulation results illustrate that HODCD can facilitate consensus between two communities with different opinions.
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.
Xu Bai, Haiming Ji, Xinghua Dong, Jianfeng Guo, Huan Yin
Proceedings Volume International Conference on Computer Application and Information Security (ICCAIS 2022), 126090M (2023) https://doi.org/10.1117/12.2672135
Through data analysis and method research on online detection of relay protection, the decision tree is used to carry out fault diagnosis on the alarm information of secondary equipment, and based on the operation information, the evaluation of relay protection status and auxiliary maintenance decision are realized. For items that cannot be inspected during the inspection cycle and items that are found abnormal, a complete detection system is formed by means of continuous power 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090N (2023) https://doi.org/10.1117/12.2672140
With the disclosure of more and more Marine investigation accident reports, it becomes a new way to study ship collision characteristics through big data of ship collision accidents. In this paper, based on the big data of ship collision accidents, a radar window risk of ship collision (ROC) cognitive model based on Kriging interpolation and the Gaussian mixture method (KGMM) is constructed to study ROC characteristics. First of all, the spatial and temporal feature perception model of collision risk perception is established under the radar window. Secondly, a method based on KGMM is constructed. The method includes two parts which were data set interpolation using the Kriging interpolation method and the Gaussian mixture clustering method to cluster the interpolation results. Finally, different collision scenarios were set for 101 cases, and the spatial-temporal differentiation characteristics of ROC are identified by the ROC cognitive model in the radar window. The results show that the ROC presents a risk-sensitive area under the radar window. The characteristics of the risk-sensitive areas of different ships in the encounter situation are consistent with the overall characteristics. The research results can provide a reference for the ship officers to choose the low-risk and favorable position to avoid the ship under Convention on the International Regulations for Preventing Collisions at Sea (COLREGS).
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090O (2023) https://doi.org/10.1117/12.2672141
The static event-triggering problem of stochastic descriptor systems under dual network attacks is carefully studied in this paper. Considering the use of network resources, a general event-triggered mechanism is widely adopted. By constructing an appropriate Lyapunov-Krasovskii functional and using Jensen inequality, necessary conditions for the stochastic admissibility are obtained. Based on aforementioned condition, the event-triggered controller is designed. Eventually, the effectiveness of joint design is verified through simulation.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090P (2023) https://doi.org/10.1117/12.2672144
For the problems of few samples, serious unbalanced categories and small defect scale of catenary cotter pin, a detection method based on three-level cascade architecture and attention mechanism is proposed. First of all, to alleviate the problem of inaccurate location caused by the small size of the cotter pin, the deep residual location network was constructed, and the atrous convolution layers of different sizes were introduced, which not only avoided the loss of internal data structure, but also preserved the hierarchical context feature. Secondly, a lightweight generative adversarial network that is sensitive to the difference of image local features is constructed to generate defect samples. Therefore, the problem of over-fitting and poor generalization performance of the detection network due to few samples and unbalanced categories is alleviated. Finally, in order to further alleviate the problem of small defect scale, the attention mechanism is adopted to learn different weights from channel domain, so as to obtain more important feature information and improve the accuracy of the detection network. Comparing the proposed method and its variant on dataset, the results show that the three-level cascade architecture proposed has certain advantages, and can alleviate the problems of few samples, unbalanced categories and small target scale.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090Q (2023) https://doi.org/10.1117/12.2672148
Ultra-high frequency (UHF) partial discharge (PD) monitoring is an important technique to detect and evaluate the internal insulation state of high-voltage equipment. In practice, multiple insulation defects may exist. As a result, the measured UHF PD signals are probably the mixture from multiple PD sources, making the current single-source-based fault diagnosis methods inapplicable. In this paper, a blind source separation algorithm based on sparse component analysis (SCA) is proposed for the separation of overlapped UHF PD signals. First, the raw signals are mapped to a two-dimensional time-frequency (TF) spectrum by using the short-time Fourier transform (STFT). Second, the peak detection technology and fuzzy clustering technology are adopted to estimate the number of PD sources and the mixing matrix. Finally, the l1-norm decomposition algorithm is applied to reconstruct the TF representations of the source signals, and the recovered source signals in time-domain are obtained by the inverse STFT (ISTFT). Numerical and experimental studies are conducted to validate the 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.
Qianqian Jin, Xun Jiang, Lijing Yan, Fangfang Dang, Cheng Dai
Proceedings Volume International Conference on Computer Application and Information Security (ICCAIS 2022), 126090R (2023) https://doi.org/10.1117/12.2672159
With the rapid development of digital transformation of power enterprises and the widespread application of cloud computing, there is a coexistence of multi-party cloud and non-cloud environments in the information network. The original security boundary has been continuously extended, and the security team is facing the problems of increased protection difficulty and reduced management efficiency. In order to solve the problem, this paper proposes an adaptive security management and control framework for multi-party cloud and non-cloud environments, based on softwaredefined and a unified resource model. First, a unified cloud security resource model is proposed. Then, by instantiating the elements of the unified cloud security resource model, an adaptive security management and control framework is built for the power multi-party cloud complex environment. Finally, the application of the linkage blocking scenario of the firewall on the cloud and outside the cloud is designed and implemented.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090S (2023) https://doi.org/10.1117/12.2671846
This paper develops a data visualization and analysis system for used cars data in response to the requirement that used cars information is complex and buyers need to obtain objective and comprehensive used cars information in a short period of time. Selenium+XPath crawler was used to crawl the used cars data in 58.com, and then import the data. The dirty data was cleaned using the Pandas data analysis toolkit in Python. The data is then stored as the corresponding CSV file and converted into JSON file. Finally, ECharts is used to read JSON files for data visualization and HTML for web display.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090T (2023) https://doi.org/10.1117/12.2672173
It is necessary to register the geometric position of ocean thermal infrared images to obtain information such as ocean temperature. The thermal infrared images are usually blurred because of the different imaging mechanisms. At the same time, it is difficult to obtain sufficient and uniformly distributed control points for geometric correction since the texture of ocean remote sensing images is relatively simple. Aiming at the above problems, a method combining point features based on the AKAZE algorithm and surface features as control data is proposed to register and correct thermal infrared images. And a verification experiment is designed using SDGSAT-1 thermal infrared images and Landsat optical images. The experimental results show that the proposed method can effectively register and correct SDGSAT-1 thermal infrared images with Landsat optical images in ocean areas.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090U (2023) https://doi.org/10.1117/12.2672185
Aiming at the problems of extensive data semantic differences and complex data analysis and processing caused by data fragmentation, semi-structure, and information heterogeneity in the information interaction of node devices under the edge computing framework, this paper proposes an information model to load the state data of the node and develops a corresponding parser for the information model, which reduces the heterogeneity of node data and ensures that the data can be uniformly connected to the edge computing platform. Through the device monitoring platform, the running status of various devices can be viewed in real-time, which proves the feasibility and effectiveness of the proposed information model and parser.
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.
Yongfa Li, Shu Li, Mu Chen, Yating Chen, Linjing Cao, Yang Liu, Yizhen Sun
Proceedings Volume International Conference on Computer Application and Information Security (ICCAIS 2022), 126090V (2023) https://doi.org/10.1117/12.2671955
With the rapid development of mobile Internet and the transformation of information technology in power energy enterprises, the demand for mobile office is increasing rapidly. However, the network security risks and attacks faced by mobile applications and terminals are also increasing, which brings hidden troubles to the safe production of enterprises. Therefore, this paper proposes a security assessment and control method for power mobile terminals, designs a mobile security protection system, puts forward indicators and methods for terminal security risk assessment, and designs a control mode for terminal risks, which effectively improves the security protection capability and emergency disposal ability of power mobile terminals, and helps the stable operation of power grid and ensure energy safety and 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090W (2023) https://doi.org/10.1117/12.2672156
This article focuses the trajectory tracking control as well as dynamics of differential-drive mobile robot (DDMR). This article sets up the dynamic as well as kinematic models simultaneously based on the mass point center of DDMR. At first, a DDMR dynamics is created in light of Lagrangian mechanics, in which the Lagrange multipliers are acquainted with tackling the issue of nonholonomic limitations. Then, a controller including torque and speed control is put up in view of backstepping technique to handle the problem of trajectory tracking, as well as its asymptotic stability is demonstrated by Lyapunov hypothesis. At long last, the mathematical simulation results show its viability and productivity.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090X (2023) https://doi.org/10.1117/12.2672153
Image registration is an important technology in the image processing, which is widely used in computer vision, image fusion, image reconstruction and other fields. To solve the problem of poor image registration due to fuzzy regions in multi-focus images, this paper proposes a multi-focus image registration algorithm based on image preprocessing and improved SIFT. The reference image and the image to be registered are preprocessed by Gaussian smoothing. And then all images are feature extracted and classified. Last, the image is feature matched by bidirectional adaptive threshold algorithm, and finally the registered image is obtained by the registration result. Compared with SIFT algorithm, the number of feature extraction and feature matching of the proposed algorithm increase by 56.57% and 67.43% respectively.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090Y (2023) https://doi.org/10.1117/12.2672150
Alltoall is an important collective communication mode that is widely used in scientific and engineering computing applications. In applications such as FFT, using as much memory space as possible can improve applications’ efficiency and expand the scale of problems to be solved. High-bandwidth alltoall_inplace communication under space-constrained buffer conditions can significantly improve the performance of such applications. In this paper, two alltoall_inpalce communication algorithms under the condition of limited buffer space are designed for the domestic parallel computing system based on Sunway many-core processor. The alltoall_inpalce communication interfaces for both the core array and the whole CPU node are realized. The experimental results show that algorithms implemented in this paper can achieve high bandwidth using limited buffer space.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126090Z (2023) https://doi.org/10.1117/12.2671917
In this work, we investigate the efficient distributed deployment design for unmanned aerial vehicle (UAV) communication systems. A game-theoretic framework is proposed to describe the interactions among UAVs. Specifically, a distributed potential game is modeled, where the decision actions of each UAV are chosen from the complex local set, and are not known by other UAVs. In order to solve this, we first employ inscribed polyhedrons to approximate UAVs’ local sets, so as to convert the original projection operation into a quadratic program subproblem. Then we design a discrete algorithm with a distribute scheme for ϵ-Nash equilibrium seeking, in which each UAV generates a local estimate action profile for other UAVs and exchanges this information with its neighbors through the communication network. Finally, we show the performance of the proposed algorithm via various numerical examples.
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.
Yongzhong Zhang, Hexiao Huang, Junzhu Zhang, Yan Ma
Proceedings Volume International Conference on Computer Application and Information Security (ICCAIS 2022), 1260910 (2023) https://doi.org/10.1117/12.2671702
Dermoscopic image segmentation aims to detect damaged skin areas. It is difficult to detect skin lesions accurately due to factors such as the method of image acquisition, the characteristics of the lesion, and the texture of the skin. This paper proposes a dermatoscopic image segmentation algorithm that combines the pigment separation algorithm with the Segnet network model. First, pigment separation is performed on the dermatoscopic images to obtain the corresponding melanin and hemosiderin images. Afterwards, the melanin and hemosiderin images are converted to single-channel grayscale maps and merged with the original images to produce image data with a channel number of 5. The channel-expanded images are then segmented using Segnet deep neural network. Experimental results on the ISIC-2018 dermoscopy image dataset show that the proposed algorithm achieves better segmentation results in terms of accuracy, sensitivity, and specificity.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260911 (2023) https://doi.org/10.1117/12.2671692
A coverage optimization method is suggested to improved node coverage in wireless sensor networks (WSNs), decrease node redundancy, and lengthen network lifetime, this method is based on the adaptive grey wolf arithmetic optimization algorithm The exploitation and exploration are first balanced using a cosine acceleration function. Then, to boost the method's performance, the grey wolf optimizer and arithmetic optimization algorithm are combined. In comparison to the conventional coverage optimization algorithm, our simulation results could improve arithmetic optimization algorithm has higher convergence efficiency and coverage rate, decreases network loss, and significantly lengthens the network life cycle.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260912 (2023) https://doi.org/10.1117/12.2671689
For downlink multi-cell massive multiple-input multiple-output (MIMO) system. An optimization algorithm for alternate iterations of energy efficiency (EE) is proposed. The system adopts minimum mean square error (MMSE) precoding. Average transmit power of the base station (BS) can be obtained according to the maximum outage probability allowed by the system and the minimum rate requirement of the user equipment (UE). An EE optimization model is established according to the average transmit power. Considering UEs and user data rate as constants to solve the optimal solution of the BS antennas. Then use the alternate iterative optimization algorithm until the EE reaches the optimum. Results illustrate that the proposed algorithm can obtain better EE performance with fewer antennas.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260913 (2023) https://doi.org/10.1117/12.2671387
How to use the methods of quantitative analysis to evaluate the importance of nodes or groups in complex networks is one of the important issues to be solved urgently in the field of network science research. Compared with the complex network, in which an edge represents the direct adjacent relationship between two nodes, the unique “hyperedge” in a hypernetwork is more suitable for representing groups, teams, and community structures of multiple nodes. Identifying the importance of teams and communities in the network is more conducive to controlling information dissemination in groups accurately, suppressing community-based outbreaks, predicting team research results, and discovering important drug targets. Existing algorithms focus on identifying important nodes in hypernetworks, and mining for important hyperedges is rare. In this paper, based on the hypergraph theory, combined with the property of the minimum eigenvalue of the grounded Laplacian matrix of the hypernetwork, a new index MEGL is proposed to identify the important hyperedges in hypernetwork. And it is applied in the drug target hypernetwork, which can not only identify important targets, but also identify important drugs. This method has important guiding significance for our drug development and target prediction, and also has certain reference significance for identifying important teams and communities in the network.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260914 (2023) https://doi.org/10.1117/12.2671713
Cyber deception is a critical component of proactive cyber defense. It releases false information about devices, applications and networks to attackers to mislead attackers, sabotage attack actions and mitigate impact of intrusion based on cyber deception strategy. There have been many researches about cyber deception strategy. Most of them consider the process of cyber attack and defense as non-cooperative game theory model and design algorithms to find optimal solutions. However, most existing researches abstract attackers and defenders into simple characters, having limitations in applicability. To supplement this part of research, we introduce intrusion prediction and honeynet to game-theoretical cyber deception and propose a novel cyber deception strategy model. We run some simulations to verify the effectiveness of our proposed model. Based on the simulation results, the rules of multi-stage cyber deception and model application are summarized, which can provide a novel and effective guidance of cyber deception.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260915 (2023) https://doi.org/10.1117/12.2671695
Today, deep learning technology is widely used in a lot of scientific research fields. A crucial question is how to accurately predict the performance and energy consumption of deep learning training (DLT) tasks. Existing prediction methods of DLT tasks either have low accuracy or use too many cluster resources, and few methods focus on the energy consumption prediction. In this paper, we analyze the relationships between the characteristics of performance and energy consumption and the task configurations of DLT tasks. Then we propose an offline prediction model to predict the performance and energy consumption of DLT tasks based on these relationships. The experiment in an actual GPU cluster shows the effectiveness of the prediction model. The average deviation of the prediction model is 4.68%.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260916 (2023) https://doi.org/10.1117/12.2671691
Genomic selection (GS) to estimate genomic estimated breeding values (GEBVs) of individuals by using high-density molecular markers covering a genome-wide range combined with phenotypic records or pedigree information has revolutionized animal and plant breeding. Support vector machines (SVM) have been shown to be an important method for implementing genomic selection, showing excellent prediction performance on a variety of traits, but the choice of hyperparameters and kernel functions has an important impact on the prediction performance. In this study, we integrated four kernel functions of SVM to construct a multiple kernel ensemble (MKE) learning framework and combined gradient boosting decision tree (GBDT), genomic best linear unbiased prediction (GBLUP) and random forest (RF) to predict GEBVs for three economic traits of milk fat percentage (MFP), milk yield (MY), and somatic cell score (SCS) in German Holstein dairy cattle. We also constructed an Optuna hyperparameter optimization (HO) framework and compared the prediction performance and time to find the optimal parameters with two commonly used grid search and random search methods. The results show that the MKE framework outperforms the single kernel SVM as well as several other machine learning (ML) algorithms, with an average improvement of 10% in prediction accuracy for the three traits. Besides, the MKE framework with Optuna optimization has the best predictive performance on each trait. Therefore, we believed that MKE is an efficient and stable GS method for phenotypes prediction.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260917 (2023) https://doi.org/10.1117/12.2671669
The development of data link technology brings new challenges to the perception and formation of battlefield situation. In view of the situation formation characteristics of LINK16, this paper analyzes the situation formation process of LINK16, proposes a new indicator system, and establishes the LINK16 based on fuzzy analytic hierarchy process. The situational quality assessment model is then used to verify the simplicity and effectiveness of the method through the simulation of typical combat scenarios of close air support. Finally, it is concluded that the confidence of the algorithm is more objective and effective than the fuzzy algorithm model and the expert experience algorithm from the aspects of the quantity, quality and integrity of the 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260918 (2023) https://doi.org/10.1117/12.2671284
The adaptive erasure coding scheme for decentralized ubiquitous storage is investigated in this paper to improve the level of durability and reduce repair bandwidth cost and repair time. First, the extended parameters Reed-Solomon (RS) codes are proposed, and the relationship equations relating to durability, repair bandwidth cost, encoding parameters and peers fluctuation rate are set. Subsequently, the Environment-adaptive Parameters Algorithm (EAPA) is proposed. In a variety of network environments, EAPA can adjust encoding parameters adaptively to retain the desired level of durability without increasing storage cost. The Optimal Repair Cost Parameters Algorithm (ORCPA) is proposed for different scenarios, which leads to the optimal repair bandwidth cost and achieves a desired level of durability. ORCPA adapts parameters in accordance with the ratio of slow peers in the network to reduce the repair time. Experiments show that EAPA and ORCPA are capable of significantly increasing level of durability and reducing repair bandwidth cost and repair time compared with several erasure codes with wide application in multi-peer failure 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260919 (2023) https://doi.org/10.1117/12.2671308
The current manual-based mining vehicle load accounting method has a large workload and low efficiency, which is difficult to meet the needs of mine wisdom development. This thesis proposes a mining vehicle load assessment and information query system, which combines the research of mining vehicle point cloud denoising algorithm, the research of mining vehicle load volume determination algorithm and the research of license plate recognition system based on computer vision. It has been verified in practice that the system can significantly improve the automation of mine vehicle load volume determination.
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.
Zhi Xie, Jiaju Wang, Chen Liu, Tai Bai, Dake He, Weimin Chen, Yihui Ding, Junyou Shi
Proceedings Volume International Conference on Computer Application and Information Security (ICCAIS 2022), 126091A (2023) https://doi.org/10.1117/12.2671811
In order to recover the loss of the stolen electric power, a comprehensive approach by analyzing the user power consumption data has been developed. According to the characteristics of the power stealing methods of each category of users, a comprehensive algorithm is employed to identify the method and the length of the power stealing behaviors. Abnormal data series that meet the power stealing characteristics for voltage, current, power and power factor are classified. Clustering algorithm is employed to identify abnormal power consumption, such that time period of power stealing can be calculated. Classification and clustering algorithms are synthesized such that results of different algorithms with different principles can be cross-verified, and stolen power can be recovered accurately and fairly.
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.
Jiaona Chen, Daofeng Li, Weijun Tao, Jing Zhang, Peng Wang
Proceedings Volume International Conference on Computer Application and Information Security (ICCAIS 2022), 126091B (2023) https://doi.org/10.1117/12.2671822
Predicting the duration of traffic accidents is an important part of emergency safety management, which can provide theoretical basis for road diversion and rescue. The validity of long-term forecasts depends largely on the quality of the data. Due to the discreteness, randomness and complexity of traffic accidents, the unbalanced samples is a common problem in traditional prediction models. The generalization ability of the model is insufficient. Based on the Mixup and ensemble learning, the accident duration prediction model is designed. The new datasets are created and extended. Several machine learning techniques are compared and analyzed with RMSE, MAPE and R2, including K Nearest Neighbor (KNN), decision trees (DT), random forests (RF), gradient-based trees (GBDT), AdaBoost, extreme random trees, and XGBoost. The results show that the Mixup-PSO-XGBoost performs the best as well as the training time. Furthermore, data augmentation is an effective technique to strengthen the ensemble algorithms in prediction.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091C (2023) https://doi.org/10.1117/12.2671805
As an important part of the power system, the power Internet of Things (IoT) is an effective active defense method to prevent and control security threats and strengthen the protection capability by effectively measuring and evaluating the network security risks it faces. Based on the investigation of the current situation, this paper puts forward a security risk assessment method for the power IoT. By collecting threat information, asset information and protective measures, and combining the characteristics of the power IoT, on the basis of assessing the vulnerability, asset value and the degree of asset impact, the network security risk quantified score value under the threat perspective is obtained, so as to evaluate the security risk faced more effectively. The validity of the method is verified by comparing the risk values before and after taking security measures in the scenario of distributed photovoltaic terminal access in the power IoT.
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.
Jiajia Cui, Biao Leng, Xianggen Wang, Fuxi Wang, Jun Yang
Proceedings Volume International Conference on Computer Application and Information Security (ICCAIS 2022), 126091D (2023) https://doi.org/10.1117/12.2671736
Malware in the network environment is a serious threat to the security of industrial control systems. With the gradual increase of malware variants, it brings great challenges to the detection and security protection of industrial control system malware. The existing detection methods have limitations such as low intelligence in adaptive detection and recognition. In response to this problem, this paper designs a detection application method framework by combining the use of reinforcement learning, an advanced machine learning algorithm, around the malware objects that threaten the network security of industrial control systems. In the implementation process, according to the actual needs of malware behavior detection, fully combined with intelligent features such as sequential decision-making and dynamic feedback learning of reinforcement learning, the key application modules such as feature extraction network, policy network and classification network are discussed and designed in detail. The application experiments based on the actual malware test data set verify the effectiveness of the method in this paper, which can provide an intelligent decision-making aid for general malware behavior 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.
Danxing Wang, Cong Lu, Mengjin Zeng, Dingling Luo, Mingliang Wang
Proceedings Volume International Conference on Computer Application and Information Security (ICCAIS 2022), 126091E (2023) https://doi.org/10.1117/12.2671656
Appropriate human-machine interface (HMI) designs were considered to be a way to enhance drivers’ cognition and improve their driving behavior. In this study, a new concept was introduced to the design of speeding alarm, which was expected to reduce the speeding behavior of drivers. Color and shape changes of user interface (UI) were considered to be beneficial to driving behavior. Four UIs were evaluated with the baseline, color change only, shape change only, and color change combining with shape change. These changes will occur when the vehicle is speeding. Task completion time, speeding duration, the average speed during speeding, reaction time of speeding judgment, and driver’s acceptance of the interfaces were collected from 18 licensed Chinese drivers. The experiment results showed that speeding alarm with color changes positively affect driver performance from a safety perspective. Owing to the color change of the interface, drivers tend to control the speed below the speed limit. However, traffic efficiency was not affected due to their speed control. The result of this study can be used as a reference for the UI designers.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091F (2023) https://doi.org/10.1117/12.2671467
Since 2016, which is regarded as the first year of the Era of Artificial Intelligence, the AI industry has been progressing rapidly with the fast development of mobile Internet and the massive generation of data. With data labeling the first key link of transferring human wisdom to machines or algorithms, the front end of building the AI industry chain is the need for a strong and powerful data labeling industry. The traditional data labeling industry is a labour-intensive industry that sells labour for cheap pay, and the data they label often does not belong to the labeling company itself, but to the data labeling commissioner. In this paper, we propose to build a data labeling industry centered on data trading, which is dedicated to transforming the data labeling company itself into a “big data company” to obtain ownership of the data. Thus, a large amount of labeled data for scenarios can be circulated through the “big data exchange” and other channels, promoting the rapid development of the overall artificial intelligence industry.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091G (2023) https://doi.org/10.1117/12.2671864
With the rapid development of China’s cities, the traffic load of urban roads has become more and more serious, and traffic congestion has become a major problem affecting the urban life. Intersection is an important node of urban traffic, and the imbalance of road load is one of the key factors leading to frequent intersection congestion. The article takes the intersection of Wuhu Road and Ningguo Road in Hefei City as an example, this paper analyzes the problems caused by unbalanced road load, proposes three optimization schemes based on the method of multi-dimensional collaborative optimization, and uses VISSIM to establish the simulation model before and after optimization, and compares the simulation results with the current situation. The results show that: for the optimization of the intersection with unbalanced traffic load. The multi-dimensional collaborative optimization method is superior to the single dimension optimization 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091H (2023) https://doi.org/10.1117/12.2671880
With the rapid development of information technique and equipment, the multi-dimensional data has been widely discussed and used in many domains. The Canonical Polyadic tensor Decomposition (CPD) is frequently employed for multi-dimensional data analysis, which has been extensively utilized in signal processing, image processing, computer vision, to name but a few. The satisfied accuracy and essential uniqueness of result computed by CPD can be guaranteed by using of exact rank value. However, the rank of the multi-dimensional data is usually unknown or is hard to obtain because of the noise disturbance in practice, thus the effectiveness of CPD is particularly weak with an inexact rank. To overcome this problem, this paper proposes a Robust CPD (R-CPD) method, which consists of two steps. The R-CPD firstly exploits the group sparsity of the over-estimated loading matrices to sense the real low rank and the group sparsity of the over-estimated loading matrices is pursued by adopting the mixed-norms, then the estimated rank can be used to compute CPD and thus obtain accurate results. Besides this paper provides the mathematical relationship on the mixednorms, nuclear norm (convex envelop of rank) and rank, and the corresponding mathematical proof to ensure the rationality of the proposed method. A series of experiments is implemented to assess the performance of the efficient RCPD 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091I (2023) https://doi.org/10.1117/12.2672176
In this paper, a synchronization control method is proposed to address the synchronization issue of the pump-controlled motor circuit of the hydraulic walking system. A double closed loop with fuzzy PID control method by applying this method is first utilized, which will reduce the error between each motor and the desired speed; then it is a cross-coupling synchronization method to reduce the speed error between two motors; finally, the purpose of synchronization of two motors will be realized. The simulation study showed that the synchronization accuracy will be effectively improved by employing this method. In addition, the tracking time can be shortened by 72% without overshoot when adjusting the speed of one side motor. After adding a sudden disturbance, the stability adjustment time is the shortest as well, and the overshoot is the smallest. Eventually, by using cross-coupling control, the synchronization error of motors on both sides will be reduced by 71%, and the error elimination time shortened by 21%. It meets the requirements of stability and synchronization control.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091J (2023) https://doi.org/10.1117/12.2672177
In order to objectively evaluate the input-output level of distribution network projects and improve the investment benefit of the distribution network, this paper considers the multi-dimensional driving factors, constructs a comprehensive and systematic investment benefit evaluation system, and proposes a cluster evaluation model of the distribution network investment benefit. In this model, the genetic algorithm and particle swarm optimization algorithm are applied to the K-means clustering model to realize collaborative clustering and improve the clustering effect. A heuristic algorithm is added to enhance the clustering efficiency, and the effectiveness and accuracy of the improved clustering algorithm proposed in this paper are verified by experiments. Finally, it is applied to an example to evaluate the investment benefit by clustering. Then the comprehensive post-evaluation of electric power investment projects is carried out by using the solved results, so as to realize the lean management and control of investment in distribution network construction and transformation of power grid companies.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091K (2023) https://doi.org/10.1117/12.2672179
In this paper, the ISIGHT software is used to decouple and optimize the powertrain mounting system (PMS) of a big mini passenger car and a six degrees of freedom (DOF) rigid body model of the PMS is established. The robust optimization model of the PMS is presented aiming at maximizing the decoupling ratios of the PMS, and the stiffness and the position parameters of each mount are selected as design variables. The statistic properties of the optimization objective and constraints are calculated using the first order Taylor series expansion. The robust optimization model is solved by combining the Modified Feasible Direction and Mixed Integer Optimization algorithms. Monte Carlo simulation is conducted to perform robustness analysis of the PMS by regarding the optimal variables as normal distribution random ones. The simulation results verify the robustness of the optimization 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091L (2023) https://doi.org/10.1117/12.2672189
The occurrence of forest fires often causes serious harm to people’s livelihood and economy. However, the current monitoring of forest fires has problems such as poor real-time interaction of forest fire-related information and low degree of data visualization. The front-end development of forest fires using relational databases MySQL and HTML5 is designed. The monitoring system processes and visualizes the fire point information sent by the sensors on the satellite in real time, realizes the real-time monitoring and rapid response of forest fires, and avoids the occurrence of large-scale fires to a certain extent. This paper studies the development method of forest fire monitoring system from the aspects of web front-end architecture and system architecture. The web front-end architecture describes the technical route of forest fire detection system implementation, and the system architecture describes the overall frame structure and design concept of forest fire detection system. Finally, the feasibility and applicability of the forest fire monitoring system are verified by the user interface function description.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091M (2023) https://doi.org/10.1117/12.2672180
With the development of anonymous network technology and the intensification of fighting domestic cyber crimes, more criminals tend to use the anonymity of Tor network to trade illegal and contraband goods and release reactionary remarks on the darknet in order to evade the supervision of public security departments, seriously endangering national security. Efficient monitoring of Chinese content on the darknet is of practical significance for obtaining investigation clues on the darknet and monitoring online public opinions. This study designs a batch extraction technology of Chinese darknet content based on Scrapy and obtaining the identification code of dark websites. Methods successfully extracts data from several Chinese Darknet online shops as well as Chinese forums, and makes further statistical analysis of the extracted data. Compared with other data monitoring methods on dark websites, this method can improve the extraction efficiency of target sites and has certain versatility, providing effective monitoring methods for fighting against darknet crimes.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091N (2023) https://doi.org/10.1117/12.2672183
This paper proposes a model for social network rumor detection that combines sentiment analysis and bi-directional graph convolutional networks (Bi-GCN) to deeply mine the semantic, sentiment, and structural features of information propagation contained in social network texts in order to improve rumor identification’s effectiveness. In this model, a BERT model is used to extract the semantic feature vector from a text, a Bi-GRU+Attention model is used to extract the sentiment feature vector from the text’s comments, and the feature vector is propagated along with the information extracted by the Bi-GCN networks to enrich the rumor detection model’s input features. The experimental results indicate that the precision ratio, recall ratio, and accuracy ratio of the method proposed in this paper are 10%, 9%, and 7% higher than those of the best performing model in the comparison models, respectively, demonstrating the model’s effectiveness.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091O (2023) https://doi.org/10.1117/12.2672191
Previous studies to defense against adversarial examples mostly focused on refining the DNN models but have either shown limited success or required expensive computation. In this paper, we introduce a new detection method against adversarial attacks. Since L0 attackers have similar search patterns, to separate clean examples from adversarial examples, we found a new distance measure on output layer. These strategies have low time and computing costs and can be easily complementary to other defenses. Moreover, our method performs well on adversarial noise localization task.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091P (2023) https://doi.org/10.1117/12.2671939
In order to improve the efficiency of nucleic acid detection and code allocation, inform the health of tested personnel, reduce labor costs and the possibility of medical personnel being infected, this paper uses the reliability of DCS and stratification, integration of mechanical arm technology, real-time fluorescent RT-PCR technology, distributed control system, using LabVIEW software system design and simulation. Through the determination of nucleic acid detection results and the monitoring and management of historical data, the communication system can precisely assign codes to all kinds of personnel, notify each place to seal the pipe, and provide data feedback to relevant personnel, so as to help determine the size of the sealed area and other purposes.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091Q (2023) https://doi.org/10.1117/12.2671303
It is necessary to build effectiveness infectious disease analysis methodology to avoid a large spreading of the disease. The factors playing role in epidemic come from different domain; moreover, their relationship is complex. Thus, it is very hard to mine the rule by single analysis. In this work, a total review is done to analyze the infected in the unit of years, which can provide a foundation to conclude the infectious rule. In order to finish this goal, Part Heuristic K-means based on Improved Grey Correlation Analysis is proposed. It uses improved grey correlation analysis to recognize the relevance among different diseases which has ability to guide the weight. Then, the year is partitioned into clusters based on distance function. It is found that the proportion of three degrees is respectively 21.4%, 28.6%, and 50%; the maximum of relevance is 0.888.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091R (2023) https://doi.org/10.1117/12.2671940
Based on statistical survey data, this paper explores the factors of food waste in colleges and universities under the background of “dual carbon”. Firstly, the support vector machine model is used to classify whether waste occurs in college cafeterias, and then the Probit regression model is established, exploring the factors that cause food waste, the result shows that food waste is related to personal characteristics, family background, food conservation promotion, and dining characteristics.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091S (2023) https://doi.org/10.1117/12.2671945
We provide customers with the best shopping experience, save cost of clothing display, make the whole process of clothing design more visualized, three-dimensional and interactive, and then improve the efficiency of brand culture information transmission, so that the concept of fashion design can be fully reflected. This paper starts from the concept and basic principle of 3D hologram technology, and explores the application of virtual reality technology in apparel display from three aspects: fashion show, virtual fitting, and offline attraction, in order to promote the deeper application of holographic projection technology in the apparel industry.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091T (2023) https://doi.org/10.1117/12.2671317
Medical insurance plays role in the wellbeing of population. However, the difficulty with the amount addition of participants increases dynamically. Especially, the increase of organizations including in this domain makes optimization of medical insurance complex. Thus, it is necessary to find the rule based on the information provided by the related to data as supplementary to support decision making. In order to finish this task, Neural Network, proved its robustness in data analysis, is included in the proposed data management frame. Input and cost as the most important attributes of medical insurance are set as target features. Then, the relationship between these two attributes must be considered. A skipping window is defined to adjust the proportion of the target features in training and testing stages. NN network with double direction of time window for medical insurance is given to foreseeing target attributes. Based on the simulation result, the largest average accuracy is 0.8333.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091U (2023) https://doi.org/10.1117/12.2671819
This article introduces the design and implementation of the safe transmission mechanism of wireless sensor network. The proposed solution improves the survival time of the sensor network, reduces the calculation intensity, decreases communication overhead of the nodes. This identified nodes solution guaranty a safer network and energy-saving system. The developed system uses the wireless microcontroller CC2430/CC2431 of Chipcon, which integrates CC2420RF wireless RF transceiver, then performs the simulation testing for program modules and 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091V (2023) https://doi.org/10.1117/12.2671741
This paper uses text mining techniques to study the hotspots and trends of Chinese medicine big data research. This study retrieved literature related to “Chinese medicine + big data” from China Knowledge Network and Wan fang database as a collection of research documents. Using python3 and related toolkits, text mining was performed on the relevant literature. Through cluster analysis, we obtained the rules of medication and the construction of big data platforms for Chinese medicine, which have been the hotspots of research in recent years; using co-occurrence analysis, knowledge graph analysis and other big data-related techniques to study the rules of medication, the rules of formulae, the thinking on the application of big data in Chinese medicine, the current situation and the construction of platforms, which are still the future research trends. The use of text mining technology can provide an intuitive and systematic representation of current hotspots as well as future development trends, and can provide methodological summaries and ideas for the modernization and development of Chinese medicine.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091W (2023) https://doi.org/10.1117/12.2671678
Based on the perspective of combining qualitative analysis and quantitative calculation, a method of operational concept capability requirement analysis is designed based on deep reinforcement learning. Firstly, it obtains the simulation small sample data set with high reliability based on simulation experiment. Secondly, the operational concept surrogate model is constructed on the empirical data, and the surrogate model is optimized and trained by using the multi-objective optimization algorithm with high credibility simulation data set as input. Finally, the trained surrogate model is interacted with the deep reinforcement learning framework to realize the reverse exploration of operational concept capability 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.
Yao Jing, Jingjing Tang, Yu Tai, Yuwei Li, Xinran Wang, Beichen Wang
Proceedings Volume International Conference on Computer Application and Information Security (ICCAIS 2022), 126091X (2023) https://doi.org/10.1117/12.2671682
The improvement of urban built-up environment is conducive to constructing a green city, promoting residents’ active life, and preventing and relieving hypertension. Based on the questionnaire and blood pressure measurement data, this paper constructs a structural equation model of multiple intermediaries in built-up environment, health behavior and hypertension, so as to analyze the influential factors of built-up environment on residents’ hypertension and clarify its path for influencing behavior. Research shows that the built-up environment in urban community has a significant impact on residents’ hypertension, and is not disturbed by individual health status. High-density supermarkets, convenience stores, parks and squares as well as low-density clinics and hospitals are likely to increase residents’ risk of hypertension and affect hypertension through healthy behaviors. Therefore, to improve the built-up environment in urban community will help to change the hygienic behavior, and improve the general level of the health, of residents.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091Y (2023) https://doi.org/10.1117/12.2671655
This paper studies the application of computer technology to identify tongue image information and its clinical application. Taking the case of clinical patients with heart palpitations as the research object, this paper explored the method of togue color extraction through combining the method of color science with computer technology. By extracting the total color difference, depth difference and saturation difference of different parts of the tongue, the characteristics of the color distribution are sought to obtain the color range, and the color characteristics of the tongue color of the heart palpitus are determined.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126091Z (2023) https://doi.org/10.1117/12.2671650
Piecewise linear regression (PLR) method is applied to study cumulative cases of COVID-19 evolving everyday in England up to 6th February 2022 just before travel restrictions are removed and people started not to get tested anymore in the UK and factors e.g. the lockdowns behind the spread COVID-19 are also investigated. It is clear that different periods exhibit distinct patterns depending on variants and government-imposed restriction. Therefore, the effectiveness of lockdown measures is evaluated by comparing the rate of increase after a certain period (delay effect of measures) and that of time before as well as how new variants take over as a dominant variant. In addition, autoregression function is studied to show strong effect of cases in the past on today’s cases since the disease is highly infectious. Most of work is carried out thorough python built-in libraries such as pandas for preprocessing data and matplotlib which allows us to gain more insight and better visualization into the real scenario. Visualization is conducted by Geoda showing the regional level of infections.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260920 (2023) https://doi.org/10.1117/12.2671473
Industrial users of fused magnesium have a certain demand response capability, which can provide flexible adjustment resources for high proportion of renewable energy power systems. In this paper, based on the analysis of the generation process and load characteristics of fused magnesium, a baseline load optimization calculation model for industrial users of fused magnesium was established with the goal of minimizing the electricity cost. On this basis, the demand response decision model of user agent for fused magnesium aiming at the minimum response cost and the power grid agent decision model aiming at tracking renewable energy power generation were constructed respectively, and a demand response analysis method of user for fused magnesium industry based on multi-agent modeling was proposed. Multiagent system simulation can provide necessary technical support for the formulation of demand response incentive measures and quantitative evaluation of the response capacity of users in the fused magnesium industry. A case study of an electromolten magnesium enterprise was carried out to verify the effectiveness of the proposed model and 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260921 (2023) https://doi.org/10.1117/12.2671315
Through the big data analysis platform and research methods, this paper studies the oil and gas resources management, mineral rights and reserve management based on the big data analysis research of Strategic Research Center of Oil and Gas Resources, Ministry of Natural Resources. The research uncovers the connections that are difficult to show in traditional technology, and assists business personnel to further improve the effectiveness and efficiency of petroleum and natural gas resources management and improve the efficiency of the reserves discovery, exploitation and utilization of petroleum and natural gas resources. It also promotes the petroleum and natural gas resources data integration and resource integration and promotes the open sharing of government data. By enhancing the technical means of relevant departments in dealing with petroleum and natural gas resources management, and establishing a “data-driven” scientific management concept, we will improve the modernization of the government’s governance capacity.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260922 (2023) https://doi.org/10.1117/12.2672154
In multicore fiber optical code division multiple access (OCDMA) systems with different quality of services requirement, Kwong and Yang introduce multiple-weight OOSPCs (optical orthogonal signature pattern codes) for 2D image transmission. Several works have been done on optimal balanced OOSPCs for weight set W ={3,4},{4,5},{3,4,5} . In this paper, by using the methods of combinatorics, optimal (5m,5n,{3,4,5},1, (3/5,1/5,1/5))-OOSPCs are obtained for any odd integer mn.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260923 (2023) https://doi.org/10.1117/12.2671685
In this paper, a design of air pollutant monitoring system with six modules based on Semi-supervised learning (SSL) is designed. More specifically, the data acquisition module, data pre-processing module, data classifier module, comprehensive analysis module, auxiliary sorting module, computer terminal module respectively realize data collection, dimension reduction pre-processing, classification, comprehensive analysis, sorting, observation and monitoring. After system operation, it perfectly realized the real-time monitoring and timely warning of haze pollution, and provided data support for the precision of urban air pollution prevention. The application of modern science and technology in air pollution monitoring has been realized, and the ability and level of air pollution prevention and control supervision have been improved. The experimental results show that the proposed system has higher accuracy monitoring of classification.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260924 (2023) https://doi.org/10.1117/12.2671820
As we all know that the performance analysis of dynamic systems will become complicated when a time delay occurs in the state derivative. For this situation, the paper puts forward a new method. By introducing the delay operator Δ, we transform this neutral system into an ordinary linear system. A novel criterion of stability is obtained by means of the Lyapunov theory and linear matrix inequality method. Finally, a numerical simulation is given to verify our 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260925 (2023) https://doi.org/10.1117/12.2671740
Differential equation has a wide range of applications in real life, and it is also an important branch of higher athematics. Through the explanation of practical cases, this paper introduces how to solve practical problems through the idea of mathematical modeling. At the same time, the numerical solution of the equation is obtained by combining MATLAB, and the purpose of combining theory with practice is 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260926 (2023) https://doi.org/10.1117/12.2671842
With the development of artificial intelligence and human-computer interaction technology, gesture has been widely used in intelligent vehicles, human-computer interaction, virtual reality, and other fields as an important way of communication in people’s daily life. However, there are few review studies that comprehensively evaluate and summarize gesture recognition in recent years. To address this situation, this paper classifies and summarizes the currently used gesture recognition methods. Firstly, the current status of research on static gestures is investigated, followed by an analysis of the progress of research on dynamic gesture recognition, then the commonly used gesture datasets are introduced and their respective characteristics are described, finally, the current challenges and future development trends of gesture recognition are analyzed.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260927 (2023) https://doi.org/10.1117/12.2671698
Although China’s meteorological departments have established a considerable number of national meteorological information monitoring networks, the information gap between meteorological departments, agricultural experts and ordinary farmers makes it impossible for them to accurately determine the objectives of agricultural production and improve the quality and efficiency of standard weather forecasts. This document addresses these issues. Therefore, this paper discusses the meteorological data collection method, collection equipment, crop fertility knowledge base and service forecast model based on the internet of things (IoT), real-time sensor data and the national integrated meteorological information sharing platform (CIMISS), develops meteorological data collection equipment suitable for small-scale agricultural environment, and develops an intelligent IoT service platform for integrated meteorology. The system has been demonstrated in a city meteorological bureau, and the results show that it can provide technical support for efficient planting, accurate management and customized services of agricultural 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.
Maobin Cai, Chensi Wu, Kefeng Fan, Xiaoying Zhao, Qifeng Sun
Proceedings Volume International Conference on Computer Application and Information Security (ICCAIS 2022), 1260928 (2023) https://doi.org/10.1117/12.2672174
Data security is an essential part of network security. Data storage, use, and transmission can easily lead to information leakage and other problems without adequate security protection. With the development of big data, China pays more attention to the data security industry. This paper focuses on the main business of typical China internet companies under big data background. This paper analyzes the data security risks in these businesses and gives some measures to deal with the risks.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 1260929 (2023) https://doi.org/10.1117/12.2672182
Web 3.0 is considered to be the next generation of the Internet. It is a decentralized Internet based on blockchain. Research on web 3.0 is essential for developing future Internet infrastructure and can also provide sustainable support for developing future business models. Web 3.0 applications are user-centered and can give convenience to data sharing while enhancing data privacy protection. However, Current web applications are less compatible with web 3.0. And there are relatively few application examples. In this paper, we have implemented a blockchain papers depository system based on web3.0. It uses smart contracts and web3.js to implement user interaction with the blockchain. In addition, we verify the feasibility of the system.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126092A (2023) https://doi.org/10.1117/12.2672184
Blockchain is becoming more popular with a combination of blockchain and the Internet of Things. The combination system is called IoT-blockchain system. Smart contracts play a critical role in IoT-blockchain systems. It can enable a wholly trusted transaction with no third parties. Therefore, the security of smart contracts needs to be guaranteed. To detect vulnerabilities in smart contracts, we use formal verification methods. We use Programming in logic (Prolog) theory to model contract programs. Then SWI-Prolog is utilized to check the model. In our paper, we use this formal method to check the vulnerability of smart contracts in Town Crier. The results show that Town Crier’s contracts satisfy the key security properties.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126092B (2023) https://doi.org/10.1117/12.2671352
With the development of social process, the change of times and the evolution of LE policy, the understanding of labor education (LE) and moral education will be different in different periods; Educators urgently need to look at LE from a new perspective, achieve the educational effect of 1 + 1 < 2 through the combination of LE and moral education, reunderstand labor education, and reconstruct China’s LE system of basic education from the perspective of “cultivating morality through labor” (CMTL). At the same time, intelligent network education (NE) integration system is also an important research topic of education departments and colleges and universities; With the continuous in-depth research on computer technology, people have gradually introduced scientific calculation methods into the education system, among which the intelligent test paper generation algorithm is one of many algorithms. This paper discusses the construction of NE integration system based on intelligent algorithm (IA), and puts forward an intelligent test paper generation algorithm based on improved genetic algorithm based on integer coding. It is verified by college students’ moral education test that using this algorithm, the system can select appropriate topics from the test question bank and combine them into a high-quality test paper; Using intelligent test paper generation algorithm to construct standard answer template for matching can effectively improve the scoring accuracy of subjective questions.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126092C (2023) https://doi.org/10.1117/12.2671485
The development of “new urbanization” human settlement environment is not only one of the important contents in the development of new urbanization, but also the key to be solved in the relationship between urban and rural areas. Therefore, this paper studies the intelligent algorithm in the intelligent monitoring model of human settlements under the improved fuzzy comprehensive evaluation (FCE). Taking Guizhou Province as an example, this paper studies and analyzes the karst landform and local land resource utilization, and evaluates the suitability of human settlements through the improved FCE algorithm. It is found that the evaluation results of coordinated development of residential environment and economy are consistent with the FCE results of human settlements. The higher the degree of coordination, the stronger the suitability of human settlements. The consistency between the degree of coordinated development and the evaluation results of the suitability of human settlements environment tests the scientificity and rationality of the FCE model of human settlements environment to a certain extent, so as to provide a scientific and feasible evaluation method for the suitability of human settlements 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126092D (2023) https://doi.org/10.1117/12.2671358
Nowadays, the pace of China’s modern economic construction is gradually accelerating, and the concrete structure has also entered a critical period of rapid development, which is widely used in people’s life. In this paper, the engineering system of RC structure based on ANSYS program is studied and analyzed under the SA. The RC structure engineering and the establishment of multiple interface structure model are analyzed, and the establishment of ANSYS finite element model is discussed; Through the general post-treatment plate of ANSYS, the ultimate strength of bamboo fiber RC beams with various volume ratios in bending test is tested. The experiment verifies the accuracy and feasibility of applying ANSYS program to RC structure engineering system.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126092E (2023) https://doi.org/10.1117/12.2671680
In recent years, with the rapid development of foundation pit engineering, many technically complex foundation pit engineering projects have emerged. The scale and depth of foundation pit excavation are getting bigger and bigger, and the requirements are getting stricter. The safety and stability of the foundation pit will determine the success or failure of the foundation pit project, and it is very important for the smooth development of the entire foundation pit project. The purpose of this paper is to study an intelligent optimization algorithm of thin-seal concrete layer technology for sheet pile foundation pits. Taking the support project as an example, the steel sheet pile support is determined as the foundation pit support scheme. The finite element software is used for simulation analysis, and the construction conditions are simulated for the scheme at the same time, the construction scheme is formulated, and the simulation results are compared and analyzed with the on-site monitoring results. The results show that when the construction of the sealing layer concrete is completed, the displacement monitoring value of the steel sheet pile is not much different from the simulated value, and does not exceed the early warning value, which is within the error 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126092F (2023) https://doi.org/10.1117/12.2671710
Since the reform and opening up, small and medium-sized privately owned economic enterprises have been consolidated, and there is bound to be an urgent need for information systems, especially with the continuous expansion of human resources teams after the development of enterprises. The purpose of human resource management (HRM) is to maximize the use of the company’s human resources, optimize the matching of work and personal abilities, use various incentive mechanisms and evaluation mechanisms, and provide a broad platform for talents. In this paper, a progressive fuzzy algorithm is proposed, the HRM system is designed through fuzzy neural network (FNN) and progressive FNN, and the other systems of the company are connected with the HRM system to realize data sharing. The HRM system is tested by 1200 users, 2400 users and 4800 users. The results show that the performance of the HRM system has been greatly improved in all aspects.
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.
Wei Liu, Haodong Xue, Feiyang Zhao, Ruiqing Hao, Lin Liao
Proceedings Volume International Conference on Computer Application and Information Security (ICCAIS 2022), 126092G (2023) https://doi.org/10.1117/12.2671700
At present, the research work on recycled concrete is still relatively slow and backward, and many problems are not studied in detail enough. It only stays at the material level, and there is no in-depth research on the performance of recycled concrete structures. The purpose of this paper is to study the automatic testing system of ceramsite concrete bearing capacity based on genetic algorithm. A prediction model for the flexural and shear resistance of RC beams after high temperature, and the bearing capacity of RC columns after high temperature, based on BP neural network and GA-BP neural network, was established to prove the effectiveness and efficiency of the automatic test system based on ceramsite concrete bearing capacity accuracy. The overall structure of the system is analyzed, and the following conclusions are obtained: Compared with the BP neural network prediction model, the flexural and shear bearing capacity of the RC beam based on the GA-BP neural network after high temperature and the axial compression of the RC column after high temperature are analyzed. The relative error, absolute error, average error and root mean square of the predicted data obtained by the bias bearing capacity prediction model and the theoretical calculation value are smaller.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126092H (2023) https://doi.org/10.1117/12.2671675
The demands of teaching English nowadays cannot be met by the traditional teaching method due to the rapid advancements in information technology. In order to meet the demands of smart classroom teaching, it is required to reconstruct traditional English teaching resources and enhance the traditional classroom’s organizational structure. This paper examines the attributes of intelligent teaching, reconstructs English teaching materials on the network platform, and employs information-based teaching organization forms to innovate teaching models to satisfy social development for talent training needs.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126092I (2023) https://doi.org/10.1117/12.2671356
Information technology plays a very important role in improving teaching effect and promoting education informatization. Cultivating talents with computer literacy through information technology education is gradually becoming a hot spot of educational development. Exploring a curriculum design platform with high efficiency, low technical threshold and simple operation has undoubtedly become the most urgent need for the development of education informatization. Therefore, this paper uses the Moodle platform to design the basic course of information technology, and meets the students’ learning needs by integrating teaching resources and giving full play to the platform’s teaching advantages. Through the platform teaching feedback experiment and teaching effect experiment, this paper analyzes whether the use of Moodle platform for information technology course teaching can improve learning interest and learning ability. The self-learning ability was improved, 76.39% of the students improved their collaborative learning ability, and 68.06% of the students improved their information processing 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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126092J (2023) https://doi.org/10.1117/12.2671574
Establishing and improving a scientific system and a system that fully extracts and utilizes commercial data plays an extremely important role in promoting the normal development of China’s foreign trade and maintaining the fundamental interests of the country and the industry. This paper aims to design an early warning system for international trade based on ant colony optimization algorithm. A method of dividing the optimized weights and thresholds into small sets is proposed for the optimization algorithm. The early warning indicator system, early warning model and early warning system construction of TBT are introduced in detail, and the design of TBT early warning system is described and demonstrated in detail. In the verification part, the algorithm after ant colony optimization is compared with the ordinary BP network before the improvement, and it is found that the error of the improved method is smaller, which shows the superiority of the algorithm in solving the problem of international trade early warning.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126092K (2023) https://doi.org/10.1117/12.2671576
At present, the deformation prediction during the construction of foundation pit is still in the exploratory stage. The more common prediction methods are to calculate the deformation based on numerical simulation software, or to find the law between the excavation conditions and the deformation according to the field measured data and use it for prediction of subsequent operating conditions. The deformation calculation accuracy of the numerical simulation software depends on the value of the model parameters, but the geotechnical parameters themselves are difficult to determine, the excavation process of the foundation pit is more complicated, and the excavation process of deep foundation pits is more complicated.The difficulty in determining the parameters can be efficiently overcome by doing an inverse analysis of the rock and soil characteristics based on field monitoring data (deformation, stress, etc.).According to the parameters obtained from the inverse analysis, the subsequent working conditions are simulated and calculated, and the deformation and stress of the foundation pit in the subsequent working conditions can be predicted.When comparing the excavation displacement inversion curve to the actual deformation curve of the soil layer parameters after inversion, the change trend of the two is essentially the same, and the relative error of the inversion is small. This paper uses the genetic algorithm to perform the inverse analysis of the engineering monitoring displacement. Experiments have proved the effectiveness of genetic algorithm prediction.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126092L (2023) https://doi.org/10.1117/12.2671686
With the continuous progress and growth of science and technology, high-end equipment manufacturing (HEM) has also ushered in a new era. Therefore, how to realize the transformation of HEM industry to intelligent and high-tech is an urgent problem to be solved. It is necessary to analyze the current problems and propose solutions and strategies to improve the company’s core competitiveness, Based on the combination of data mining and technology selection, this paper studies the growth and innovation mode of HEM industry. Firstly, this paper introduces the concept and basic characteristics of HEM innovation, and then studies the application of data mining technology in HEM innovation. Finally, the performance of the data mining technology is tested. The test results show that the data mining technology is very fast in processing data and analyzing innovation needs, and the accuracy of technology selection is also high.
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 International Conference on Computer Application and Information Security (ICCAIS 2022), 126092M (2023) https://doi.org/10.1117/12.2671707
Due to the maturity of database technology and the increase of data applications, the total amount of data stored by people has increased exponentially. Due to the rapid increase of the total amount of information, once there is no reasonable way to obtain useful information and knowledge in computer and information technology, network information will become a mess. Faced with this challenge, data mining technology came into being. This paper studies the application of association rule algorithm in intelligent manufacturing of mechanical manufacturing and automation majors. The management system is designed, and the association rule algorithm applied in the design is tested. Through the test results, it is concluded that the running time of the improved algorithm is much shorter than that of the Aprior algorithm, and the difference of the total time will also vary with the newly added data. The number of episodes increases and becomes larger. Therefore, in some fields where the database needs to be updated frequently, the IUAC algorithm shows obvious advantages.
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.