Simulation and prediction study based on Lotka-Volterra model and grey neural network

Boren Xie; Xin Huang; Dongyang Wang

doi:10.1117/12.3032961

5 July 2024 Simulation and prediction study based on Lotka-Volterra model and grey neural network

Boren Xie, Xin Huang, Dongyang Wang

Proceedings Volume 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024); 1318462 (2024) https://doi.org/10.1117/12.3032961
Event: 3rd International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 2024, Kuala Lumpur, Malaysia

Abstract

In this research, we innovatively utilize differential equations to simulate ituation in the real world, offering a rigorous mathematical framework for our predictive model. The Lotka-Volterra model forms the basis of our simulation, enabling the detailed representation of species interactions over time. Through sophisticated data processing techniques, including normalization and imputation for missing values, we enhance the fidelity of our simulation inputs. The application of a grey neural network, tailored with a sigmoid activation function and optimized learning rate, allows for the accurate prediction of future population trends. A key contribution of our work is the visualization of simulation results, achieved through graphical representations, which not only validates our model but also provides intuitive insights into the complex dynamics governing species populations. This study not only showcases the integration of mathematical modeling with neural networks for ecological predictions but also demonstrates the power of visualization in comprehending and communicating complex data patterns.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Boren Xie, Xin Huang, and Dongyang Wang "Simulation and prediction study based on Lotka-Volterra model and grey neural network", Proc. SPIE 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 1318462 (5 July 2024); https://doi.org/10.1117/12.3032961

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

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.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available