Prediction model of Illegal Wildlife Trade using genetic algorithm and Bayesian optimization

Authors

  • Ziqi Li
  • Yiming Sun
  • Jiayu Wei
  • Yan Gao
  • Yifei Li

DOI:

https://doi.org/10.54097/ky6amq73

Keywords:

Genetic algorithm; Long short-term memory network; Difference in Differences method; Bayesian optimization; Support vector machine.

Abstract

In this paper, genetic algorithm and Long Short Term memory network (GA-LSTM) are used to predict the amount of global illegal wildlife trade, and differential method and Bayesian optimization support vector machine (SVM) are used to predict the future trade volume of high-risk countries. GA-LSTM model combines the memory retention ability of LSTM and the optimization ability of genetic algorithm, and performs well on time series data. The differential approach identifies strict international wildlife trade restrictions that significantly reduce the volume of trade, while large-scale infrastructure investments have a positive impact on raising local incomes. Bayesian optimization support vector machine (SVM) finds the global optimal parameters of the model through the probabilistic proxy model and the return function. The results of this paper provide data support for the government to strengthen governance.

Downloads

Download data is not yet available.

References

DAUT E F, BRIGHTSMITH D J, PETERSON M J. Role of non-governmental organizations in combating illegal wildlife–pet trade in Peru [J]. Journal for Nature Conservation, 2015, 24: 72-82.

MOZER A, PROST S. An introduction to illegal wildlife trade and its effects on biodiversity and society [J]. Forensic Science International: Animals and Environments, 2023, 3.

TLUSTY M F, CAWTHORN D-M, GOODMAN O L B, et al. Real-time automated species level detection of trade document systems to reduce illegal wildlife trade and improve data quality [J]. Biological Conservation, 2023, 281.

NIKBAKHT S, ANITESCU C, RABCZUK T. Optimizing the neural network hyperparameters utilizing genetic algorithm [J]. Journal of Zhejiang University-SCIENCE A, 2021, 22(6): 407-26.

ZHOU J, LI Z. Improved Genetic Algorithm to Optimize BP Neural Network [Z]. 2022 IEEE 10th Joint International Information Technology and Artificial Intelligence Conference (ITAIC). 2022: 1347-50.10.1109/itaic54216.2022.9836965

QIYUN C, CAIXIN S, XIAOXING Z. Short-Term load forecasting model and method for power system based on complementation of neural network and fuzzy logic [J]. Transactions of China Electrotechnical Society, 2004, 19(10): 53-8.

AMJADY N. Short-term hourly load forecasting using time-series modeling with peak load estimation capability [J]. IEEE Transactions on power systems, 2001, 16(3): 498-505.

BIAO S, XIA L Y, XHUA Y, WANG Y. Short-term load forecasting based on modified particle swarm optimizer and fuzzy neural network model [J]. Systems Engineering-Theory and Practice, 2010, 30(1): 158-60.

FUKUSHIMA C S, TRICORACHE P, TOOMES A, et al. Challenges and perspectives on tackling illegal or unsustainable wildlife trade [J]. Biological Conservation, 2021, 263.

FAN F, ZHANG X. Transformation effect of resource-based cities based on PSM-DID model: An empirical analysis from China [J]. Environmental Impact Assessment Review, 2021, 91: 106648.

XIE W, NIE W, SAFFARI P, et al. Landslide hazard assessment based on Bayesian optimization–support vector machine in Nanping City, China [J]. Natural Hazards, 2021, 109(1): 931-48.

Downloads

Published

20-05-2024