Traffic accident prediction based on an artificial bee colony algorithm and a self-adaptive fuzzy wavelet neural network
by Zhicheng Li
International Journal of Computing Science and Mathematics (IJCSM), Vol. 17, No. 3, 2023

Abstract: This study combines an artificial bee colony algorithm with a fuzzy wavelet neural network to establish a new traffic accident prediction model. It introduces the self-adaptive mutation operation of differential evolution algorithms and the selection operator, crossover operator, and mutation operator of a genetic algorithm into the traditional artificial bee colony algorithm. These actions aim to improve the shortcomings of the slow convergence rate and the weak local search ability of the artificial bee colony algorithm in the later period. This study also uses the improved artificial bee colony algorithm to optimise the weights and thresholds of the fuzzy wavelet neural network and to make up for the randomness of the weights and threshold selection of the wavelet neural network. It combines the good nonlinear fitting ability of the self-adaptive fuzzy wavelet neural network with the strong robustness of the artificial bee colony algorithm to build a model for predicting traffic death tolls. Computer simulation shows that the prediction accuracy of the proposed method is higher.

Online publication date: Tue, 13-Jun-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computing Science and Mathematics (IJCSM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com