Cargando…

Improved genetic algorithm optimized LSTM model and its application in short-term traffic flow prediction

Considering that the road short-term traffic flow has strong time series correlation characteristics, a new long-term and short-term memory neural network (LSTM)-based prediction model optimized by the improved genetic algorithm (IGA) is proposed to improve the prediction accuracy of road traffic fl...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Junxi, Qu, Shiru, Zhang, Zhiteng, Cheng, Shaokang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9454874/
https://www.ncbi.nlm.nih.gov/pubmed/36091988
http://dx.doi.org/10.7717/peerj-cs.1048
_version_ 1784785455345041408
author Zhang, Junxi
Qu, Shiru
Zhang, Zhiteng
Cheng, Shaokang
author_facet Zhang, Junxi
Qu, Shiru
Zhang, Zhiteng
Cheng, Shaokang
author_sort Zhang, Junxi
collection PubMed
description Considering that the road short-term traffic flow has strong time series correlation characteristics, a new long-term and short-term memory neural network (LSTM)-based prediction model optimized by the improved genetic algorithm (IGA) is proposed to improve the prediction accuracy of road traffic flow. Firstly, an improved genetic algorithm (IGA) is proposed by dynamically adjusting the mutation rate and crossover rate of standard GA. Secondly, the parameters of the LSTM, such as the number of hidden units, training times, gradient threshold and learning rate, are optimized by the IGA. Therefore, the optimal parameters are obtained. In the analysis stage, 5-min short-term traffic flow data are used to demonstrate the superiority of the proposed method over the existing neural network algorithms. Finally, the results show that the Root Mean Square Error achieved by the proposed algorithm is lower than that achieved by the other neural network methods in both the weekday and weekend data sets. This verifies that the algorithm can adapt well to different kinds of data and achieve higher prediction accuracy.
format Online
Article
Text
id pubmed-9454874
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-94548742022-09-09 Improved genetic algorithm optimized LSTM model and its application in short-term traffic flow prediction Zhang, Junxi Qu, Shiru Zhang, Zhiteng Cheng, Shaokang PeerJ Comput Sci Adaptive and Self-Organizing Systems Considering that the road short-term traffic flow has strong time series correlation characteristics, a new long-term and short-term memory neural network (LSTM)-based prediction model optimized by the improved genetic algorithm (IGA) is proposed to improve the prediction accuracy of road traffic flow. Firstly, an improved genetic algorithm (IGA) is proposed by dynamically adjusting the mutation rate and crossover rate of standard GA. Secondly, the parameters of the LSTM, such as the number of hidden units, training times, gradient threshold and learning rate, are optimized by the IGA. Therefore, the optimal parameters are obtained. In the analysis stage, 5-min short-term traffic flow data are used to demonstrate the superiority of the proposed method over the existing neural network algorithms. Finally, the results show that the Root Mean Square Error achieved by the proposed algorithm is lower than that achieved by the other neural network methods in both the weekday and weekend data sets. This verifies that the algorithm can adapt well to different kinds of data and achieve higher prediction accuracy. PeerJ Inc. 2022-07-19 /pmc/articles/PMC9454874/ /pubmed/36091988 http://dx.doi.org/10.7717/peerj-cs.1048 Text en © 2022 Zhang et al. https://creativecommons.org/licenses/by-nc/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by-nc/4.0/) , which permits using, remixing, and building upon the work non-commercially, as long as it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Adaptive and Self-Organizing Systems
Zhang, Junxi
Qu, Shiru
Zhang, Zhiteng
Cheng, Shaokang
Improved genetic algorithm optimized LSTM model and its application in short-term traffic flow prediction
title Improved genetic algorithm optimized LSTM model and its application in short-term traffic flow prediction
title_full Improved genetic algorithm optimized LSTM model and its application in short-term traffic flow prediction
title_fullStr Improved genetic algorithm optimized LSTM model and its application in short-term traffic flow prediction
title_full_unstemmed Improved genetic algorithm optimized LSTM model and its application in short-term traffic flow prediction
title_short Improved genetic algorithm optimized LSTM model and its application in short-term traffic flow prediction
title_sort improved genetic algorithm optimized lstm model and its application in short-term traffic flow prediction
topic Adaptive and Self-Organizing Systems
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9454874/
https://www.ncbi.nlm.nih.gov/pubmed/36091988
http://dx.doi.org/10.7717/peerj-cs.1048
work_keys_str_mv AT zhangjunxi improvedgeneticalgorithmoptimizedlstmmodelanditsapplicationinshorttermtrafficflowprediction
AT qushiru improvedgeneticalgorithmoptimizedlstmmodelanditsapplicationinshorttermtrafficflowprediction
AT zhangzhiteng improvedgeneticalgorithmoptimizedlstmmodelanditsapplicationinshorttermtrafficflowprediction
AT chengshaokang improvedgeneticalgorithmoptimizedlstmmodelanditsapplicationinshorttermtrafficflowprediction