GRU-LSTM model based on the SSA for short-term traffic flow prediction

The transportation department relies on accurate traffic forecasting for effective decision-making. However, determining relevant parameters for existing traffic flow prediction models poses challenges. To address this issue, this study proposes a hybrid model, sparrow search algorithm-gated recurre...

Full description

Saved in:
Bibliographic Details
Main Authors: Changxi Ma, Xiaoyu Huang, Yongpeng Zhao, Tao Wang, Bo Du
Format: Article
Language:English
Published: Tsinghua University Press 2025-03-01
Series:Journal of Intelligent and Connected Vehicles
Subjects:
Online Access:https://www.sciopen.com/article/10.26599/JICV.2024.9210051
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849326142295638016
author Changxi Ma
Xiaoyu Huang
Yongpeng Zhao
Tao Wang
Bo Du
author_facet Changxi Ma
Xiaoyu Huang
Yongpeng Zhao
Tao Wang
Bo Du
author_sort Changxi Ma
collection DOAJ
description The transportation department relies on accurate traffic forecasting for effective decision-making. However, determining relevant parameters for existing traffic flow prediction models poses challenges. To address this issue, this study proposes a hybrid model, sparrow search algorithm-gated recurrent unit-long short-term memory (SSA-GRU-LSTM), which leverages the SSA to optimize the GRUs and LSTM networks. The SSA is employed to identify the optimal parameters for the GRU-LSTM model, mitigating their impact on prediction accuracy. This model integrates the predictive efficiency of the GRU, LSTM’s capability in temporal data analysis, and the fast convergence and global search attributes of the SSA. Comprehensive experiments are conducted to validate the proposed method via traffic flow datasets, and the results are compared with those of baseline models. The numerical results demonstrate the superior performance of the SSA-GRU-LSTM model. Compared with the baselines, the proposed model results in reductions in the root mean square error (RMSE) of 4.632%–45.206%, the mean absolute error (MAE) of 2.608%–53.327%, the mean absolute percentage error (MAPE) of 1.324%–13.723%, and an increase in R2 of 0.5%–17.5%. Consequently, the SSA-GRU-LSTM model has high prediction accuracy and measurement stability.
format Article
id doaj-art-63397c0010ba4873b193d98b04258db4
institution Kabale University
issn 2399-9802
language English
publishDate 2025-03-01
publisher Tsinghua University Press
record_format Article
series Journal of Intelligent and Connected Vehicles
spelling doaj-art-63397c0010ba4873b193d98b04258db42025-08-20T03:48:14ZengTsinghua University PressJournal of Intelligent and Connected Vehicles2399-98022025-03-0181921005110.26599/JICV.2024.9210051GRU-LSTM model based on the SSA for short-term traffic flow predictionChangxi Ma0Xiaoyu Huang1Yongpeng Zhao2Tao Wang3Bo Du4School of Traffic and Transportation, Lanzhou Jiaotong University, Lanzhou 730070, ChinaSchool of Traffic and Transportation, Lanzhou Jiaotong University, Lanzhou 730070, ChinaGansu Highway Traffic Construction Group Co., Ltd., Lanzhou 730000, ChinaSchool of Architecture and Transportation Engineering, Guilin University of Electronic Technology, Guilin 541004, ChinaDepartment of Business Strategy and Innovation, Griffith University, Brisbane QLD 4111, AustraliaThe transportation department relies on accurate traffic forecasting for effective decision-making. However, determining relevant parameters for existing traffic flow prediction models poses challenges. To address this issue, this study proposes a hybrid model, sparrow search algorithm-gated recurrent unit-long short-term memory (SSA-GRU-LSTM), which leverages the SSA to optimize the GRUs and LSTM networks. The SSA is employed to identify the optimal parameters for the GRU-LSTM model, mitigating their impact on prediction accuracy. This model integrates the predictive efficiency of the GRU, LSTM’s capability in temporal data analysis, and the fast convergence and global search attributes of the SSA. Comprehensive experiments are conducted to validate the proposed method via traffic flow datasets, and the results are compared with those of baseline models. The numerical results demonstrate the superior performance of the SSA-GRU-LSTM model. Compared with the baselines, the proposed model results in reductions in the root mean square error (RMSE) of 4.632%–45.206%, the mean absolute error (MAE) of 2.608%–53.327%, the mean absolute percentage error (MAPE) of 1.324%–13.723%, and an increase in R2 of 0.5%–17.5%. Consequently, the SSA-GRU-LSTM model has high prediction accuracy and measurement stability.https://www.sciopen.com/article/10.26599/JICV.2024.9210051traffic flow predictionhybrid modelsparrow search algorithm (ssa)long short-term memory (lstm) networkgated recurrent unit (gru)
spellingShingle Changxi Ma
Xiaoyu Huang
Yongpeng Zhao
Tao Wang
Bo Du
GRU-LSTM model based on the SSA for short-term traffic flow prediction
Journal of Intelligent and Connected Vehicles
traffic flow prediction
hybrid model
sparrow search algorithm (ssa)
long short-term memory (lstm) network
gated recurrent unit (gru)
title GRU-LSTM model based on the SSA for short-term traffic flow prediction
title_full GRU-LSTM model based on the SSA for short-term traffic flow prediction
title_fullStr GRU-LSTM model based on the SSA for short-term traffic flow prediction
title_full_unstemmed GRU-LSTM model based on the SSA for short-term traffic flow prediction
title_short GRU-LSTM model based on the SSA for short-term traffic flow prediction
title_sort gru lstm model based on the ssa for short term traffic flow prediction
topic traffic flow prediction
hybrid model
sparrow search algorithm (ssa)
long short-term memory (lstm) network
gated recurrent unit (gru)
url https://www.sciopen.com/article/10.26599/JICV.2024.9210051
work_keys_str_mv AT changxima grulstmmodelbasedonthessaforshorttermtrafficflowprediction
AT xiaoyuhuang grulstmmodelbasedonthessaforshorttermtrafficflowprediction
AT yongpengzhao grulstmmodelbasedonthessaforshorttermtrafficflowprediction
AT taowang grulstmmodelbasedonthessaforshorttermtrafficflowprediction
AT bodu grulstmmodelbasedonthessaforshorttermtrafficflowprediction