Research on Short-Term Traffic Flow Prediction Based on KOA-CNN-BiGRU-MultiAttention Hybrid Neural Network Model
DOI:
https://doi.org/10.54097/gww5br40Keywords:
KOA, CNN, Bidirectional GRU, Multi Attention, Short-term Traffic Flow Prediction.Abstract
The demand for transportation brought about by urban population expansion has been increasing in the last few decades, and since the construction of transportation infrastructure is becoming highly saturated, it is tougher for regular traffic management measures to effectively ease traffic congestion in daily travel. Due to the wide application of deep learning in the field of transportation, a great number of deep learning models have been applied to traffic flow prediction in a various traffic environments, and short-term traffic flow prediction is undoubtedly among the most economical and effective measures to assist traffic management. In this paper, a hybrid neural network of KOA-CNN-BiGRU-MultiAttention based on pytorch deep learning framework for short-term traffic flow prediction is proposed. This model shows significant advantages of high prediction accuracy and robustness compared with traditional CNN-BiGRU-Attention prediction model, and its rapid response has significant advantages in predicting the characteristics of road network traffic flow.
Downloads
References
[1] WANG Xiang-xue, XU Lun-hui. Short-term Traffic Flow Prediction Based on Deep Learning[J]. Journal of Transportation Systems Engineering and Information Technology, 2018,18(01):81-88.
[2] FENG Ning, GUO Sheng-Nan, SONG Chao, et al. Multi-component Spatial-temporal Graph Convolution Networks for Traffic Flow Forecasting[J]. Journal of Software, 2019, 30(03):759-769.
[3] YUAN Hua, CHEN Zehao. Short-term Traffic Flow Prediction Based on Temporal Convolutional Networks[J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(11):107-113+122.
[4] Nisha Singh, Kranti Kumar, Bhawna Pokhriyal. Attention based spatiotemporal model for short-term traffic flow prediction[J]. International Journal of System Assurance Engineering and Management, 2025, 16(4):1-15.
[5] Sonia Mrad, Rafaa Mraihi, Aparna S. Murthy. Efficient implementation of a wavelet neural network model for short-term traffic flow prediction: Sensitivity analysis[J]. International Journal of Transportation Science and Technology, 2025, 17:21-38.
[6] Naheliya Bharti, Redhu Poonam, Kumar Kranti. Deep Bi-LSTM Neural Network with Chaotic Particle Swarm Optimization Technique for Short-Term Traffic Speed Prediction. Springer Nature Singapore, 2025, :171-191.
[7] Guowen Dai, Jinjun Tang. A Short-Term Traffic Flow Prediction Method Based on Personalized Lightweight Federated Learning[J]. Sensors, 2025, 25(3):967-967.
[8] Xiaoqing Wang, Feng Sun, Xiaolong Ma, et al. Short-term traffic flow prediction based on vehicle trip chain features[J]. Transportation Letters, 2025, 17(1):157-168.
[9] Ali Reza Sattarzadeh, Ronny J. Kutadinata, Pubudu N. Pathirana, et al. A novel hybrid deep learning model with ARIMA Conv-LSTM networks and shuffle attention layer for short-term traffic flow prediction[J]. Transportmetrica A: Transport Science, 2025, 21(1):388-410.
[10] Lingjuan Chen, Cong Xie, Dongfang Ma, et al. A short-term traffic flow prediction model for road networks using inverse isochrones to determine dynamic spatiotemporal correlation ranges[J]. Physica A: Statistical Mechanics and its Applications, 2025, 657:130244-130244.
[11] Derong Xie, Hongli Chen, Huiming Duan. A dynamic multivariate partial grey model based on the traffic flow parameter equation and its application[J]. Physica A: Statistical Mechanics and its Applications, 2024, 656:130204-130204.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
