ABSTRACT
Spatiotemporal data, such that collected from road traffic monitoring and congestion prediction, exhibits temporal and geographical relationships. This investigation employs a two-pronged strategy, first investigating spatiotemporal characteristics and then creating a model for traffic flow monitoring and congestion prediction based on a deep neural network. With the use of a graph convolutional neural network and an attention mechanism, this research is the first to propose a method for learning spatial features of traffic flows. To improve our expression and the capacity to extract relevant spatial attributes, we introduce node adaptive learning and apply different weights to the degree of mutual influence across different nodes. Furthermore, we present a temporal convolutional network-based learning approach for temporal features of traffic flow, which uses causal convolution to guarantee that input and output data dimensions are consistent. Long-length spatiotemporal sequence data benefit greatly from the dilated convolution's ability to dynamically regulate the receptive field by adjusting the sampling interval. Using spatiotemporal graphs, a system is developed to monitor and foresee traffic congestion. In order to learn feature information, mode-specific parameter values, and overall model performance, this model combines a graph convolutional neural network with an attention mechanism.
- Haifeng Zheng, Feng Lin, Xinxin Feng, and Youjia Chen. 2021. A Hybrid Deep Learning Model With Attention-Based Conv-LSTM Networks for Short-Term Traffic Flow Prediction. IEEE Transactions on Intelligent Transportation Systems, vol. 22, pp. 6910-6920Google ScholarDigital Library
- Aniekan Essien, Ilias Petrounias, Pedro Sampaio, and Sandra Sampaio. 2021. A deep-learning model for urban traffic flow prediction with traffic events mined from twitter. World Wide Web, vol. 24, pp. 1345-1368Google ScholarDigital Library
- Anirudh Ameya Kashyap. 2022. Traffic flow prediction models–A review of deep learning techniques. Cogent Engineering, vol. 9, p. 2010510Google ScholarCross Ref
- Jianbin Li, Shike Li, Long Cheng, Qingzhi Liu, Jiaming Pei, and Shen Wang. 2022. BSAS: A Blockchain-Based Trustworthy and Privacy-Preserving Speed Advisory System. IEEE Transactions on Vehicular Technology, vol. 71, 11421-11430Google ScholarCross Ref
- Chen Chen, Ziye Liu, Shaohua Wan, Jintai Luan, and Qingqi Pei .2020. Traffic flow prediction based on deep learning in internet of vehicles. IEEE transactions on intelligent transportation systems, vol. 22, pp. 3776-3789Google Scholar
- Yiqun Li, Songjian Chai, Zhengwei Ma, and Guibin Wang. 2021. A hybrid deep learning framework for long-term traffic flow prediction. IEEE Access, vol. 9, pp. 11264-11271Google ScholarCross Ref
- Nicholas G Polson, and Vadim O. Sokolov. 2017. Deep learning for short-term traffic flow prediction. Transportation Research Part C: Emerging Technologies, vol. 79, pp. 1-17Google ScholarCross Ref
- Jianhu Zheng, and Mingfang Huang. 2020. Traffic flow forecast through time series analysis based on deep learning. IEEE Access, vol. 8, pp. 82562-82570Google ScholarCross Ref
- Shahid Mumtaz, Kazi Mohammed Saidul Huq, Ayman Radwan, Jonathan Rodriguez, and Rui L. Aguiar. 2014. Energy efficient interference-aware resource allocation in LTE-D2D communication. 2014 IEEE International Conference on Communications. IEEE, 282-287Google Scholar
- Cong Li, and Pei Xu. 2021. Application on traffic flow prediction of machine learning in intelligent transportation. Neural Computing and Applications, vol. 33, pp. 613-624Google ScholarDigital Library
- Shahid Mumtaz, Henrik Lundqvist, Kazi Mohammed Saidul Huq, Jonathan Rodriguez, and Ayman Radwan. 2014. Smart Direct-LTE communication: An energy saving perspective. Ad Hoc Networks, vol. 13, 296-311Google ScholarDigital Library
- Poonam Redhu, and Kranti Kumar. 2023. Short-term traffic flow prediction based on optimized deep learning neural network: PSO-Bi-LSTM. Physica A: Statistical Mechanics and its Applications, vol. 625, p. 129001Google Scholar
- Jiaming Pei, Kaiyang Zhong, Jinhai Li, and Zhi Yu. 2022. PAC: partial area clustering for re-adjusting the layout of traffic stations in city's public transport. IEEE Transactions on Intelligent Transportation Systems, vol. 24, 1251-1260Google ScholarCross Ref
- Azzedine Boukerche, and Jiahao Wang. 2020. A performance modeling and analysis of a novel vehicular traffic flow prediction system using a hybrid machine learning-based model. Ad Hoc Networks, vol. 106, p. 102224Google ScholarCross Ref
Recommendations
Traffic Flow Prediction With Big Data: A Deep Learning Approach
Accurate and timely traffic flow information is important for the successful deployment of intelligent transportation systems. Over the last few years, traffic data have been exploding, and we have truly entered the era of big data for transportation. ...
Traffic Flow Prediction Using Long-Short Term Memory Technique for Connected Vehicles in Smart Cities
Advances in Visual InformaticsAbstractAn intelligent transportation system is an advanced application that aims to improve the efficiency and safety of various modes of transportation. It works by providing innovative services related to different modes of transportation and traffic ...
A Survey of Hybrid Deep Learning Methods for Traffic Flow Prediction
ICAIP '19: Proceedings of the 2019 3rd International Conference on Advances in Image ProcessingTraffic flow prediction using big data and deep learning attracts great attentions in recent years. Researchers show that DNN models can provide better traffic prediction accuracy than the traditional shallow models. Since the traffic flow reveals both ...
Comments