Long-Term Traffic Flow Prediction using Hybrid Deep Learning Technique
Long-Term Traffic Flow Prediction using Hybrid Deep Learning Technique |
||
 |
 |
|
| © 2023 by IJETT Journal | ||
| Volume-71 Issue-5 |
||
| Year of Publication : 2023 | ||
| Author : Mohandu Anjaneyulu, Mohan Kubendiran |
||
| DOI : 10.14445/22315381/IJETT-V71I5P216 | ||
How to Cite?
Mohandu Anjaneyulu, Mohan Kubendiran, "Long-Term Traffic Flow Prediction using Hybrid Deep Learning Technique," International Journal of Engineering Trends and Technology, vol. 71, no. 5, pp. 156-165, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I5P216
Abstract
Smart city traffic regulation relies heavily on advanced traffic management systems (ATMS), a key component of the broader intelligent transportation system (ITS). Traffic flow forecasting is a crucial aspect of transportation that aids in traffic planning, control, management, and information dissemination. Although there are a great variety of models whose primary focus is on the development of short-term traffic flow predictions, making credible long-term traffic flow (LTTF) forecasts has become an increasingly difficult topic in recent years. To solve this problem, this paper proposed a novel hybrid model called the autoencoder gated recurrent unit (AEGRU) that can accurately predict long-term traffic flow for the next 24 hours. Firstly, the autoencoder (AE) will take the raw data and pick out the most important features before doing dimensionality reduction. Secondly, the gated recurrent unit (GRU) uses the information given by the AE to make predictions about how much traffic volume there will be in the future. The outcomes of the evaluation show that the proposed AEGRU model is much better than compared approaches in terms of root mean square error (RMSE) of 1.6% mean absolute percentage error (MAPE) of 2.3% and mean absolute error (MAE) of 1.9%.
Keywords
Traffic flow prediction, Long-term traffic flow prediction, Autoencoder, Gated recurrent unit, Neural networks, Deep learning.
References
[1] Yuhan Jia, Jianping Wu, and Ming Xu, “Traffic Flow Prediction with Rainfall Impact Using a Deep Learning Method,” Journal of Advanced Transportation, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Junping Zhang et al., “Data-Driven Intelligent Transportation Systems: A Survey,” IEEE Transactions on Intelligent Transportation Systems, vol. 12, no. 4, pp. 1624-1639, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Fei Su et al., “Long-Term Forecasting Oriented to Urban Expressway Traffic Situation,” Advances in Mechanical Engineering, vol. 8, no. 1, pp. 1-16, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Xiaobo Chen et al., “Ensemble Learning Multiple LSSVR with Improved Harmony Search Algorithm for Short-Term Traffic Flow Forecasting,” IEEE Access, vol. 6, pp. 9347-9357, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Eleni I. Vlahogianni et al., “Short-Term Traffic Forecasting: Where We are and Where We’re Going,” Transportation Research Part C: Emerging Technologies, vol. 43, pp. 3-19, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Yiqun Li et al., “A Hybrid Deep Learning Framework for Long-Term Traffic Flow Prediction,” IEEE Access, vol. 9, pp. 11264-11271, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Zhumei Wang, Xing Su, and Zhiming Ding, “Long-Term Traffic Prediction Based on LSTM Encoder-Decoder Architecture,” IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 10, pp. 6561-6571, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Senzhang Wang, Jiannong Cao, and Philip S. Yu, “Deep Learning for Spatio-Temporal Data Mining: A Survey,” IEEE Transactions on Knowledge and Data Engineering, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Jürgen Schmidhuber, “Deep Learning in Neural Networks: An Overview,” Neural networks, vol. 61, pp. 85-117, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Mascha Van Der Voort, Mark Dougherty, and Susan Watson, “Combining Kohonen Maps with ARIMA Time Series Models to Forecast Traffic Flow,” Transportation Research Part C: Emerging Technologies, vol. 4, no. 5, pp. 307-318, 1996.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Kit Yan Chan et al., “Neural-Network-Based Models for Short-Term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg–Marquardt Algorithm,” IEEE Transactions on Intelligent Transportation Systems, vol. 13, no. 2, pp. 644-654, 2012.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Selvaraj Vasantha Kumar, “Traffic Flow Prediction Using Kalman Filtering Technique,” Procedia Engineering, vol. 187, pp. 582-587, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Zheng Zhao et al., “LSTM Network: A Deep Learning Approach for Short-Term Traffic Forecast,” IET Intelligent Transport Systems, vol. 11, no. 2, pp. 68-75, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Yi Hou, Praveen Edara, and Yohan Chang, “Road Network State Estimation Using Random Forest Ensemble Learning,” 2017 IEEE 20th International Conference on Intelligent Transportation Systems, pp. 1-6, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Zhang Mingheng et al., “Accurate Multisteps Traffic Flow Prediction Based on SVM,” Mathematical Problems in Engineering, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Shiliang Sun, Changshui Zhang, and Guoqiang Yu, “A Bayesian Network Approach to Traffic Flow Forecasting,” IEEE Transactions on Intelligent Transportation Systems, vol. 7, no. 1, pp.124-132, 2006.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Bin Sun et al., “Short-Term Traffic Forecasting Using Self-Adjusting K-Nearest Neighbours,” IET Intelligent Transport Systems, vol. 12, no. 1, pp. 41-48, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Deva Priya Isravel, Salaja Silas, and Elijah Blessing Rajsingh, “Long-Term Traffic Flow Prediction Using Multivariate SSA Forecasting in SDN Based Networks,” Pervasive and Mobile Computing, vol. 83, p. 101590, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Hao Peng et al., “Dynamic Graph Convolutional Network for Long-Term Traffic Flow Prediction with Reinforcement Learning,” Information Sciences, vol. 578, pp. 401-416, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Asma Belhadi et al., “A Recurrent Neural Network for Urban Long-Term Traffic Flow Forecasting,” Applied Intelligence, vol. 50, no. 10, pp. 3252-3265, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Qu Licheng et al., “Daily Long-Term Traffic Flow Forecasting Based on a Deep Neural Network,” Expert Systems with Applications, vol. 121, pp. 304-312, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Autoencoders in Deep Learning. [Online]. Availability: https://www.v7labs.com/blog/autoencoders-guide/
[23] Introduction to Gated Recurrent Unit (GRU). [Online]. Availability: https://www.analyticsvidhya.com/blog/2021/03/introduction-to-gated-recurrent-unit-gru/
[24] Road Traffic Statistics, Great Britain, UK. [Online]. Available: https://roadtraffic.dft.gov.uk/downloads
[25] Alexei Botchkarev, “Performance Metrics (Error Measures) in Machine Learning Regression, Forecasting and Prognostics: Properties and Typology,” ArXiv preprint arXiv: 1809.03006, 2018.
[CrossRef] [Google Scholar] [Publisher Link]