TRANSPORT FLOW FORECASTING BASED ON DEEP LEARNING MODELS
Abstract
This study is devoted to researching the problem of traffic congestion related to the growth of the number of vehicles in the world, in which the analysis of experiments to predict traffic flows using deep learning models is presented. Recurrent neural networks including the Elman model, LSTM, and GRU model were selected for the experiments, and the MSE indicator was used to compare their performance. The results showed that the GRU model performs best in predicting traffic flows, making it a promising tool for traffic management and infrastructure optimization.
Keywords:
traffic flow, recurrent neural network, Elman, LSTM, GRU, normalization, deep learning.References
W. Zeng et al., “Traffic Flow Prediction Based on Hybrid Deep Learning Models Considering Missing Data and Multiple Factors,” Sustainability 2023, Vol. 15, Page 11092, vol. 15, no. 14, p. 11092, Jul. 2023, doi: 10.3390/SU151411092.
H. F. Yang, T. S. DIllon, and Y. P. P. Chen, “Optimized Structure of the Traffic Flow Forecasting Model with a Deep Learning Approach,” IEEE Trans Neural Netw Learn Syst, vol. 28, no. 10, pp. 2371–2381, Oct. 2017, doi: 10.1109/TNNLS.2016.2574840.
B. L. Smith and M. J. Demetsky, “Traffic Flow Forecasting: Comparison of Modeling Approaches,” J Transp Eng, vol. 123, no. 4, pp. 261–266, Jul. 1997, doi: 10.1061/(ASCE)0733-947X(1997)123:4(261).
Farhad Mortezapour Shiri, Thinagaran Perumal, Norwati Mustapha, Raihani Mohamed “A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU” Computer Science, May 2023, pp 1-16, DOI:10.48550/arXiv.2305.17473
S. Hochreiter, J. Schmidhuber, Long Short-Term Memory. Neural Comput. 9, 8, 1735-1780, November 1997.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Жалелов Р.М.
This work is licensed under a Creative Commons Attribution 4.0 International License.
(+998)90 142-39-38
m.z.abdutolibov@gmail.com
@universal_jurnal
House 189 Kashgar Street, Marhamat district, Andijan region