Short Term Prediction of Urban Traffic Flow based on Machine Learning Algorithms

Conghe Wang

doi:10.54097/5c1y5h07

Authors

Conghe Wang

DOI:

https://doi.org/10.54097/5c1y5h07

Keywords:

Traffic flow; LSTM; random forest; prediction.

Abstract

With the increasing per capita car ownership worldwide, existing transportation facilities are unable to fully meet people's travel needs. The massive traffic flow can lead to traffic congestion, so predicting traffic flow can play a crucial role in urban traffic management. This study predicts the westbound traffic flow data of the Minnesota Department of Transportation (MN DoT) ATR 301 station on Interstate 94 in the United States for 28 consecutive days using a Long Short-Term Memory Network (LSTM) data prediction model. The Random Forest is utilized to analyze the association between attributes and the historical data has been separated into 1-hour intervals. The highway displays a bimodal pattern on weekdays and a unimodal pattern on holidays, according to the final forecast results. Furthermore, after making the necessary adjustments to the parameters, the simulated trend closely resembles the real value, proving that LSTM can be used to model short-term traffic flow. Accurately predicting urban traffic flow can make the management of urban traffic management systems more comprehensive and provide citizens with higher quality travel planning references.

Downloads

Download data is not yet available.

References

[1] Zhang Kunpeng, Zheng Liang, Liu Zijian, et al. A deep leaning based multitask model for network-wide traffic speed prediction. Neurocomputing, 2020, 396: 438-450.

[2] Zhou Feng, Wang Shipu, Zhang Kunpeng. Short-term Traffic Flow Prediction Model of Urban Road Network Based on Graph Transformer Network. Science Technology and Engineering, 2024, 24(10): 4307-4316.

[3] He Yiyang, Yin Feng, Yuan Ping. Survey of short-term traffic flow prediction models in intelligent transportation system. Modern Computer, 2020(16): 8-11.

[4] Long Jiancheng, Guo Jiaqi. Review and prospect of dynamic traffic assignment research. Journal of Transportation Systems Engineering and Information Technology,2021,21(5): 125-138.

[5] Lv Hongyan, Feng Qian. A Review of Random Forest Algorithm Research. Journal of Hebei Academy of Sciences, 2019, 36(03): 37-41.

[6] Zhu Shiwei, Ye Baolin, Wu Weimin. A review and simulation study on short-term traffic flow prediction methods based on deep learning. Software Guide, 23(02), 182-193.

[7] Cao Yu, Wang Cheng, Wang Xin et al. Urban Road Short-term Traffic Flow Prediction based on Spatiotemporal Node Selection and Deep Learning. Journal of Computer Applications, 2020, 40(5): 1488-1493.

[8] Wang Xin. Research on Short-term Passenger Flow Prediction of Urban Rail Transit Based on Deep Learning and Multi-feature Fusion. Lanzhou Jiaotong University, 2024.

[9] Feng Biyu. Research on Short-term Passenger Flow Prediction of Urban Rail Transit Based on CNN-LSTM Combined Model[D]. East China Jiaotong University, 2021.

[10] Shao Hongxin, Soong Boon-Hee. Traffic Flow Prediction with Long Short-Term Memory Networks (LSTMs). Proceedings of 2016 IEEE Region 10 Conference Singapore: IEEE, 2016: 2986-2989.

[11] Doğan Erdem. Robust-LSTM: A Novel Approach to Short-traffic Flow Prediction based on Signal Decomposition. Soft Computing, 2022.26: 5227-5239.

[12] Zheng Haifeng, Lin Feng, Feng Xinxin et al. A Hybrid Deep Learning Model with Attention-based Conv-LSTM Networks for Short-Term Traffic Flow Prediction. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(11): 6910-6920.

[13] Shi Ruize, Du Lijing. Multi-Section Traffic Flow Prediction based on MLR-LSTM Neural Network. Sensors, 2022, 22(19): 7517.

[14] Kong Siqin. Short-Term Traffic Flow Prediction based on VMD-HSSA-BP Neural Network Model. Electronic Design Engineering, 2024, 32(10): 1-7.

[15] Liu Weiyuan et al. Research on Holiday Passenger Flow Prediction in Suzhou Rail Transit. Urban Rapid Rail Transit, 2021, 34(05): 66-73.