USING MACHINE LEARNING METHODS TO OPTIMIZE URBAN TRAFFIC MOVEMENT IN BISHKEK

Authors

A.K. Kadyrzhanov Kyrgyz-German University of Applied Informatics
R.A. Koso-Ogly Kyrgyz-German University of Applied Informatics

Keywords:

machine learning, traffic flows, traffic optimization, travel time prediction, Bishkek, OpenRouteService, adaptive traffic signals

Abstract

This article examines the application of machine learning algorithms for the analysis and optimization of traffic flows in the city of Bishkek. The study is aimed at identifying traffic movement patterns and developing a travel time prediction model based on data from the OpenRouteService platform. The proposed approach makes it possible to generate recommendations for adapting traffic signal cycles depending on traffic intensity. The implementation of the proposed model may contribute to reducing traffic congestion and improving the efficiency of the urban transportation system.

References

1. Казанцев М. Р., Верзунов С. Н. Методологические подходы к оценке влияния моторного транспорта на состояние атмосферного воздуха в городе Бишкек // Проблемы автоматики и управления. — 2025. — № 2. — С. 74–87.

2. Breiman L. Random Forests // Machine Learning. — 2001. — Vol. 45, No. 1. — P. 5–32. — DOI: 10.1023/A:1010933404324.

3. Nagy A. M., Simon G., Szabó R., Varga P. Survey on traffic prediction in smart cities // Transportation Research Procedia. — 2018. — Vol. 27. — P. 475–482.

4. Abduljabbar R., Dia H., Liyanage S., Bagloee S. A. Machine learning traffic flow prediction models for smart cities // Buildings. — 2020. — Vol. 10, No. 7. — Art. 155. — DOI: 10.3390/buildings10070155.

5. Liu Z., Li Z., Li M., Xing X., Lu Y. Urban traffic prediction from mobility data using deep learning // IEEE Transactions on Intelligent Transportation Systems. — 2018. — Vol. 19, No. 7. — P. 2140–2151.

6. Chen Y., Lv Y., Wang F.-Y., Li X., Wang S. When traffic flow prediction and wireless big data analytics meet // IEEE Network. — 2018. — Vol. 32, No. 4. — P. 58–64. — DOI: 10.1109/MNET.2018.1700209.

7. Zhao W., Zhang S., Zhou B., Wang B. STCGAT: A spatio-temporal causal graph attention network for traffic flow prediction // arXiv. — 2022. — arXiv:2203.10749.

8. Li F., Zhang Y., Zhang Y., Wang Y. Dynamic graph convolutional recurrent network for traffic prediction: Benchmark and solution // arXiv. — 2021. — arXiv:2104.14917.