Data-driven insights: Unravelling traffic dynamics with k-means clustering and vehicle type differentiation

Anwar Mehmood Sohail; Khurram Shehzad  Khattak; Zawar Hussain Khan

doi:10.59400/issc1737

Anwar Mehmood Sohail Department of Computer System Engineering, University of Engineering and Technology, Peshawar 25120, Pakistan; Department of Information Systems, Faculty of Computer Science and Information Technology, University of Malaya, Kuala Lumpur 50603, Malaysia
Khurram Shehzad Khattak Department of Computer System Engineering, University of Engineering and Technology, Peshawar 25120, Pakistan
Zawar Hussain Khan Department of Electrical and Computer Engineering, University of Victoria, Victoria V8W 2Y2, Canada

Article ID: 1737

67 Views, 40 PDF Downloads

DOI: https://doi.org/10.59400/issc1737

Keywords: traffic flow analysis; k-means clustering; multi linear regression; machine learning; transportation

Abstract

Urban traffic poses persistent challenges, necessitating innovative approaches for effective traffic flow analysis and management. This research adopts a data-driven methodology, employing different algorithms such as K-Means clustering, multiple linear regression to analyse real-world traffic flow. The study utilizes road traffic data collected over seven days, spanning seven hours each day, comprising traffic count, vehicle speed, and categorization by vehicle type. Through rigorous data preprocessing and K-Means clustering, the research identifies distinct traffic clusters, revealing patterns beyond average counts and speeds. Notably, the differentiation of vehicle types within clusters provides nuanced insights into transport mode interactions. The findings contribute to the traffic flow analysis field and offer practical implications for informed urban traffic management strategies. Understanding traffic dynamics aids in developing effective congestion mitigation measures. The study concludes by highlighting potential areas for future research and improvements in optimizing traffic dynamics, emphasizing the importance of data-driven approaches in addressing urban traffic challenges.

References

[1]Khan, Khattak, Khan et al. Edge computing for effective and efficient traffic characterization. Sensors. 2023; 23(23): 9385.

[2]Saha, Tariq, Hadi et al. Pattern recognition using clustering analysis to support transportation system management, operations, and modeling. Journal of Advanced Transportation. 2019; 2019(1): 1628417.

[3]Li, Zhou, Gu et al. A novel K-means clustering method for locating urban hotspots based on hybrid heuristic initialization. Applied Sciences. 2022; 12(16): 8047.

[4]Khattak, Minallah, Khan et al. Sensing technologies for traffic flow characterization: From heterogeneous traffic perspective. Journal of Applied Engineering Science. 2022; 20(1): 29–40.

[5]Song R, Yang H. Clustering and understanding traffic flow patterns of large scale urban roads. In: Proceedings of the 2021 International Conference on Control, Automation and Information Sciences (ICCAIS); 2021.

[6]Li X, Gui J, Liu J. Data-driven traffic congestion patterns analysis: A case of Beijing. Journal of Ambient Intelligence and Humanized Computing. 2023; 14(7): 9035–9048.

[7]Muntean MV. Identifying critical traffic flow time slots using k-means and decision trees. In: Proceedings of the 2020 IEEE 10th International Conference on Intelligent Systems (IS); 2020.

[8]Chu HC, Wang CK. Using K-means algorithm for the road junction time period analysis. In: Proceedings of the 2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST). 2017.

[9]Daniswara FA, Gunawan P. Simulation of transport problem with clustering velocity-density function. In: Proceedings of the 2020 8th International Conference on Information and Communication Technology (ICoICT). 2020.

[10]Esfahani RK, Shahbazi F, Akbarzadeh M. Three-phase classification of an uninterrupted traffic flow: a k-means clustering study. Transportmetrica B: transport dynamics; 2018.

[11]Gao, Chen, Chen Z et al. Traffic state recognition of urban expressway based on K-means clustering and AdaBoost-DS. In: Proceedings of the Sixth International Conference on Traffic Engineering and Transportation System (ICTETS 2022). 2023.

[12]Zeb, Khattak, Rehmat et al. HetroTraffSim: A macroscopic heterogeneous traffic flow simulator for road bottlenecks. Future Transportation. 2023; 3(1): 368–383.

[13]Khattak KS, Khan ZH. Evaluation and Challenges of IoT Simulators for Intelligent Transportation System Applications. Science. Engineering and Technology. 2024; 4(1): 94–111.