Using Machine Learning to Identify Clustering Patterns of Traffic Accidents

• Autorzy: Passarella Rossi , Utami Putri Shobiroh , Ubaya Huda , Widyastuti Rifka

Identyfikatory

DOI

10.5604/01.3001.0054.9635

• Języki publikacji: EN

Abstrakty

EN

Between 20 and 50 million people suffer non-fatal injuries from traffic accidents each year, while more than one million of these result in death. Road traffic accidents pose a significant threat not only to the economy but also to public health. The figures obtained are objective statistics and not based on personal opinions. This study aims to develop a clustering model using a machine learning approach based on the characteristics of the occurrence and number of victims of traffic accidents in Palembang City, South Sumatra Province, Indonesia. This research will analyze patterns that observe different relationships among crashes by using various clustering techniques such as K-means clustering, Gaussian mixture model (GMM), density-based (DBSCAN), hierarchical clustering, spectral clustering, and OPTICS (sorted points to identify clustering structure). Through the machine learning approach, this research attempts to bridge the knowledge gap between the factors involved in traffic accidents and the development of more effective prevention strategies. In addition, this research also provides further insight into the potential use of machine learning algorithms in analyzing and processing traffic accident data. The results show that an algorithm called spectral clustering outperforms the other algorithms with a low Davies-Bouldin score (0.3221), a high Calinski-Harabasz score (14789.9374), and a silhouette coefficient (0.7695). Spectral clustering was the best algorithm out of the six algorithms evaluated for this paper. By favoring spectral clustering as the best algorithm, this research provides a new outlook on the application of technology in the field of highway safety. The results also show that there are specific patterns of traffic accidents in Palembang City that can be identified through data analysis using clustering techniques. The implications of this research provide an important contribution to the development of strategies for traffic accident prevention and road safety improvement in the region. It is expected that the findings can assist the government and related agencies in taking more effective measures to reduce the number of traffic accidents and protect the public from the associated risks.

Słowa kluczowe

EN

traffic accidents; machine learning; road safety

PL

wypadki drogowe; uczenie maszynowe; bezpieczeństwo na drodze

• Wydawca: Oficyna Wydawnicza Politechniki Warszawskiej
• Czasopismo: Prace Naukowe Politechniki Warszawskiej. Transport
• Rocznik: 2024
• Tom: z. 139
• Strony: 19--32
• Opis fizyczny: Bibliogr. 14 poz., tab., wykr.

Twórcy

autor

Passarella Rossi

• Department of Computer System, University of Sriwijaya, Palembang, Indonesia

• https://orcid.org/0000-0002-7243-0451

autor

Utami Putri Shobiroh

• Department of Computer System, University of Sriwijaya, Palembang, Indonesia

• https://orcid.org/0009-0007-1567-068X

autor

Ubaya Huda

• Department of Computer System, University of Sriwijaya, Palembang, Indonesia

• https://orcid.org/0000-0002-4240-149X

autor

Widyastuti Rifka

• Department of Technology Information, Cyber University, Jakarta Indonesia

• https://orcid.org/0009-0009-7717-9823

Bibliografia

• 1. Belyadi, H., Haghighat, A. (2021). Machine Learning Guide for Oil and Gas Using Python, Chapter 4 - Unsupervised machine learning: clustering algorithms, Editor(s): Hoss Belyadi, Alireza Haghighat. Gulf Professional Publishing, Pages 125-168. ISBN 9780128219294. doi:10.1016/B978-0-12-821929-4.00002-0.
• 2. Buchari, E. (2015). Transportation Demand Management: A Park and Ride System to Reduce Congestion in Palembang City Indonesia, Procedia Engineering, Vol 125, pp 512-518, doi: 10.1016/j.proeng.2015.11.047.
• 3. Ekemeyong Awong, L.E., Zielinska, T. (2023). Comparative Analysis of the Clustering Quality in Self-Organizing Maps for Human Posture Classification, Sensors, vol. 23, no. 18, doi: 10.3390/s23187925.
• 4. Fahs, B., Rafacz, T., Patel, S.J., Lumetta, S.S. (2005). Continuous optimization, Proc. - Int. Symp. Comput. Archit., pp. 86–97, doi: 10.1109/isca.2005.19.
• 5. Gutierrez-Osorio, C., Pedraza, C. (2020). Modern data sources and techniques for analysis and forecast of road accidents: A review, J. Traffic Transp. Eng. (English Ed., vol. 7, no. 4, pp. 432–446, doi: 10.1016/j.jtte.2020.05.002.
• 6. Leonardi, S., Distefano, N., Pulvirenti, G. (2020). Identification of road safety measures for elderly pedestrians based on k-means clustering and hierarchical cluster analysis," Arch. Transp., vol. 56, no. 4, pp. 107–118, doi: 10.5604/01.3001.0014.5630.
• 7. Montazeri, A. (2004). Road-traffic-related mortality in Iran: A descriptive study, Public Health, vol. 118, no. 2, pp. 110–113, doi: 10.1016/S0033-3506(03)00173-2.
• 8. Rolison, J.J., Regev, S., Moutari, S., Feeney, A. (2018). What are the factors that contribute to road accidents? An assessment of law enforcement views, ordinary drivers' opinions, and road accident records, Accid. Anal. Prev., vol. 115, no. August 2017, pp. 11–24, 2018, doi: 10.1016/j.aap.2018.02.025.
• 9. Salloum, S., Alhumaid, K., Salloum, A., Shaalan. K. (2024). K-means Clustering of Tweet Emotions: A 2D PCA Visualization Approach. Procedia Comput. Sci. Vol 244, pp 30-36, doi: 10.1016/j.procs.2024.10.175.
• 10. Shirmohammadi, H., Hadadi, F., Saeedian, M. (2019). Clustering Analysis of Drivers Based on Behavioral Characteristics Regarding Road Safety, Int. J. Civ. Eng., vol. 17, no. 8, pp. 1327–1340, doi: 10.1007/s40999-018-00390-2.
• 11. Yang, D., Wang, J., He, J., Zhao, C. (2024). A clustering mining method for sports behavior characteristics of athletes based on the ant colony optimization". Heliyon. Vol 10, Issue 12: e33297, 2024. doi :10.1016/j.heliyon.2024.e33297.
• 12. Yassin, S.S., Pooja, (2020). Road accident prediction and model interpretation using a hybrid K-means and random forest algorithm approach, SN Appl. Sci., vol. 2, no. 9, doi: 10.1007/s42452-020-3125-1.
• 13. Yuan, R., Abdel-Aty, M., Xiang. Q.(2024). A study on diversion behavior in weaving segments: Individualized traffic conflict prediction and causal mechanism analysis. Accid. Anal. Prev. Vol 205:107681, doi: 10.1016/j.aap.2024.107681.
• 14. Zhou, H.B., Gao, J.T. (2024). Automatic method for determining cluster number based on silhouette coefficient, Adv. Mater. Res., vol. 951, pp. 227–230, doi: 10.4028/www.scientific.net/AMR.951.227.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).