Association Rule Mining of Road Traffic Accidents in Thailand
Received: 25 June 2025 | Revised: 24 August 2025 and 3 September 2025 | Accepted: 7 September 2025 | Online: 8 October 2025
Corresponding author: Sutisa Songleknok
Abstract
Road traffic accidents have a substantial impact on Thailand's human capital, affecting both public health and economic productivity. Association rule mining can assist relevant agencies in identifying patterns of accident occurrences based on severity levels, thereby informing policy development and preventive measures. This study aims to analyze the support and confidence values consistent with real-world accident data and uncover association rules related to accident severity levels. Three provinces with the highest accident rates, representing diverse geographical contexts, were examined. Data were sourced from the Ministry of Transport's Accident Management System (TRAMS) between 2019 and 2024. The proposed system comprises four modules: dataset, data preprocessing, data imbalance handling, and association rule mining. The findings indicated that the optimal support and confidence values are 0.01 and 0.4, respectively. The association rules for the three provinces, categorized by severity levels—fatalities, serious injuries, and minor injuries—revealed distinct patterns for the first two severity levels, while similar patterns were observed for minor injuries in all three provinces. The results of this study are valuable for traffic and road transportation agencies in designing policies and guidelines to prevent or reduce accidents in alignment with their root causes.
Keywords:
road traffic accidents, association rule mining, Apriori algorithm, accident patternsDownloads
References
M. D. Belete, G. K. Alitasb, S. Nibretu, and M. E. Dessie, "Road traffic accident determinant factor identification in case of East Gojjam, Ethiopia using wrapper feature selection algorithm," African Transport Studies, vol. 3, 2025, Art. no. 100018. DOI: https://doi.org/10.1016/j.aftran.2024.100018
Q. Cai, "Cause Analysis of Traffic Accidents on Urban Roads Based on an Improved Association Rule Mining Algorithm," IEEE Access, vol. 8, pp. 75607–75615, 2020. DOI: https://doi.org/10.1109/ACCESS.2020.2988288
"Global status report on road safety 2023," World Health Organization. https://www.who.int/publications/i/item/9789240086517.
"Report on Road Accident Situation Analysis on the Ministry of Transport’s Road Network," Office of Transport and Traffic Policy and Planning, Bureau of Safety Planning, Ministry of Transport, Bangkok, Thailand, 2021.
Y. Alassaf and Y. Said, "DPPNet: A Deformable-Perspective-Perception network for Safety Helmet Violation Detection," Engineering, Technology & Applied Science Research, vol. 14, no. 1, pp. 12659–12669, Feb. 2024. DOI: https://doi.org/10.48084/etasr.6633
A. S. Alkarim, A. S. Al-Malaise Al-Ghamdi, and M. Ragab, "Ensemble Learning-based Algorithms for Traffic Flow Prediction in Smart Traffic Systems," Engineering, Technology & Applied Science Research, vol. 14, no. 2, pp. 13090–13094, Apr. 2024. DOI: https://doi.org/10.48084/etasr.6767
I. C. Obasi and C. Benson, "Evaluating the effectiveness of machine learning techniques in forecasting the severity of traffic accidents," Heliyon, vol. 9, no. 8, Aug. 2023, Art. no. e18812. DOI: https://doi.org/10.1016/j.heliyon.2023.e18812
Shweta, J. Yadav, K. Batra, and A. K. Goel, "A Framework for Analyzing Road Accidents Using Machine Learning Paradigms," Journal of Physics: Conference Series, vol. 1950, no. 1, Dec. 2021, Art. no. 012072. DOI: https://doi.org/10.1088/1742-6596/1950/1/012072
Y. Pranata, T. B. Kurniawan, E. S. Negara, and A. H. Mirza, "Analysis of Traffic Accident Patterns Using Association Rule Mining," Journal of Data Sciences, vol. 2024, Dec. 2024, https://doi.org/10.61453/jods.v2024no63. DOI: https://doi.org/10.61453/jods.v2024no63
I. Mohamad, R. Kasemsri, V. Ratanavaraha, and S. Jomnonkwao, "Application of the Apriori Algorithm for Traffic Crash Analysis in Thailand," Safety, vol. 9, no. 3, Aug. 2023, Art. no. 58. DOI: https://doi.org/10.3390/safety9030058
B. Or, "Improving Requirements Classification with SMOTE-Tomek Preprocessing." arXiv, 2025.
M. H. Kotb and R. Ming, "Comparing SMOTE Family Techniques in Predicting Insurance Premium Defaulting using Machine Learning Models," International Journal of Advanced Computer Science and Applications, vol. 12, no. 9, 2021. DOI: https://doi.org/10.14569/IJACSA.2021.0120970
"Road accident data on the road network of the Ministry of Transport - Dataset – MOT data catalog." [Online]. Available: https://datagov.mot.go.th/dataset/roadaccident.
A. Elsobky, A. Keshk, and M. Malhat, "A Comparative Study for Different Resampling Techniques for Imbalanced datasets," International Journal of Computers and Information, vol. 10, no. 3, pp. 147–156, Nov. 2023. DOI: https://doi.org/10.21608/ijci.2023.236287.1136
T. Tanantong and P. Loetwiphut, "Association rule mining framework for financial credit-risk analysis in peer-to-peer lending platforms," Science, Engineering and Health Studies, Dec. 2023, Art. no. 23020006. DOI: https://doi.org/10.69598/sehs.17.23020006
G. Lemaitre, F. Nogueira, and C. K. Aridas, "Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning." arXiv, 2016.
E. Hikmawati, N. U. Maulidevi, and K. Surendro, "Minimum threshold determination method based on dataset characteristics in association rule mining," Journal of Big Data, vol. 8, no. 1, Dec. 2021, Art. no. 146. DOI: https://doi.org/10.1186/s40537-021-00538-3
M. Nasr, M. Hamdy, D. Hegazy, and K. Bahnasy, "An efficient algorithm for unique class association rule mining," Expert Systems with Applications, vol. 164, Feb. 2021, Art. no. 113978. DOI: https://doi.org/10.1016/j.eswa.2020.113978
J. Zhang, T. Feng, H. Timmermans, and Z. Lin, "Improved imputation of rule sets in class association rule modeling: application to transportation mode choice," Transportation, vol. 50, no. 1, pp. 63–106, Feb. 2023. DOI: https://doi.org/10.1007/s11116-021-10238-9
S. Katragadda et al., "Association mining based approach to analyze COVID-19 response and case growth in the United States," Scientific Reports, vol. 11, no. 1, Sep. 2021, Art. no. 18635. DOI: https://doi.org/10.1038/s41598-021-96912-5
R. Abdulla, B. Qader, and K. Sdiq, "Traffic Accident Traits and Driver Characteristics Implication on Road Accidents using Descriptive Analysis: A Cross Sectional Study in Sulaymaniyah, Iraq," Engineering, Technology & Applied Science Research, vol. 13, no. 2, pp. 10372–10376, Apr. 2023. DOI: https://doi.org/10.48084/etasr.5669
I. Mohamad, S. Jomnonkwao, and V. Ratanavaraha, "Using a decision tree to compare rural versus highway motorcycle fatalities in Thailand," Case Studies on Transport Policy, vol. 10, no. 4, pp. 2165–2174, Dec. 2022. DOI: https://doi.org/10.1016/j.cstp.2022.09.016
S. Kumar and D. Toshniwal, "A data mining framework to analyze road accident data," Journal of Big Data, vol. 2, no. 1, Dec. 2015, Art. no. 26. DOI: https://doi.org/10.1186/s40537-015-0035-y
P. Iamtrakul and S. Chayphong, "GIS-based analysis of spatio-temporal clustering of road traffic accidents in Bangkok Metropolitan Region (BMR), Thailand from 2012 to 2021," Transportation Research Interdisciplinary Perspectives, vol. 31, May 2025, Art. no. 101489. DOI: https://doi.org/10.1016/j.trip.2025.101489
A. C. Amil, "Leadership decision-making in Vuca Bureaucracy: Global Turbulence, influence, challenges, and strategies," International Journal of Multidisciplinary Research & Reviews, vol. 3, no. 3, pp. 109–127, Jul. 2024. DOI: https://doi.org/10.56815/IJMRR.V3I3.2024/109-127
Downloads
How to Cite
License
Copyright (c) 2025 Suthasinee Kuptabut, Sutisa Songleknok
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
