Exploring Key Determinants of Traffic Accidents Fatalities in Thailand: A Hybrid Approach Machine Learning and Statistics
- DOI
- 10.2991/978-94-6463-972-8_12How to use a DOI?
- Keywords
- Road Safety; Virtual Geometry Group Model; Fatality
- Abstract
Road traffic incidents are the 8th leading cause of mortality globally, with 90% of fatalities occurring in low- and middle-income countries. Moreover, these severe accidents are often attributed to the negligence or behavior of vulnerable road users. In Thailand, the mortality rate from road traffic accidents stand at 25 per 100,000 individuals, the highest among ASEAN nations. This study aims to investigate the various risk factors contributing to mortality from road traffic accidents, which have been collected since 2011 through the Highway Accident Information Management System (HAIMS), using statistical methodologies such as Cramer’s V, Information Values (IV), which are employed to identify the most significant causes of mortality. In addition, the mortality had been investigated by deep learning model based on convolution and neural networks algorithms before being explored the significant factors influencing fatality from resulting traffic accidents from deep learning model by numerical techniques for quantifier the likelihood of associated with each significant factor. Three primary factors have been identified by Cramer’s V, Information Value, and numerical analysis: using safety equipment of people, type of road user, and lighting conditions. These findings underscore the importance of targeted interventions, including stricter enforcement of safety equipment use, good road or infrastructure design for preventing accidents with different road users, and improving lighting infrastructure in some sections of a road, which could significantly reduce the road traffic mortality rate. While numerous factors contribute to road traffic fatalities in Thailand, these three factors demonstrate the strongest association with fatal outcomes.
- Copyright
- © 2025 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Nanon Sonnatthanon AU - Kasem Choocharukul PY - 2025 DA - 2025/12/29 TI - Exploring Key Determinants of Traffic Accidents Fatalities in Thailand: A Hybrid Approach Machine Learning and Statistics BT - Proceedings of the 14th Asia-Pacific Conference on Transportation and the Environment (APTE 2025) PB - Atlantis Press SP - 116 EP - 126 SN - 2589-4943 UR - https://doi.org/10.2991/978-94-6463-972-8_12 DO - 10.2991/978-94-6463-972-8_12 ID - Sonnatthanon2025 ER -