Document Type : Scientific - Research
Authors
1
Associate Professor, School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran Road Safety Research Center, Iran University of Science and Technology, Tehran, Iran
2
Head of Safety and Traffic, Department of Road Maintenance and Road Transportation Department of Isfahan Province, Isfahan, Iran
3
Ph.D. Candidate, School of Civil Engineering, College of Engineering, University of Tehran, Tehran, Iran Deputy of Transportation, Road Maintenance and Transportation Organization, Isfahan, Iran
4
M.Sc. Student, School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran Road Safety Research Center, Iran University of Science and Technology, Tehran, Iran
Abstract
Discovering patterns among traffic crashes has always been a focus for various researchers. By identifying correlations between these incidents, they aim to propose strategies to prevent crashes. With the increase in crashes and, consequently, the number of injuries and fatalities in recent years, analyzing crashes and uncovering their relationships has become essential. Therefore, in the present study, we delve into the analysis of rural traffic crashes in Isfahan province using correspondence analysis and multiple correspondence analysis, through which hidden patterns among these crashes are identified. Initially, we employ correspondence analysis to explore the human factor in crashes, which plays a role in over 90 percent of crash occurrences. Three meaningful categories are identified, representing a novel aspect of this research. Subsequently, we apply multiple correspondence analysis to analyze the crashes. The results reveal that the crashes in Isfahan province can be broadly categorized into four groups. Notably, the model developed in this study exhibits significantly higher accuracy compared to models used in previous studies. This research introduces the use of correspondence analysis and multiple correspondence analysis models for the first time in crash data analysis, providing a new tool for analysts and researchers.
Keywords
Subjects
