A Clustering Approach to Identify High-Risk Taxi Drivers Based on Self-Reported Driving Behavior

Abstract

This study aimed to evaluate the driving behavior of taxi drivers in Isfahan, Iran, and assess the probability of a driver being among the high-risk taxi drivers. To identify risky driving behaviors among taxi drivers, the Driver Behavior Questionnaire (DBQ) was used. By collecting data from 548 taxi drivers, exploratory factor analysis identified the significant components of DBQ including “Inattention errors,” “Inexperience errors,” “Lapses,” “Ordinary violations,” and “Aggressive violations.” K-means clustering was conducted to cluster taxi drivers into three risk groups of low-risk, medium-risk, and high-risk taxi drivers based on their self-reported annual traffic crashes and fines. In addition, logistic regressions identified the extent to which drivers’ crashes and traffic fines are related to their driving behavior, and therefore, what aberrant driving behaviors are more important in explaining the presence of taxi drivers in the high-risk cluster. The results revealed that the majority of participants (66.78%) were low-risk taxi drivers. Aggressive violations and ordinary violations were significant predictors of taxi drivers being in the high-risk group, while inattention errors and aggressive violations were significant predictors of being in the medium/high-risk cluster. The findings from this study are valuable resources for developing safety measures and training for new drivers in the taxi industry.

Model for Predicting Lateral Shifts and Driving Style of Motorized Two-Wheelers

“…Characterizing the driving style of MTW riders during the lateral shift process can help avoid unsafe driving behavior, reduce the frequency of possible traffic conflicts, enhance the safety of riders as well as interacting vehicles, and improve traffic in general ( 24 – 26 ). As labeling driving style becomes challenging because of its latent nature, most of the existing studies have performed cluster-based unsupervised classification methodology to classify it either in a three-class ( 27 – 29 ) or in a multi-class system ( 30 – 34 ). Zhang et al ( 35 ) and Chen and Chen ( 27 ) defined a three-clustered model, naming the driving style groups as prudent, normal, and aggressive drivers.…”

“…While some of the existing studies have applied hierarchical ( 31 , 34 ) and fuzzy-based clustering methods ( 31 ), the K -means clustering approach ( 27 , 31 ) has been widely employed in most of the driving style-related literature. Before clustering, a few studies have also even executed different methods of factor analysis (exploratory factor analysis and confirmatory factor analysis) to reduce the dimension of the influencing features from a higher level to a lower level ( 28 , 32 , 37 ).…”