{"title":"Prediction of high-risk bus drivers characterized by aggressive driving behavior","authors":"Eunsol Cho, Yunjong Kim, Seolyoung Lee, Cheol Oh","doi":"10.1080/19439962.2023.2253759","DOIUrl":null,"url":null,"abstract":"AbstractIdentification of driving behavior is a fundamental to developing effective treatments to address various traffic-related problems. In particular, the driving behavior of city bus drivers is of great interest because the crash severity can become much higher than any other vehicle types due to the larger number of passengers on board. However, there is a lack of effective policy preparation to prevent crashes because of limitations associated with identifying intrinsic factors underlying the cause of traffic crashes based on driving behavior analysis. This study aims to develop a methodology to predict high-risk bus drivers, which can be a baseline in establishing effective bus safety policies. An in-depth questionnaire survey was conducted to collect wellness data to represent intrinsic characteristics used for inputs of the proposed prediction methodology in addition to the aggressive driving behavior data obtained from in-vehicle data recorders. Bus drivers were classified into two groups, normal drivers and risky drivers, based on aggressive driving behavior. The priority of intrinsic factors was determined by a gradient boosting method and further utilized to derive input features of the proposed method. Deep-learning-based neural network models were evaluated to predict risky bus drivers in this study. A model with variables up to 11th priority as inputs was selected as the best model. A classification accuracy of 85% was achievable with the proposed model. The outcome of this study would be valuable in supporting policymaking activities to prevent aggressive driving behavior.Keywords: aggressive driving behaviorartificial neural networkbus driver wellnessgradient boosting methodtraffic safety Disclosure statementNo potential conflict of interest was reported by the authors.Additional informationFundingThis research was supported by a grant from Transportation and Logistics Research Program funded by Ministry of Land, Infrastructure and Transport of the Korean government (21TLRP-B148683-04).","PeriodicalId":46672,"journal":{"name":"Journal of Transportation Safety & Security","volume":"4 1","pages":"0"},"PeriodicalIF":2.4000,"publicationDate":"2023-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Transportation Safety & Security","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/19439962.2023.2253759","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"TRANSPORTATION","Score":null,"Total":0}
引用次数: 0
Abstract
AbstractIdentification of driving behavior is a fundamental to developing effective treatments to address various traffic-related problems. In particular, the driving behavior of city bus drivers is of great interest because the crash severity can become much higher than any other vehicle types due to the larger number of passengers on board. However, there is a lack of effective policy preparation to prevent crashes because of limitations associated with identifying intrinsic factors underlying the cause of traffic crashes based on driving behavior analysis. This study aims to develop a methodology to predict high-risk bus drivers, which can be a baseline in establishing effective bus safety policies. An in-depth questionnaire survey was conducted to collect wellness data to represent intrinsic characteristics used for inputs of the proposed prediction methodology in addition to the aggressive driving behavior data obtained from in-vehicle data recorders. Bus drivers were classified into two groups, normal drivers and risky drivers, based on aggressive driving behavior. The priority of intrinsic factors was determined by a gradient boosting method and further utilized to derive input features of the proposed method. Deep-learning-based neural network models were evaluated to predict risky bus drivers in this study. A model with variables up to 11th priority as inputs was selected as the best model. A classification accuracy of 85% was achievable with the proposed model. The outcome of this study would be valuable in supporting policymaking activities to prevent aggressive driving behavior.Keywords: aggressive driving behaviorartificial neural networkbus driver wellnessgradient boosting methodtraffic safety Disclosure statementNo potential conflict of interest was reported by the authors.Additional informationFundingThis research was supported by a grant from Transportation and Logistics Research Program funded by Ministry of Land, Infrastructure and Transport of the Korean government (21TLRP-B148683-04).