Ruifeng Wang, Wenyuan Zheng, Miaohua Huang, Guohang Li
{"title":"Driving Behavior Evaluation Based on DBSCAN and Kmeans++ Clustering","authors":"Ruifeng Wang, Wenyuan Zheng, Miaohua Huang, Guohang Li","doi":"10.1109/AEMCSE55572.2022.00046","DOIUrl":null,"url":null,"abstract":"Public transportation plays an important role in residents’ daily travel, and it’s important to improve the comprehensive driving ability of drivers. This paper establishes a scientific and comprehensive evaluation system for bus drivers’ driving behavior. First, based on the big data of the operation of new energy buses, the kinematic segments are divided into consideration of the temperature changes in four seasons and traffic conditions, and the index features under the three dimensions of driving behavior security, energy consumption and passenger comfort are excavated, and then combined with DBCSAN and Kmeans++, the driving behavior of each dimension is clustered and classified, which improves the reliability of the clustering and the rationality of the classification. Finally, based on the weighted scoring method, the classification of the driving behavior is determined by combining the temperature of the four seasons and the proportion of different traffic conditions. The driver’s comprehensive driving behavior scoring model is established to realize the quantitative evaluation of the driver’s driving behavior. The model can reasonably evaluate the driver’s comprehensive driving ability and help the driver to improve their comprehensive driving skills.","PeriodicalId":309096,"journal":{"name":"2022 5th International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE)","volume":"59 4","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 5th International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AEMCSE55572.2022.00046","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Public transportation plays an important role in residents’ daily travel, and it’s important to improve the comprehensive driving ability of drivers. This paper establishes a scientific and comprehensive evaluation system for bus drivers’ driving behavior. First, based on the big data of the operation of new energy buses, the kinematic segments are divided into consideration of the temperature changes in four seasons and traffic conditions, and the index features under the three dimensions of driving behavior security, energy consumption and passenger comfort are excavated, and then combined with DBCSAN and Kmeans++, the driving behavior of each dimension is clustered and classified, which improves the reliability of the clustering and the rationality of the classification. Finally, based on the weighted scoring method, the classification of the driving behavior is determined by combining the temperature of the four seasons and the proportion of different traffic conditions. The driver’s comprehensive driving behavior scoring model is established to realize the quantitative evaluation of the driver’s driving behavior. The model can reasonably evaluate the driver’s comprehensive driving ability and help the driver to improve their comprehensive driving skills.