东南大学学报（英文版）2025，Vol.41Issue(2)：215-225,11.DOI:10.3969/j.issn.1003-7985.2025.02.011
共享单车绕行行为判别及影响因素研究
Research on the discrimination of detour behavior and influencing factors of shared bicycles
摘要
Abstract
To investigate the distribution characteristics and influencing factors of bicycle detour behavior,this study ac-curately identified detour behavior using global positioning system(GPS)track data from shared bicycles.Factors such as travel time,road conditions,public transportation facili-ties,and land use types were considered in constructing a detour behavior influence model based on the CatBoost ma-chine learning algorithm.The interpretability of the ma-chine learning framework was enhanced via Shapley addi-tive explanations(SHAP),enabling an analysis of the im-pact of each factor on detour behavior.The results indicated that the CatBoost model effectively recognized detour be-havior with high accuracy.The frequency of detour behav-ior increased with higher road levels,greater distances to crossing facilities,wider bike lanes,and an increased num-ber of bus stops,subway stations,and leisure and entertain-ment facilities,while it decreased with a higher number of office commuting facilities.In addition,detour behavior was more prevalent on weekends,during off-peak hours,and under conditions involving physical central lane separa-tion and physical bike lane separation.These findings offer a novel approach for identifying bicycle riding behaviors and analyzing their influencing factors,providing effective technical support for non-motorized traffic management and infrastructure optimization.关键词
共享单车/绕行行为/轨迹数据/机器学习/影响因素Key words
shared bicycles/detour behavior/trajectory data/machine learning/influencing factor分类
交通运输引用本文复制引用
边扬,尹璐瑶,赵晓华,韩唐姗,张晓龙..共享单车绕行行为判别及影响因素研究[J].东南大学学报（英文版）,2025,41(2):215-225,11.基金项目
The National Natural Science Foundation of China(No.52072012). （No.52072012）
