Multidimensional Visualization of Bikeshare Travel Patterns Using a Visual Data Mining Technique: Data Cubes  

作　　者：Xinwei Ma Yanjie Ji Yang Liu Yuchuan Jin Chenyu Yi 

机构地区：[1]School of Transportation,Southeast University,Nanjing 210096,China [2]Jiangsu Key Laboratory of Urban ITS,Nanjing 210096,China [3]Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies,Nanjing 210096,China

出　　处：《Journal of Beijing Institute of Technology》2019年第2期265-277,共13页北京理工大学学报（英文版）

基　　金：Supported by Projects of International Cooperation and Exchange of the National Natural Science Foundation of China(51561135003);Key Project of National Natural Science Foundation of China(51338003);Scientific Research Foundation of Graduated School of Southeast University(YBJJ1842)

摘　　要：In order to explore the travel characteristics and space-time distribution of different groups of bikeshare users,an online analytical processing(OLAP)tool called data cube was used for treating and displaying multi-dimensional data.We extended and modified the traditionally threedimensional data cube into four dimensions,which are space,date,time,and user,each with a user-specified hierarchy,and took transaction numbers and travel time as two quantitative measures.The results suggest that there are two obvious transaction peaks during the morning and afternoon rush hours on weekdays,while the volume at weekends has an approximate even distribution.Bad weather condition significantly restricts the bikeshare usage.Besides,seamless smartcard users generally take a longer trip than exclusive smartcard users;and non-native users ride faster than native users.These findings not only support the applicability and efficiency of data cube in the field of visualizing massive smartcard data,but also raise equity concerns among bikeshare users with different demographic backgrounds.In order to explore the travel characteristics and space-time distribution of different groups of bikeshare users,an online analytical processing( OLAP) tool called data cube was used for treating and displaying multi-dimensional data. We extended and modified the traditionally threedimensional data cube into four dimensions,which are space,date,time,and user,each with a user-specified hierarchy,and took transaction numbers and travel time as two quantitative measures.The results suggest that there are two obvious transaction peaks during the morning and afternoon rush hours on weekdays,while the volume at weekends has an approximate even distribution.Bad weather condition significantly restricts the bikeshare usage. Besides,seamless smartcard users generally take a longer trip than exclusive smartcard users; and non-native users ride faster than native users. These findings not only support the applicability and efficiency of data cube in the field of visualizing massive smartcard data,but also raise equity concerns among bikeshare users with different demographic backgrounds.

关 键 词：bikeshare smartcard data TRAVEL PATTERN MULTIDIMENSIONAL VISUALIZATION 

分 类 号：U12[交通运输工程]