A Method to Match Users Across Transportation Modes Based on Repeated Transfer Behaviors
REGISTRATION: https://bit.ly/3uyVv5d (Deadline: 07 June 2022, 12:00)
This seminar will be via ZOOM only.
Dr Hongtai Yang Associate Professor, Southwest Jiaotong University
DATE & TIME:
June 08 (Wednesday) 13:00-14:00 HKT
For the purpose of privacy protection, trip trajectory data containing rich personal travel information needs to be anonymized before being shared and analyzed. This practice makes it difficult for researchers to identify the same individuals in different datasets, which hinders the construction of complete trip chains and the exploration of important travel patterns. Therefore, this paper develops a method to match users of different transportation modes based on the following idea. If a user makes a transfer, the ending point of the previous trip will be around the same time (a little earlier) and same location as the starting point of the next trip. When this pattern happens for two user accounts repeatedly, we can infer that the two users are actually the same person. This method is demonstrated using the metro and bus data of Chengdu city from January to March 2021. When setting the minimum transfer times as three, the precision and recall of user matching is 56.50% and 26.45% for the one-month data, 61.76% and 38.60% for the two-month data, and 65.36% and 50.49% for the three-month data. Sensitivity analysis is performed to study the effect of parameters on the user matching result.
ABOUT THE SPEAKER:
Hongtai Yang is an associate professor of Southwest Jiaotong University, located in Chengdu, China. He obtained his PhD in civil engineering with emphasis on transportation engineering and MS in statistics from The University of Tennessee at Knoxville. His research interests include urban big data analytics and multimodal transportation demand management. He has served as PI for research projects from various funding sources such as National Science Foundation of China and China Postdoctoral Science Foundation. He serves as an academic editor of Journal of Advanced Transportation and an editorial board member of China Safety Science Journal. He has published more than 40 papers on journals such as Transportation Research Part A/D/F and IEEE Transaction on Intelligent Transportation Systems, and five of them have been selected as ESI highly cited papers.
Institute of Transport Studies, The University of Hong Kong