Travel Modes Recognition Method Based on Mobile Phone Signaling Data

초록

With the acceleration of urbanization and motorization, the characteristics and rules of residents’ travel are constantly changing. Analysis of this information provides reference and guidance for transportation planning, urban management and residents’ travel. With the development of mobile positioning and wireless communications, GPS signals, mobile phone signaling data and other data have established the foundation for obtaining wide-area travel information. This paper proposes a travel mode recognition method based on mobile phone signaling data. In the data preprocessing stage, the method effectively identifies and processes exceptions such as “ping-pong switching” effect and “data drift” effect through time-space threshold filtering, and accurately recognizes key points in the trajectory segmentation stage through feature analyses. In the recognition stage, this method utilizes the road network constraints to improve the calculation of features. The experimental results show that the method can effectively recognize the mode of residents’ travel according to the mobile phone signaling data. © 2019, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

키워드