Security and Privacy in New Computing Environments. Second EAI International Conference, SPNCE 2019, Tianjin, China, April 13–14, 2019, Proceedings

Research Article

Travel Modes Recognition Method Based on Mobile Phone Signaling Data

Download
104 downloads
  • @INPROCEEDINGS{10.1007/978-3-030-21373-2_57,
        author={Ying Xia and Jie Tang and Xu Zhang and Hae-young Bae},
        title={Travel Modes Recognition Method Based on Mobile Phone Signaling Data},
        proceedings={Security and Privacy in New Computing Environments. Second EAI International Conference, SPNCE 2019, Tianjin, China, April 13--14, 2019, Proceedings},
        proceedings_a={SPNCE},
        year={2019},
        month={6},
        keywords={Travel mode recognition Mobile phone signaling Clustering analysis Data preprocessing Road network constraints},
        doi={10.1007/978-3-030-21373-2_57}
    }
    
  • Ying Xia
    Jie Tang
    Xu Zhang
    Hae-young Bae
    Year: 2019
    Travel Modes Recognition Method Based on Mobile Phone Signaling Data
    SPNCE
    Springer
    DOI: 10.1007/978-3-030-21373-2_57
Ying Xia1,*, Jie Tang1,*, Xu Zhang1,*, Hae-young Bae2,*
  • 1: Chongqing University of Posts and Telecommunications
  • 2: Inha University
*Contact email: xiaying@cqupt.edu.cn, S160201056@stu.cqupt.edu.cn, zhangx@cqupt.edu.cn, hybae@inha.ac.kr

Abstract

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.