inis 20(22): e3

Research Article

Histogram-based Feature Extraction for GPS Trajectory Clustering

Download60 downloads
  • @ARTICLE{10.4108/eai.13-7-2018.162796,
        author={Chi Nguyen and Thao Dinh and Van-Hau Nguyen and Nhat Phuong  Tran and Anh Le},
        title={Histogram-based Feature Extraction for GPS Trajectory Clustering},
        journal={EAI Endorsed Transactions on Industrial Networks and Intelligent Systems},
        volume={7},
        number={22},
        publisher={EAI},
        journal_a={INIS},
        year={2020},
        month={1},
        keywords={trajectory clustering, histogram, data clustering, GPS},
        doi={10.4108/eai.13-7-2018.162796}
    }
    
  • Chi Nguyen
    Thao Dinh
    Van-Hau Nguyen
    Nhat Phuong Tran
    Anh Le
    Year: 2020
    Histogram-based Feature Extraction for GPS Trajectory Clustering
    INIS
    EAI
    DOI: 10.4108/eai.13-7-2018.162796
Chi Nguyen1, Thao Dinh2, Van-Hau Nguyen3, Nhat Phuong Tran4, Anh Le1,*
  • 1: Ho Chi Minh City, University of Transport, Vietnam
  • 2: Department of Information Technology and Resources and Environment Data, Vietnam
  • 3: Hung Yen University of Technology and Education, Vietnam
  • 4: The Institute of Electronics, Communications and Information Technology (ECIT), Queen's University Belfast, UK
*Contact email: anhlvq@gmail.com

Abstract

Clustering trajectories from GPS data is a crucial task for developing applications in intelligent transportation systems. Most existing approaches perform clustering on raw data consisting of series of GPS positions of moving objects over time. Such approaches are not suitable for classifying moving behaviours of vehicles, e.g., how to distinguish between a trajectory of a taxi and a trajectory of a private car. In this paper, we focus on the problem of clustering trajectories of vehicles having the same moving behaviours. Our approach is based on histogram-based feature extraction to model moving behaviours of objects and utilizes traditional clustering algorithms to group trajectories. We perform experiments on real datasets and obtain better results than existing approaches.