Mapping grid based online taxi anomalous trajectory detection

Abstract

This paper proposes an online taxi driving anomalous trajectory detection framework for maintaining the city public transport civilisation. The framework consists of two parts: an offline detector building and an online trajectory detection. The former employs a popular route concept to process massive trajectory data and adapts the mapping grid-based anomaly detection method by taking into account spatial and temporal characteristics of the trajectory dataset. The latter maps ongoing trajectory points and detects whether the ongoing driving route is anomalous or reliable. The proposed trajectory anomaly detection method is faster than the existing methods as it involves only simple activities of trajectory point mapping and retrieval procedure, without requiring extra distance or density calculation. In addition, the proposed method has detection accuracy comparable to that of the existing high-performance methods. The application and efficiency of the proposed method are demonstrated using extensive experiments on real datasets.

KEYWORDS:

• Taxi trajectory anomaly detection
• spatial and temporal characteristic
• mapping grid
• detouring detection

Acknowledgements

Part of this work was presented at the International Conference on Life System Modeling and Simulation jointly with the International Conference on Intelligent Computing for Sustainable Energy and Environment in 2017 (Ding, 2017). We thank the conference attendees for their feedback that helped improve the quality of this paper.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work is supported by the Open Project of Top Key Discipline of Computer Software and Theory in Zhejiang Provincial [grant numbers ZC323014100, ZC323016038], The Doctoral Research Start-up Fund of Zhejiang Normal University [grant number ZC304016020], Project of Department of Education of Zhejiang Province [grant number KYZ04Y19267], partly by the National Science Foundation of China [grant numbers 61572442, 71631001, 11531011].

Notes on contributors

Zhiguo Ding

Zhiguo Ding received the B.E. degree in computer science from Shaanxi Normal University, Xi'an, China, in 2001, the M.S. degree in computer software and theory, and the Ph.D. degree in control theory and engineering from Shanghai University, Shanghai, China, in 2007 and 2015, respectively. He is currently a lecturer with the College of Mathematics and Computer Science, Zhejiang Normal University, Jinhua, China. His current research interests include system anomaly prediction and detection, software reliability analysis and quality assurance.

Liudong Xing

Liudong Xing received the B.E. degree in computer science from Zhengzhou University, China in 1996, and the M.S. and Ph.D. degrees in electrical engineering from the University of Virginia, USA, in 2000 and 2002, respectively. She is a professor with the Department of Electrical and Computer Engineering, University of Massachusetts (UMass) Dartmouth, USA. Her current research interests include reliability and resilience modeling, analysis and optimization of complex systems and networks.

Yuchang Mo

Yuchang Mo received the B.E. MS, and PhD degrees in computer science from Harbin Institute of Technology, Harbin, China, in 2002, 2004, and 2008, respectively. He is a distinguished professor with the School of Mathematical Sciences, Huaqiao University, Quanzhou, China. His current research interests includereliability modeling, analysis and optimization of complex systems and networks.