An Unlicensed Taxi Identification Model Based on Big Data Analysis
- 24 November 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 17 (6), 1703-1713
- https://doi.org/10.1109/tits.2015.2498180
Abstract
Social networks and mobile networks are exposing human beings to a big data era. With the support of big data analytics, conventional intelligent transportation systems (ITS) are gradually changing into data-driven ITS (D 2 ITS). Along with traffic growth, D 2 ITS need to solve more real-life problems, including the issue of unlicensed taxis and their identification, which potentially disrupts the taxi business sector and endangers society safety. As a remedy to this issue, a smart model is proposed in this paper to identify unlicensed taxis. The proposed model consists of two submodel components, namely, candidate selection model and candidate refined model. The former is used to screen out a coarse-grained suspected unlicensed taxi candidate list. The list is taken as an input for the candidate refined model, which is based on machine learning to get a fine-grained list of suspected unlicensed taxis. The proposed model is evaluated using real-life data, and the obtained results are encouraging, demonstrating its efficiency and accuracy in identifying unlicensed taxis, helping governments to better regulate the traffic operation and reduce associated costs.Keywords
Funding Information
- National Natural Science Foundation of China (61100066, 61472283, 61572220, 61262013)
- Fok Ying-Tong Education Foundation of China (142006)
- Fundamental Research Funds for the Central Universities (2100219043, 1600219246, x2jq-D2154120)
- Scientific Research Foundation for the Returned Overseas Chinese Scholars, state Education Ministry
This publication has 33 references indexed in Scilit:
- Supporting Highly Mobile Users in Cost-Effective Decentralized Mobile Operator NetworksIEEE Transactions on Vehicular Technology, 2014
- Transit smart card data mining for passenger origin information extractionJournal of Zhejiang University SCIENCE C, 2012
- Analysis of Pedestrian Travel with Static Bluetooth SensorsTransportation Research Record: Journal of the Transportation Research Board, 2012
- Processing Commercial Global Positioning System Data to Develop a Web-Based Truck Performance Measures ProgramTransportation Research Record: Journal of the Transportation Research Board, 2011
- DRIVE NetTransportation Research Record: Journal of the Transportation Research Board, 2011
- Model‐Free Video Detection and Tracking of Pedestrians and BicyclistsComputer-Aided Civil and Infrastructure Engineering, 2009
- Video-Based Vehicle Detection and Tracking Using Spatiotemporal MapsTransportation Research Record: Journal of the Transportation Research Board, 2009
- MapReduceCommunications of the ACM, 2008
- Video-Based Monitoring of Pedestrian Movements at Signalized IntersectionsTransportation Research Record: Journal of the Transportation Research Board, 2008
- Can using global positioning system (GPS) improve trip reporting?Transportation Research Part C: Emerging Technologies, 1999