Approach to discovering companion patterns based on traffic data stream. Issue 10 (9th October 2018)

• Record Type: Journal Article
• Authors: Zhu, Meiling; Liu, Chen; Han, Yanbo
• Is Part Of: IET intelligent transport systems. Volume 12:Issue 10(2018)
• Page Start: 1351
• Page End: 1359
• Publication Date: 2018-10-09
• Subjects: traffic engineering computing -- tree data structures -- data mining -- trees (mathematics) -- data structures; companion patterns -- traffic data stream -- object group -- generalised companion pattern -- time segments -- called automatic number plate recognition data -- related approaches -- companion discovery -- frequent sequence mining problem -- data structure -- platoon tree -- discovered platoon companions -- mining platoon companions; Intelligent transportation systems -- Periodicals; Electronics in transportation -- Periodicals; 388.31205
• DOI: 10.1049/iet-its.2018.5166
• Languages: English
• ISSNs: 1751-956X

Abstract

Abstract : A companion of moving objects is an object group that move together in a period of time. Platoon companions are a generalised companion pattern, which describes a group of objects that move together for time segments, each with some minimum consecutive duration of time. This study proposes a method that can instantly discover platoon companions from a special kind of streaming traffic data, called automatic number plate recognition data. Compared to related approaches, the authors transform the companion discovery into a frequent sequence mining problem. The authors propose a data structure, platoon tree (PTree), to record discovered platoon companions. To reduce the cost of tree traversal during mining platoon companions, they utilise the last two together‐moving objects of a group to update PTree. Finally, a lot of experiments have been carried out to show the efficiency and effectiveness of the proposed approach.