A hybrid temporal association rules mining method for traffic congestion prediction. (April 2019)

• Record Type: Journal Article
• Authors: Wen, Feng; Zhang, Guo; Sun, Lingfeng; Wang, Xingqiao; Xu, Xiaowei
• Is Part Of: Computers & industrial engineering. Volume 130(2019)
• Page Start: 779
• Page End: 787
• Publication Date: 2019-04
• Subjects: Traffic congestion prediction -- DBSCAN -- Temporal association rule -- Genetic algorithm; 00-01 -- 99-00; Engineering -- Data processing -- Periodicals; Industrial engineering -- Periodicals; 620.00285
• DOI: 10.1016/j.cie.2019.03.020
• Languages: English
• ISSNs: 0360-8352

Abstract

Abstract: Traffic congestion is a significant problem in the research field of Intelligent Transportation Systems. In this paper, a Hybrid Temporal Association Rules Mining method is proposed to predict traffic congestion. In the proposed method, DBSCAN algorithm is applied to find traffic environments, which generate eligible rules for predicting traffic congestion in the road network. Genetic Algorithm based Temporal Association Rules Mining algorithm is designed to extract temporal association rules in traffic environments. The rules are analysed by a classification mechanism so that a classifier can be built to predict the traffic congestion level. Simulation experiment of the extracted rules and classification prediction are studied in various sizes of road networks. Experimental results demonstrate that the proposed method can predict the traffic congestion with high accuracy.