An Efficient MapReduce-Based Parallel Clustering Algorithm for Distributed Traffic Subarea Division

Abstract

Traffic subarea division is vital for traffic system management and traffic network analysis in intelligent transportation systems (ITSs). Since existing methods may not be suitable for big traffic data processing, this paper presents a MapReduce-based Parallel Three-PhaseK-Means (Par3PKM) algorithm for solving traffic subarea division problem on a widely adopted Hadoop distributed computing platform. Specifically, we first modify the distance metric and initialization strategy ofK-Means and then employ a MapReduce paradigm to redesign the optimizedK-Means algorithm for parallel clustering of large-scale taxi trajectories. Moreover, we propose a boundary identifying method to connect the borders of clustering results for each cluster. Finally, we divide traffic subarea of Beijing based on real-world trajectory data sets generated by 12,000 taxis in a period of one month using the proposed approach. Experimental evaluation results indicate that when compared withK-Means, Par2PK-Means, and ParCLARA, Par3PKM achieves higher efficiency, more accuracy, and better scalability and can effectively divide traffic subarea with big taxi trajectory data.

MapReduce framework based big data clustering using fractional integrated sparse fuzzy C means algorithm

“…The comparative methods of the big data clustering are performed using the methods, like Multiple Kernel and a Swarm‐Based Map‐Reduce Framework (MKS‐MRF) [53], K‐Means [54], FCM [55], KFCM [56], FPWhale‐MRF [obtained by integrating fractional theory into TSK clustering algorithm, and PSO with WOA, and Sparse FCM [48].…”

Decreasing the execution time of reducers by revising clustering based on the futuristic greedy approach

“…In recent years, a third category has been introduced, which is based on traffic awareness for arrival of irregular jobs. Xia et al [11] proposed an algorithm based on traffic awareness. They applied efficient MapReduce-based parallel clustering algorithm for distributed traffic subarea division.…”

Research on Key Technology of Signal Control Subarea Partition Based on Correlation Degree Analysis

“…Zhao [17] proposed subarea division based on the degree of correlation of key intersections. Xia et al [18] proposed a MapReduce-based parallel three-phase K-Means algorithm for large-flow data partitioning. Xie [19] established a fuzzy C-means clustering method.…”