Chanchan Zhao, Feng Liu, Xiaowei Hai, Journal of Information Processing Systems Vol. 14, No. 3, pp. 694-708, Jun. 2018  

https://doi.org/10.3745/JIPS.04.0074
Keywords: Hierarchical Dividing, K-means, Passenger Nodes, Passenger Dedicated line, Self-Organizing Map
Fulltext: PDF Full Text PubReader

Abstract

China possesses a passenger dedicated line system of large scale, passenger flow intensity with uneven distribution, and passenger nodes with complicated relations. Consequently, the significance of passenger nodes shall be considered and the dissimilarity of passenger nodes shall be analyzed in compiling passenger train operation and conducting transportation allocation. For this purpose, the passenger nodes need to be hierarchically divided. Targeting at problems such as hierarchical dividing process vulnerable to subjective factors and local optimum in the current research, we propose a clustering approach based on self-organizing map (SOM) and k-means, and then, harnessing the new approach, hierarchical dividing of passenger dedicated line passenger nodes is effectuated. Specifically, objective passenger nodes parameters are selected and SOM is used to give a preliminary passenger nodes clustering firstly; secondly, Davies–Bouldin index is used to determine the number of clusters of the passenger nodes; and thirdly, k-means is used to conduct accurate clustering, thus getting the hierarchical dividing of passenger nodes. Through example analysis, the feasibility and rationality of the algorithm was proved.

Statistics
Cite this article