Rail Transit Stations Classification Based on Spectral Clustering

Qi Shi

School of Science, Zhejiang University of Science and Technology, Hangzhou, China.

Shaowei Sun *

School of Science, Zhejiang University of Science and Technology, Hangzhou, China.

Jingjing Jie

School of Economics and Management, Zhejiang University of Science and Technology, Hangzhou, China.

*Author to whom correspondence should be addressed.


Abstract

To identify the function and positioning of urban rail stations, and provide further guidance for design and construction, a classification method based on spectral clustering algorithm is established. Firstly, based on the principles of comprehensiveness and robustness, 5 initial indicators were selected, including total entry count, total exit count, entrances count, bus connecting lines count, and metro connecting lines count. Secondly, we normalize the original data by Z-score method and extract two main clustering factors through principal component analysis. Finally, we propose a station classification model based on spectral clustering algorithm. The effectiveness of the proposed method is verified in Hangzhou Metro System. The K-means cluster algorithm and spectral cluster methods are employed. The results show that the proposed model can successfully identify the types of urban rail transit stations, clarify the function and orientation of each station.

Keywords: Urban rail transit, spectral clustering, station classification, cluster analysis


How to Cite

Shi, Qi, Shaowei Sun, and Jingjing Jie. 2022. “Rail Transit Stations Classification Based on Spectral Clustering”. Asian Journal of Probability and Statistics 17 (4):12-21. https://doi.org/10.9734/ajpas/2022/v17i430428.

Downloads

Download data is not yet available.