Railway station classification is an effective way to simplify train timetable planning under the condition of railway network. In this paper, a classification method framework of railway station is proposed, which combines principal component analysis with hierarchical clustering. Firstly, considering that there are many attribute indicators and some indicators may be correlated, a new set of indicators is obtained by using principal component analysis to aggregate and reduce the dimension of attribute indicators of railway station. Secondly, a hierarchical clustering method is used to cluster the reduced data set of new station attributes, and the result of station classification is obtained. Finally, taking Beijing-Shanghai high-speed railway as an example, this method is compared with the direct clustering method. The results show that the hierarchical clustering based on principal component analysis is better than the direct clustering method.
Application of Hierarchical Clustering Based on Principal Component Analysis to Railway Station Classification
Sixth International Conference on Transportation Engineering ; 2019 ; Chengdu, China
ICTE 2019 ; 162-171
2020-01-13
Conference paper
Electronic Resource
English
British Library Conference Proceedings | 2009
|Unsupervised Clustering Trees by Nonlinear Principal Component Analysis
British Library Online Contents | 2001
|Nonlinear Principal Component Analysis Based on Hierarchical Input-training Neural Network
British Library Online Contents | 2005
|