期刊
JOURNAL OF TRANSPORTATION ENGINEERING PART A-SYSTEMS
卷 149, 期 11, 页码 -出版社
ASCE-AMER SOC CIVIL ENGINEERS
DOI: 10.1061/JTEPBS.TEENG-7855
关键词
High-speed railway (HSR) station; Time series data; Density-Based Spatial Clustering of Applications with Noise (DBSCAN); Evolution characteristics
This study adopts the DBSCAN algorithm to classify HSR stations in different years and accurately cluster them using large-scale actual passenger flow data. The results show that both the hierarchical structure of HSR stations and passenger flow exhibit spatial-temporal evolution across years.
Effective management of the high-speed railways (HSR) system requires an in-depth understanding of the HSR stations in the network, e.g., the time-dependent volume distribution. The classification of HSR stations is the scientific basis for transport policymaking and land-use planning. Existing classification methods cannot meet the needs of temporal variation of passenger flow or the refined design and operation of HSR stations. This study adopts the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm to classify HSR stations in different years. Using the data of Jiangsu Province, China, as an example, the time series of arrival and departure passenger flow at HSR stations are clustered via the DBSCAN algorithm, and the HSR stations are clustered into three classes. To determine the hierarchical structure of HSR stations representing the evolution of HSR networks, we use large-scale panel data obtained from mobile phone cellular data across years (July 1-14 from each of the years 2018, 2020, and 2021) to capture and analyze the spatial-temporal evolution characteristics of massive passenger flow at HSR stations. It is indicated that both HSR station hierarchy and passenger flow have the characteristics of spatial-temporal evolution across years, and the classification results are influenced by the geographical positions of cities and HSR layout. Accurate clustering of HSR stations via large-scale actual passenger flow data enables railway authorities and operators to identify critical nodes for efficient HSR network performance. The resulting classification would contribute to an in-depth understanding of the evolution characteristics of passenger flow in different years.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据