Document Type : Original Article
Authors
1 Department of Industrial Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran
2 Assistant Professor Department of Industrial Engineering Faculty of Engineering Ferdowsi University Of Mashhad (FUM)
3 Department of Civil Engineering, Faculty of Engineering, Golestan University, Gorgan, Iran
Abstract
Abstract
Travel patterns are significantly related to certain characteristics such as spatial and temporal diversity of passengers, population density, land use and access to public transportation, and creating meaningful links between them is an important issue. The analysis of passengers' behaviors and characteristics can be done according to spatial and temporal dimensions. The pattern of how people move and their travel behavior is closely related to urban structures. This study delves into zonal-based public transport travel behavior in Mashhad, Iran, leveraging smart card data. Based on public transportation travel transactions, the K-Means algorithm was used to cluster zones in the morning, noon, and evening time periods, and the Mean Shift algorithm was used to cluster them based on the spatial variables of the population and the types of built-up areas in each zone. In the temporal clustering of zones for bus transactions into 2 and metro into 7 clusters; And in spatial clustering, the zones were divided into 8 clusters. Analysis of clusters with demographic information and built-up areas in each zone showed that each cluster has its own function and a single and specific reason for the amount of transactions in all zones cannot be determined. The findings of the research were able to confirm correlations between population and residential areas with morning trips; or commercial and educational areas with midday trips; as well as the transactions of marginal traffic zones with near outer residential areas in time intervals. The results of this study are important for the decision makers and planners in the design and development of land and transportation policies.
Keywords: built-up areas, clustering of traffic zones, temporal and spatial patterns, smart card data
Keywords
Main Subjects
Send comment about this article