Increasing the precision of public transit user activity location detection from smart card data analysis via spatial–temporal DBSCAN

Date

2024-09-01

Author

Ozer, Fehmi Can
Tüydeş Yaman, Hediye
Dalkıç Melek, Gülçin

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

48
views

0
downloads

Cite This

Smart Card (SC) systems have been increasingly adopted by public transit (PT) agencies all over the world, which facilitates not only fare collection but also PT service analyses and evaluations. Spatial clustering is one of the most important methods to investigate this big data in terms of activity locations, travel patterns, user behaviours, etc. Besides spatio-temporal analysis of the clusters provide further precision for detection of PT traveller activity locations and durations. This study focuses on investigation and comparison of the effectiveness of two density-based clustering algorithms, DBSCAN, and ST-DBSCAN. The numeric results are obtained using SC data (public bus system) from the metropolitan city of Konya, Turkey, and clustering algorithms are applied to a sample of this smart card data, and activity clusters are detected for the users. The results of the study suggested that ST-DBSCAN constitutes more compact clusters in both time and space for transportation researchers who want to accurately detect passengers’ individual activity regions using SC data.

Subject Keywords

Clustering, DBSCAN, Smart card, ST-DBSCAN

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85199191421&origin=inward
https://hdl.handle.net/11511/110768

Collections

Department of Civil Engineering, Article