Year: 2018
Type: report
Abstract: Many public transit networks around the world use the smart card data which provides the information about the users.With the aim of uncovering the users' behaviours, there has been an increased interest in analyzing their temporal activities, in recent years.In this regard, several methods are developed mostly applying clustering approaches to perform data segmentation and discover the pattern of users.The next step is retrieving the information from the clusters, such as the variability of a user in cluster's membership over a period of time.This study addresses the applicability of the temporal segmented data identified in 18 clusters for measuring the stability of temporal habits of users as well as conducting descriptive analysis of clusters, fare types and the days of week to support the justification of findings.Each cluster contains users with specified time of day and number of boarding.To understanding whether the users are stable in the clusters, the sequential measurement based on the Euclidean distance between centers of clusters, as the representative of their members, is applied for each user over one month in this study.Then, the stabilities are ranked to three different levels of high and medium stable or unstable by the help of a histogram.The data and stability levels have the potential to track and visualize users, specifically, in days of week.The outcomes demonstrate the high stability of adult customers on three temporal routines, specifically, regarding the days of week.The users of the first and last working days of a week have the similar tendency in cluster's membership tracks and pretty same proportion of stability levels, having the minimum high stable and the maximum unstable users.And we discover that the most single-traveled day users commute in these two days.On the other hand, the other three working days show similar trends containing the maximum high stable users.In addition, tracking the users shows the moderate impact of long weekends as well as first and last day of month on the level of stability.Analyzing the weekends and holidays, shows no pattern and users are present on network on average once over these days.Furthermore, more than 70% of users are present on the network more than 14 days and interestingly, they are categorized in high and medium stable levels.Regarding the fare types, we recognized that regular students with the significant fewer frequency than regular adults but tending to have the same unstable frequency.
Authors: Moradi, Mahnaz, Trépanier, Martin
Language: English
Subfield: Transportation
Field: Social Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7034318485