Understanding the intra-day and intra-week ridership patterns of urban rail transit stations in London using a fuzzy clustering approach

Abstract

The needs for transit station classification are ever-growing as the planning process, be it at a strategic or operational level, becomes increasingly automated, data-oriented, and short-cycled. Whilst most existing models have used binary methods, this study applied a fuzzy clustering approach and examined cluster memberships (i.e., to what degree a station belongs to each cluster) of London rail transit stations by using entry and exit data with intra-day and intra-week variations. A method of hyperparameter selection in fuzzy clustering considering the context of transportation and a framework of ridership variation analysis was proposed. The results suggest that fuzzy clustering can maximise the information from high-resolution temporal passenger flow data of urban rail transit. The membership breakdowns allow users to have a better understanding of station characteristics and help to avoid inadequate plans by treating the stations belonging to multiple clusters in a different manner from the binary clustering, where each station only belongs to one cluster. Furthermore, fuzzy clustering can capture the ridership variation patterns and reveal special clusters. The results can be potentially applied in operation planning, such as service timetabling, station staff working-hour designs and fare strategy designs, etc.