Fast and efficient discovery of key bike stations in bike sharing systems big datasets

Abstract

Bike Sharing Systems (BSS) became one of the popular transportation systems due to their environmental friendly, mobility endorsing, and outdoor activity nature. City residents tend to use particular bike stations more frequently and prevalent than other stations for different reasons, such as popularity and centrality of the locations. Discovering key bike stations is the exploration of frequent and mostly utilized bike stations which are highly preferred by BSS users in terms of spatial and temporal activities. Discovering key stations is important for optimal planning for BSS, bike repositioning methods, and urban land use applications. However, discovering key stations is challenging due to variability of bike user preferences, effect of weather conditions, and big data nature of BSS datasets. In this study, two interest measures are proposed to discover key bike stations using BSS big datasets. Proposed interest measures reveal frequency and prevalence of stations in terms of daily and dataset-wide usage of BSS users. Two algorithms are proposed to discover key stations using proposed interest measures. One of the proposed algorithms could better handle BSS big datasets within less execution time and more efficient memory usage by dividing and processing each section of dataset separately. The proposed algorithms are experimentally evaluated using Chicago Divvy Bikes dataset. The results show that the proposed algorithms are effective on discovering key stations among BSS big datasets, which could be beneficial for making decisions about city resident mobility behaviors in terms of bike user activities and for extracting knowledge about bike user preferences.