Weighted Dynamic Time Warping for Grid-Based Travel-Demand-Pattern Clustering: Case Study of Beijing Bicycle-Sharing System

Abstract

Many kinds of spatial–temporal data collected by transportation systems, such as user order systems or automated fare-collection (AFC) systems, can be discretized and converted into time-series data. With the technique of time-series data mining, certain travel-demand patterns of different areas in the city can be detected. This study proposes a data-mining model for understanding the patterns and regularities of human activities in urban areas from spatiotemporal datasets. This model uses a grid-based method to convert spatiotemporal point datasets into discretized temporal sequences. Time-series analysis technique dynamic time warping (DTW) is then used to describe the similarity between travel-demand sequences, while the clustering algorithm density-based spatial clustering of applications with noise (DBSCAN), based on modified DTW, is used to detect clusters among the travel-demand samples. Four typical patterns are found, including balanced and unbalanced cases. These findings can help to understand the land-use structure and commuting activities of a city. The results indicate that the grid-based model and time-series analysis model developed in this study can effectively uncover the spatiotemporal characteristics of travel demand from usage data in public transportation systems.

Shared Cycling Demand Prediction during COVID-19 Combined with Urban Computing and Spatiotemporal Residual Network

“…The demand near the residential areas is large in the morning peak period, and the demand near the commercial and industrial land is large in the evening peak period, and there is a significant difference between working days and non-working days. It is found that the demand hot spots in the morning peak period are mainly in the residential areas and the surrounding transportation hubs, and in the evening peak period, they are concentrated in the commercial and industrial land areas, which also corroborates the research of Refs [6,7,12]. In addition, we also found that during COVID-19, the link between the rail transit hubs and the shared bicycles was stronger than that between the buses and shared bicycles, which was also consistent with the findings of Ref [37].…”

“…Shared cycling has a high degree of time regularity, which is significantly different during holidays and working days [5], and there are obvious tidal characteristics near the subway station in residential areas [6]. Gao et al [7] built a shared bicycle space model by combining land use information to analyze the distribution characteristics of strong source and sink points of the Beijing Mobike system and found that the distribution pattern of strong source and sink points has an obvious spatial-temporal heterogeneity.…”

Geographic Complexity: Concepts, Theories, and Practices

“…Zhao et al [11] proposed a data-mining model for exploring the regularities and patterns of human activities from complex spatiotemporal datasets. The model applies to a raster format of geospatial time-series data.…”