Exploratory data analysis of activity diary data: a space–time GIS approach

Abstract

Study of human activities in space and time has been an important research topic in transportation research. Limitations of conventional statistical methods for analysis of individual-level human activities have encouraged spatiotemporal analysis of human activity patterns in a space–time context. Based on Hägerstrand’s time geography, this study presents a space–time GIS approach that is capable of representing and analyzing spatiotemporal activity data at the individual level. Specifically, we have developed an ArcGIS extension, named Activity Pattern Analyst (APA), to facilitate exploratory analysis of activity diary data. This extension covers a set of functions such as space–time path generation, space–time path segmentation, space–time path filter, and activity distribution/density pattern exploration. It also provides a space–time path based multi-level clustering method to investigate individual-level spatiotemporal patterns. Using an activity diary dataset collected in Beijing, China, this paper presents how this Activity Pattern Analyst extension can facilitate exploratory analysis of individual activity diary data to uncover spatiotemporal patterns of individual activities.