Extracting land-use patterns using location data from smartphones

摘要: This paper proposes an approach to extract area-by-area and daily land-use patterns using location data obtained from users of Yahoo! Japan's smartphone applications. Information used for extracting is extracted only data. In this research, a pattern defined as how the area throughout day. We based on temporal transition in number people area. petterns extraction, clustering technique with infinite Gaussian mixture model Dirichlet process mixtures used, which can be discover appropriate patterns. Experiments were conducted 34 areas over 56 consecutive days. means 1,904 conditions studied. The results our experiments show that successfully extracts population.The also reveal additional features are estimated spatio-temporal helps us control