Authors: Geonhwa You*, Dept. of Geography, Kyung Hee University, Seoul, South Korea, Chul Sue Hwang, Dept. of Geography, Kyung Hee University, Seoul, South Korea
Topics: Urban Geography, Quantitative Methods, Geographic Information Science and Systems
Keywords: Urban structure model, Spatio-temporal clustering, non-parametric clustering, cell phone user-based population data, Machine learning
Session Type: Paper
Start / End Time: 5:00 PM / 6:40 PM
Room: Tyler, Marriott, Mezzanine Level
Presentation File: No File Uploaded
The city is a place for political, economic, social-cultural activities and human lives. Many cities carrying out commercial and business functions show the large density of population and affect the life pattern of households, such as commuting, leisure activities at a specific time and space. Therefore, identifying the spatial structure of cities is a prerequisite for the management of cities including development and validation of adequate planning strategies. Many theories which describing the urban structure are introduced by Burgess (1925), Hoyt (1939), Harris and Ullman (1945). While these theories still valid, another approach of describing the urban structure is required. Because the internal structure of cities became increasingly complex as cities became more polynucleated and dispersed and conurbation. In addition, in the era of big data, a huge amount and various forms of data can be gathered from sensors, which shows the possibility of constructing different form of the urban structural model. In this research, we use cell phone user-based population data which measures the number of population at a specific time and space. In analyzing data, we classify the age groups of the population, according to life cycle focused on labor and consumption. To discover the patterns from each age group, we use spatio-temporal polygonal data clustering methodology. The results show different patterns with each age at a specific time and space. Furthermore, we can identify different patterns from weekday and weekend within a same age group. After comprehensive reviewing the results, we describe the urban structure.