Methodology for Mining, Discovering and Analyzing Semantic Human Mobility Behaviors
Several institutes produce large semantic data sets about daily activities and human mobility. The analysis and the understanding of these data are crucial for urban planning, socio-psychology and political sciences or epidemiology. Currently, none of usual data mining process is customized for a complete analysis of semantic mobility sequences from data to understandable behaviors. Based on an extended review of the literature, we define in this article a new methodological pipeline, SIMBA (Semantic Indicators for Mobility and Behavior Analysis), for mine and analyze semantic mobility sequences in order to discover coherent information and human behaviors. A framework for semantic sequence mobility analysis and clustering explicability integrating different complementary statistical indicators and visual tools is proposed. To validate this methodology, we use a large set of real daily mobility sequences obtained from one household-travel survey. Complementary knowledge are automatically discovered help to this method.
READ FULL TEXT