Mining from Time Series Human Movement Data

Human motion not only contains a wealth of information about actions and intentions, but also about identity and personal attributes of the moving person. Research also indicates that there are positive relationships between the health of a person and their pattern of motion. In this research we utilize human walking data collected from volunteers to identify age categories and to detect possible changes in the individual´s health condition. The approach is based on transforming biological motion data into a representation that subsequently allows for analysis using artificial intelligence techniques. Using wireless accelerometer sensors we were able to collect and transform the data into a numeric representation. We then applied the numeric data to various artificial intelligence algorithms to form classification models and use it for our analysis.