Detection of upper limb activities using multimode sensor fusion

Human motion monitoring and activity classification, specifically in the free-living conditions, are becoming increasingly important as preventative and rehabilitative measures in health and wellness applications. In contrast to gate analysis, wearable sensor-based evaluation of the upper body activities is not well studied. The work in this paper describes a novel system for upper body activity monitoring and classification. This paper focuses specifically on the application of motion classification to a complex task of automating rehabilitation evaluation, such as a Wolf Motor Function Test. The presented system consists of a novel wearable motion sensor platform and classification algorithms that convert motion data to an alphabet representation to form strings of primitives. A general string expression is then derived for each task and a regular expression-based searching method is developed. We present results from the successful application of the proposed system to upper extremity activity characterization.