Automatic Recognition of Postures and Activities in Stroke Patients

Stroke is the leading cause of disability in the United States. It is estimated that 700,000 people in the United States will experience a stroke each year and that there are over 5 million Americans living with a stroke. In this paper we describe a novel methodology for automatic recognition of postures and activities in patients with stroke that may be used to provide behavioral enhancing feedback to patients with stroke as part of a rehabilitation program and potentially enhance rehabilitation outcomes. The recognition methodology is based on Support Vector classification of the sensor data provided by a wearable shoe-based device. The proposed methodology was validated in a case study involving an individual with a chronic stroke with impaired motor function of the affected lower extremity and impaired walking ability. The results suggest that recognition of postures and activities may be performed with very high accuracy.