An automatic recognition system for patients with movement disorders based on wearable sensors

Movement disorder in lower extremity has been a major concern for the elder worldwide. Early diagnosis and effective therapy monitoring is an important prerequisite to treat patients and reduce health care costs. Objective and non-invasive assessment strategies are an urgent need in order to achieve this goal. In this study, we apply a wearable, lightweight and easy applicable sensor based gait analysis system to measure gait cycle. We analyse the features of different kinds of patients with movement disorder. An automatic pattern recognition system by machine learning and statistical approaches is proposed to support the classification of different neuro-degenerative diseases. The results demonstrate that it is feasible to apply computational classification techniques in characterise these three diseases with the features extracted from gait cycles.