Towards arm tremor diagnosis

Many clinical studies have shown that the arm movement of patients with neurological injury is often slow. In this paper, the speed analysis of arm movement is presented, with the aim of evaluating arm movement automatically using a Kinect camera. The consideration of arm movement appears trivial at first glance, but in reality it is very complex neural and biomechanical process that can potentially be used for detecting a neurological disorder. This is a preliminary study, on healthy subjects, which investigates three different arm-movement speeds: fast, medium and slow. With a sample size of 27 subjects, our developed algorithm is able to classify the three different speed classes (slow, normal, and fast) with overall error of 5.43% for interclass speed classification and 0.49% for interaclass classification. This is the first step towards enabling future studies that investigate abnormality in arm movement, via use of a Kinect camera.