Competent and Affordable Rehabilitation Robots for Nervous System Disorders Powered with Dynamic CNN and HMM

Neurological disorder is one of the common health issues that affect billions of people in and around the world. This disease is caused by the malfunctioning of central nerve system and the peripheral nerve system. Few of such disorders like the Alzheimer's disease and Parkinson's disease are much difficult to live with and ruined life of many people. In particular, the Parkinson's disease affected patients who experience complications due to the Gait Freezing (GF) symptoms that create specific movement inabilities. The only rehabilitation mechanism available is the artificial generation of the dopamine levels. A rehabilitation mechanism robot is proposed, which triggers the exercises automatically by inducing certain vibration to the affected. It comprises of two parts, viz., a fixed actuator mechanism at the bed/chairs and the other is a wearable sensor and is fixed in the patient's hands/ legs/neck as bracelets, bands, or chains. Here, convolutional neural networks (CNN) and hidden Markov model (HMM) are used for the processing of sensor signals and decision-making. Thus, the proposed sensor-based robot paves way for an affordable and efficient rehabilitation mechanics to person in need, powered with dynamic CNN techniques that keep them motivated and feel comfortable without help of a skilled person.

Перевод пока недоступен