Design and Implementation of Gesture Recognition for Rehabilitative Technology in Orthopaedic Recovery

Rehabilitation process after an accident is crucial for proper and systematic healing of the bones, muscles and other body organs and parts that are affected due to the injuries. In most parts of India, rehabilitation is largely ignored after the treatment preventing proper recovery of the affected body parts due to lack of adequate infrastructure and economic feasibility. Recently, a large body of work has revealed a very accurate deep learning established movement categorization algorithmic technique for assistive technology applications. However, minimum seriousness is given to its relative hardware execution. But direct mapping these algorithms onto battery-operated devices is a point of care, edge devices would not yield optimum results necessitating an algorithm-architectural holistic design methodology. In the current study, we offered a method for creating reconfigurable Embedded Systems along with Internet of Things (IoT) for deep learning established gesture recognition for rehabilitative technology applications. The microcontroller was used as a web server to facilitate the design. The sensor was used to provide the 3D object representation which is a sensor based on Micro-Electromechanical Systems (MEMS) Technology. This chip uses Inter-Integrated Circuit (I2C) protocol for communication. Resulting to effectively monitor stage-wise recovery process with an IoT enabled Web-Interface and the data is stored in a cloud.