A Self-Learning Control Scheme for Upper-Limb Prosthesis Control Using Combined Neuromuscular and Brain Wave Signals

The control scheme in myoelectric prosthesis includes a pattern recognition section whose task is to decode an input signal and produce a respective actuation signal to drive the motors in the prosthesis limb towards the completion of the user intended gesture motion. The pattern recognition architecture works with a classifier which is typically trained and calibrated offline with a supervised learning framework, this method involves the training of classifiers which form part of the pattern recognition scheme but also induces additional and often undesired lead time in the prosthesis design phase. In this study, a 4 stage identification framework is formulated to design an intelligent system capable of self-learning patterns from bio-signal inputs from Electromyography (neuromuscular) and Electroencephalography (brain wave) biosensors for a Transhumeral amputee case study. The results show that the designed self-learning framework could form an online automated system that will be beneficial in the reduction of lead time involved in the customization and design of the controller for a myoelectric prosthesis.