Upper Limb Movement Recognition Utilising EEG and EMG Signals for Rehabilitative Robotics

Upper limb movement classification, which maps input signals to the target activities, is a key building block in control of rehabilitative robotics. Classifiers are trained for system comprehend desires patient whose upper limbs do not function properly. Electromyography (EMG) and Electroencephalography (EEG) used widely classification. By analysing classification results real-time EEG EMG signals, can understand intention user predict events that one would like carry out. Accordingly, it will provide external help user. However, noise data collection process contaminates effectiveness data, undermines performance. Moreover, all patients strong due muscle damage neuromuscular disorder. To address these issues, this paper explores different feature extraction techniques machine learning deep models proposes novel decision-level multisensor fusion technique integrate with signals. This retrieves effective information from both sources desire user, thus aid. testing out proposed on publicly available WAY-EEG-GAL dataset, contains were recorded simultaneously, we manage conclude feasibility system.