Decoding of Hand Motion Using State of Art Time Domain, Frequency Domain And Feature Extraction

Abstract

Exoskeletons that are activated by the muscles and brain have been suggested to train the motor skills of stroke victims. Training can incorporate task variety since an exoskeleton allows for the execution of various movement types.Differentiating between movement types at the same time from brain activity is challenging, but it might be accessible from residual muscular activity that many patients retain regain.This study examines whether forearm EMG from five stroke patients can be used to decode seven distinct motion classes of the hand and forearm. This study evaluates classifiers like Support vector machine (SVM), Lineardiscriminant analysis (LDA) and K nearest neighbor (KNN). It investigated the relation of motor impairment with classification accuracy by the classifiers. During the following motion classes: Supination, Pronation, Hand Close, Hand Open, Wrist Extension, Wrist Flexion, and Pich, five surface EMG channels were recorded.Every motion was performed by patients three times repetition over the course of eight weeks.Support vector machines, k nearest neighbor, and linear discriminant analysis were used to classify decoding of hand moments for stroke patients. On average,73.69 ± 6.39%SVM,71.6 ± 5.09% KNNand 50±4.56 LDA of the movements were correctly classified.Seven motion classes were demonstrated to be decoded from residual EMG, and SVM proved to be the most effective classification method when compared to the other three classifiers for decoding of hand motion for stroke patients.The results of this study may have implications for the development of exoskeletons, suits, or gadgets, that are powered by EMG signals. These devices might be utilized in the comfort of the patient's home to assist stroke sufferers with their training activities. Therefore, the findings of this study may assist in improving the effectiveness and accessibility of these useful tools for stroke survivors.