Hand Movements Detection Using EMG Signals for Human-Computer Interface and convolution neural network

Abstract

This article presents a study on the effectiveness of a Convolutional Neural Network -based approach for hand movement detection using electromyography (EMG) signals. The study involved 40 participants and used Myo armbands to record EMG signals. The CNN model consisted of three convolutional layers, three max-pooling layers, and two fully connected layers. The model achieved an F1-score of 0.981, precision of 0.981, and recall of 0.981, outperforming two other machine learning algorithms, SVM and RF. The study’s results demonstrate the potential of using CNNs for detecting hand movements using EMG signals, which can be applied in prosthetics and robotics for controlling prosthetic limbs and robotic arms. The study’s findings suggest that CNN-based approaches have great potential for future research in the field of EMG-based hand movement detection.