Supervised Machine Learning based Fast Hand Gesture Recognition and Classification Using Electromyography (EMG) Signals

Machines are built to give accessibility, precision, cost-effectiveness, and adaptability characteristics. This work will facilitate the recognition of hand gestures based on supervised learning. Signal processing-based techniques such as pre-processing (normalization) and segmentation (empirical mode decomposition) are employed. The Cubic-Support Vector Machine classifier is trained on four different EMG (Electromyography) based hand gestures named as wrist flexion, wrist extension, resting hand, clenched fist. Spectral domain features are extracted, which provide less variance than other extraction methods. This supervised machine learning model achieved a cumulative classification accuracy of 98.9%. This hand gesture-based system can help handicapped people in nonverbal communication and physically challenged individuals in non-invasive machine communication.