| Summary: | This paper explores the application of Surface Electromyography (SEMG) for hand movement classification using machine learning techniques. SEMG signals play a crucial role in sports medicine, rehabilitation, prosthesis control, and medical diagnosis. The study addresses a multi-class problem, extending the dataset with limited prior exploration. Nine features from SEMG signal's time domain are extracted, including Maximum Amplitude, Root Mean Square, Slope Sign Change, Variance, Simple Square Integral, Zero Crossing, Waveform Length, and Willison Amplitude. Linear Discriminant Analysis is employed for dimensionality reduction as a feature selection technique. The proposed algorithm achieves an overall classification accuracy of 72% for the classification of six different hand movements performed by five healthy subjects using Support Vector Machines. This research contributes to the advancement of SEMG-based hand movement classification in various practical applications. © 2024 IEEE.
|
|---|