Analysis of Surface Electromyography Signals using Continuous Wavelet Transform for Feature Extraction

A number of Digital Signal Processing techniques are being applied to Surface Electromyography (SEMG) signals for classification using feature extraction. Traditional analysis methods such as Fast Fourier Transform (FFT) could not be used alone because muscle diagnosis requires time-based information. Continuous Wavelet Transform (CWT) was selected for extracting efficient features of the SEMG signals in this research. CWT includes time-based information as well as scales, which can be converted to frequencies, making muscle diagnosis easier. CWT produces a scalogram plot along with its corresponding time-frequency based spectrum plot. Using the extracted features of the dominant frequencies of the wavelet transform and the related scales, we were able to train and validate an Artificial Neural Network (ANN) for signal classification.