Open AccessImproving Gaussianity of EMG Envelope for Myoelectric Robot Arm Control
Author(s) -
Sandra Márquez-Figueroa,
Yuriy S. Shmaliy,
Oscar Ibarra-Manzano
Publication year - 2021
Publication title -
wseas transactions on biology and biomedicine
Language(s) - English
Resource type - Journals
eISSN - 2224-2902
pISSN - 1109-9518
DOI - 10.37394/23208.2021.18.12
Subject(s) - envelope (radar) , smoothing , filter (signal processing) , computer science , signal (programming language) , electromyography , artificial intelligence , speech recognition , kalman filter , pattern recognition (psychology) , computer vision , telecommunications , medicine , radar , psychiatry , programming language
Several methods have been developed in biomedical signal processing to extract the envelope and features of electromyography (EMG) signals and predict human motion. Also, efforts were made to use this information to improve the interaction of a human body and artificial protheses. The main operations here are envelope acquiring, artifacts filtering, estimate smoothing, EMG value standardizing, feature classifying, and motion recognizing. In this paper, we employ EMG data to extract the envelope with a highest Gaussianity using the rectified signal, where we deal with the absolute EMG signals so that all values become positive. First, we remove artifacts from EMG data by using filters such as the Kalman filter (KF), H1 filter, unbiased finite impulse response (UFIR) filter, and the cKF, cH1 filter, and cUFIR filter modified for colored measurement noise. Next, we standardize the EMG envelope and improve the Gaussianity. Finally, we extract the EMG signal features to provide an accurate prediction.