Details
Poster
Presenter(s)
Display Name
Reza Azhiri
- Affiliation
-
AffiliationUniversity of Texas at Dallas
- Country
Abstract
Electromyography is a promising way to control prosthetic limbs. It is necessary to select the best classifier with a satisfying accuracy. In this paper, we propose to utilize Extreme Value Machine (EVM) as a powerful and promising algorithm for the classification of EMG signals. We employ reflection coefficients obtaining from an Autoregressive (AR) model to train a set of classifiers. This paper shows that EVM has better accuracy in comparison to the conventional classifiers that are applied in the literature, i.e., K-Nearest Neighbors (KNN) and Support Vector Machine (SVM), to solve a classification task over EMG signals.