Evaluation of emg features for movement control of prostheses

A cluster separation index has been applied to a variety of commonly-used EMG (electromyelogram) features for movement control of a prosthetic arm. It has been shown that, for small window sizes, the Integral of the Absolute Value (IAV) of the EMG is the most suitable feature, while, for hrge window sizes, the first coefficient of the Auto Regressive (AR) mode1 of the EMG provides greater class separability. Suggestions for future work are discussed.

[1]  George N. Saridis,et al.  EMG Pattern Analysis and Classification for a Prosthetic Arm , 1982, IEEE Transactions on Biomedical Engineering.

[2]  Jerry M. Mendel,et al.  Identification of moving-average systems using higher-order statistics and learning , 1992 .

[3]  Donald W. Bouldin,et al.  A Cluster Separation Measure , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Daniel Graupe,et al.  Functional Separation of EMG Signals via ARMA Identification Methods for Prosthesis Control Purposes , 1975, IEEE Transactions on Systems, Man, and Cybernetics.