Bispectrum-based features classification for myoelectric control

EUGENIO C. OROSCO; NATALIA M. LÓPEZ; FERNANDO DI SCIASCIO

BIOMEDICAL SIGNAL PROCESSING AND CONTROL

ELSEVIER SCI LTD

Lugar: Amsterdam; Año: 2012 p. 1 - 16

1746-8094

Surface electromyographic signals provide useful information about motion intentionality; therefore, served as a suitable reference signal for control purposes. We propose a continuous classification scheme of five upper limb movements applied to a myoelectric control of a robotic arm. This classification is based on features extracted from the bispectrum of four EMG signal channels. Among several bispectrum estimators, we have focused on arithmetic mean, median, and trimmed mean estimators, and their ensemble average versions. All bispectrum estimators have been evaluated in terms of accuracy, robustness against outliers, and computational time. The median bispectrum estimator shows low variance and high robustness properties. We propose two feature reduction methods for the complex bispectrum matrix. The first one estimates the three classic means (Arithmetic, Harmonic, and Geometric means) from the module of the bispectrum matrix, and the second one estimates the same three means from the square of the real part of the bispectrum matrix. We use a two-layer feedforward network for movement’s classification, and a dedicated system to achieve the myoelectric control of a robotic arm. We found that the classification performance in real-time is similar to those obtained off-line by other authors, and that all volunteers successfully completed the control task.