INVESTIGADORES
LOPEZ CELANI Natalia Martina
artículos
Título:
Bispectrum-based features classification for myoelectric control
Autor/es:
EUGENIO C. OROSCO; NATALIA M. LÓPEZ; FERNANDO DI SCIASCIO
Revista:
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
Editorial:
ELSEVIER SCI LTD
Referencias:
Lugar: Amsterdam; Año: 2012 p. 1 - 16
ISSN:
1746-8094
Resumen:
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 movements
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.