Adaptive feature extraction for QRS classification and ectopic beat detection

An adaptive system based on the Hermite functions is proposed to adaptively estimate and track the QRS complexes in the electrocardiogram (ECG) signal with few and nonredundant parameters. The system is based on the multiple-input adaptive linear combiner, where the primary input signal is the succession of the QRS complexes, and the reference inputs are the Hermite functions. The weight vector becomes an estimation of the coefficients that represent the QRS complex in the Hermite function base. To adapt these weights the LMS algorithm is used. The authors incorporated a procedure to adaptively estimate a width parameter (b ) that best fits each QRS complex. Applications of this system to classify QRS in case of ECG signals affected by the phenomenon of bigeminy and to detect ectopic beats using the b parameter are presented. In both cases correct pattern classification was obtained