A COMBINED PCA–ICA STATISTICAL APPROACH AND QUADRATIC SPLINE WAVELETS FOR DETECTION OF R-PEAKS AND HEART RATE ESTIMATIONS IN ELECTROCARDIOGRAMS

Abstract

The need for the possible improvements in the proposed algorithm is felt toward more effective filtering in the principal component analysis (PCA) preprocessing stage itself, as well for better variance threshold adjustment. Using composite wavelet transform (WT)-based PCA–ICA methods helps for redundant data reduction as well for better feature extraction. This article discusses some of the conditions of ICA that could affect the reliability of the separation and evaluation of issues related to the properties of the signals and number of sources. In this analysis, a new statistical algorithm is proposed, based on the use of combined PCA–ICA for the three correlated channels of 12-channel electrocardiographic (ECG) data. This study also deals with the detection of QRS complexes in electrocardiograms using combined PCA–ICA algorithm. The efficacy of the combined PCA–ICA algorithm lies in the fact that the location of the R-peaks is accurately determined, and none of the peaks are ignored or missed, as quadratic spline wavelet is also used. With (WT)-based methods, PCA and ICA are used not only for preprocessing, but may also be used for postprocessing based on the requirements, whether ICA is used first then PCA or vice versa.