Find in Library

Electrocardiogram (ECG) monitoring is continuously required to detect cardiac ailments. At times it is challenging tointerpret the differences in the P- QRS-T curve. The proposed approach aims to show the excellence of kernel capabilitiesof Kernel Principal Component Analysis (KPCA) and Kernel Independent Component Analysis (KICA) in the waveletdomain. In this work, experiments are performed using five different categories of cardiac beats. The supervisedclassifiers like feed-forward neural network (FNN), backpropagation neural network (BPNN), and K nearest neighbor(KNN) statistically evaluates the impact of discrete wavelet with KPCA and KICA on extracted beats. The performanceevaluation also compares the outcomes with existing techniques. The obtained results justify the supremacy of thecombination of wavelet, kernel, and KNN approach, yielding a 99.7 % classification success rate. The five-fold crossvalidation scheme is used for measuring the efficacy of classifiers.