Arrhythmia recognition and classification using kernel ICA and higher order spectra

Electrocardiogram (ECG) is one of the monitoring methodology for the identification of arrhythmia disease. The conventional methodologies of arrhythmia identification are based on morphological features or certain transformation technique. These conventional techniques are partially successful in arrhythmia identification, because it treats heart as a linear structure. In this paper, ECG based arrhythmia identification is assessed by employing MIT-BIH arrhythmia dataset. The proposed approach contains two major steps: feature extraction and classification. Initially, a combination of non-linear and linear feature extraction is carried-out using Principal Component Analysis (PCA), Kernel Independent Component Analysis (KICA) and Higher Order Spectrum (HOS) for achieving optimal feature subsets. The linear experiments on ECG data achieves high performance in noise free data and the non-linear experiments distinguish the ECG data more effectively, extract hidden information and also helps to attain better performance under noisy conditions. After finding the feature information, a binary classifier Support Vector Machine (SVM) is employed for classifying the normality and abnormality of arrhythmia. In experimental analysis, the proposed approach distinguishes the normality and abnormality of arrhythmia ECG signals in terms of specificity, sensitivity and accuracy. Experimental outcome shows that the proposed approach improved accuracy in arrhythmia detection up to 0.5-1% compared to the existing methods: neural network and SVM based radial basis function.