Selection of significant independent components for ECG beat classification

In this paper, we propose a novel independent components (ICs) arrangement strategy to cooperate with the independent component analysis (ICA) method used for ECG beat classification. The ICs calculated with a regular ICA algorithm are re-arranged according to the L2 norms of the rows of the de-mixing matrix. The validity of this ICs arrangement strategy is discussed mathematically and testified experimentally. Only when the ICs are arranged in an appropriate order, we are able to select the first couple of components for the calculation of the most significant subset of bases to discriminate different types of ECG beats. The effectiveness and efficiency of the proposed method and three other ICs arrangement strategies are studied. Two kinds of classifiers, including probabilistic neural network and support vector machines, are used to evaluate the proposed method. ECG samples attributing to eight different ECG beat types were extracted from the MIT-BIH arrhythmia database for the study. The experiment results demonstrate that the proposed ICs arrangement strategy outperforms the other strategies in reducing the number of features required for the classifiers. Among the many experimental setups, the scheme with the SVM classifier in conjugate with the log(cosh(·)) contrast function and the proposed ICs arrangement strategy requires only 17 ICs to achieve more than 98.7% classification accuracy and is determined to be most efficient. When comparing to the other methods in the literature, the proposed scheme outperforms the other methods in terms of effectiveness and efficiency. The impressive result validates the strategy in the selection of significant ICs subset and demonstrates the proposed scheme an effective and efficient approach in computer-aided diagnosis of heart diseases based on ECG signals.