Deep neural networks versus support vector machines for ECG arrhythmia classification

Heart arrhythmia is a condition in which the heartbeat is too fast, too slow, or irregular. As Electrocardiography (ECG) is an efficient measurement of heart arrhythmia, lots of research efforts have been spent on the identification of heart arrhythmia by classifying ECG signals for health care. Among them, support vector machines (SVMs) and artificial neural networks (ANNs) are the most popular. However, most of the previous studies reported the performance of either the SVMs or the ANNs without in-depth comparisons between these two methods. Also, a large number of features can be extracted from ECG signals, and some may be more relevant to heart arrhythmia than the others. This paper is to enhance the performance of heart arrhythmia classification by selecting relevant features from ECG signals, applying dimension reduction on the feature vectors, and applying deep neural networks (DNNs) for classification. A holistic comparison among DNNs, SVMs, and ANNs will be provided. Experimental results suggest that DNNs outperform both SVMs and ANNs, provided that relevant features have been selected.