Arrhythmia Recognition Based on EMD and Support Vector Machines

According to the non-stationary feature of ECG signal, a new classification method of arrhythmia is introduced. This method combines empirical mode decomposition (EMD) with singular value decomposition (SVD), using support vector machines (SVM) for classifying. First, ECG signal is decomposed into a set of intrinsic mode function (IMF) using empirical mode decomposition method. The initial feature vector matrix is formed by these IMFs. Then, the initial feature vector matrix is decomposed using singular value decomposition, and singular values of the matrix can be calculated. Singular values are regarded as the feature vector of ECG signal, support vector machines used as classifiers are established to identify the condition of arrhythmia. Experimental results show that, this method can classify the types of arrhythmia accurately and effectively, and can be used for the field of ECG pathological auxiliary diagnosis.