Cardiac arrhythmia classification based on multi-features and support vector machines / 生物医学工程学杂志

ABSTRACT

To solve the problem of cardiac arrhythmias classification, we proposed a novel algorithm based on the multi-feature fusion and support vector machines (SVM). Kernel independent component analysis (KICA) was used to extract nonlinear features and wavelet transform (WT) was used to extract time-frequency features. Combining these features could include more information about the disease. We designed the classification model based on SVM combined with error correcting output codes (ECOC). Receiver operating characteristic curve (ROC) and Area Under the ROC curve (AUC) value were used to assess the classification model. The value of AUC is 0.956 against MIT-BIH arrhythmia database. Experimental results showed effectiveness of the proposed method.