A 12-lead clinical ECG classification method based on Semi-supervised Discriminant Analysis

In this paper, we propose an electrocardiogram (ECG) pattern classification method for 12-lead ECG using Semi-supervised Discriminant Analysis (SDA). The feature of 12-lead ECG signal is firstly extracted by wavelet transformation (WT). SDA is used to find a projection which projects the WT feature space into low dimension feature space for ECG pattern classification. The semi-supervised learning approach is used to cluster unlabeled data. Finally the SVM classifier is applied to multi-classification experiments. The experiment results show the proposed method can achieve high classification accuracy. When the labeled data is insufficient, the proposed method also demonstrates good generalization ability.