LAUSR

In the field of arrhythmia classification, classification accuracy has always been a research hotspot. However, the noises of electrocardiogram (ECG) signals, the class imbalance of ECG data, and the complexity of spatiotemporal features of ECG data are all important factors affecting the accuracy of ECG arrhythmias classification. In this article, a novel DSCSSA ECG arrhythmias classification framework is proposed. First, discrete wavelet transform (DWT) is used to denoise and reconstruct ECG signals to improve the feature extraction ability of ECG signals. Then, the synthetic minority oversampling technique (SMOTE) oversampling method is used to synthesize a new minority sample ECG signal to reduce the impact of ECG data imbalance on classification. Finally, a convolutional neural network (CNN) and sequence-to-sequence (Seq2Seq) classification model with attention mechanism based on bidirectional long short-term memory (Bi-LSTM) as the codec is used for arrhythmias classification, and the model can give corresponding weight according to the importance of heartbeat features and can improve the ability to extract and filter the spatiotemporal features of heartbeats. In the classification of five heartbeat types, including normal beat (N), supraventricular ectopic beat (S), ventricular ectopic beat (V), fusion beat (F), and unknown beat (Q), the proposed method achieved the overall accuracy (OA) value and Macro- $F1$ score of 99.28% and 95.70%, respectively, in public the Massachusetts Institute of Technology-Boston’s Beth Israel Hospital (MIT-BIH) arrhythmia database. These methods are helpful to improve the effectiveness and clinical reference value of computer-aided ECG automatic classification diagnosis.