Classification Method of ECG Signals Based on RANet

Electrocardiograms (ECG) are an important source of information on human heart health and arewidely used to detect different types of arrhythmias.

With the advancement of deep learning, end-to-end ECG classification models based on neuralnetworks have been developed. However, deeper network layers lead to gradient vanishing. Moreover, differentchannels and periods of an ECG signal hold varying significance for identifying different types of ECGabnormalities.

To solve these two problems, an ECG classification method based on a residual attention neural networkis proposed in this paper. The residual network (ResNet) is used to solve the gradient vanishing problem.Moreover, it has fewer model parameters, and its structure is simpler. An attention mechanism is added to focus onkey information, integrate channel features, and improve voting methods to alleviate the problem of dataimbalance.

Experiments and verifications are conducted using the PhysioNet/CinC Challenge 2017 dataset. Theaverage F1 value is 0.817, which is 0.064 higher than that for the ResNet model. Compared with the mainstreammethods, the performance is excellent.