Method of arrhythmia classification on ECG signal

This paper proposes an improved arrhythmia classification method based on a convolutional neural network (CNN) applied to ECG signals. To improve the quality of classification, ECG signals were split into fragments containing three cardiac cycles with the current cardiac cycle in the center. The improved CNN architecture includes the addition of batch normalization layers, an additional convolutional layer, and a dropout layer, which improvs the model's accuracy. In addition, hyperparameters were optimized for new CNN architecture. The model was trained data of the MIT-BIH Arrhythmia Database to classify nine classes of ECG. The achieved average accuracy of 99.26% confirms the effectiveness of the proposed method in diagnosing various types of arrhythmias