Jinhee Kwak  Jaehee Jung

10.5626/JOK.2023.50.11.947

ECG Arrhythmia data augmentation MIT-BIH

Due to its convenient accessibility, and crucial importance in arrhythmia diagnosis, ECG data is often considered in predicting heart disease. The MIT-BIH Arrhythmia dataset, which is widely utilized in research focused on arrhythmia analysis, is one of the contributing factors to heart disease. However, the dataset exhibits imbalanced arrhythmia classes due to variations in incidence rate. These imbalanced arrhythmia classes affect the performance of arrhythmia classification. To solve the imbalanced problem, this paper presents four distinct classification methods that utilize augmented data. These different augmentation techniques were compared and assessed alongside the VAE method in terms of classification performance. Furthermore, the CNN and the CNN-LSTM models were compared and analyzed in the context of the classification model. In conclusion, by applying VAE augmentation to train the balanced data and classifying the arrhythmia using the CNN, we achieved an accuracy of 98.9%. These results confirm the superior effectiveness of the proposed model compared to other existing arrhythmia classification models, particularly in terms of the sensitivity.