Comparative study of time-frequency transformation methods for ECG signal classification

In this study, we highlighted the growing need for automated electrocardiogram (ECG) signal classification using deep learning to overcome the limitations of traditional ECG interpretation algorithms that can lead to misdiagnosis and inefficiency. Convolutional neural networks (CNN) application to ECG signals is gaining significant attention owing to their exceptional image-classification capabilities. However, we addressed the lack of standardized methods for converting 1D ECG signals into 2D-CNN-compatible input images by using time-frequency methods and selecting hyperparameters associated with these methods, particularly the choice of function. Furthermore, we investigated the effects of fine-tuned training, a technique where pre-trained weights are adapted to a specific dataset, on 2D-CNNs for ECG classification. We conducted the experiments using the MIT-BIH Arrhythmia Database, focusing on classifying premature ventricular contractions (PVCs) and abnormal heartbeats originating from ventricles. We employed several CNN architectures pre-trained on ImageNet and fine-tuned using the proposed ECG datasets. We found that using the Ricker Wavelet function outperformed other feature extraction methods with an accuracy of 96.17%. We provided crucial insights into CNNs for ECG classification, underscoring the significance of fine-tuning and hyperparameter selection in image transformation methods. The findings provide valuable guidance for researchers and practitioners, improving the accuracy and efficiency of ECG analysis using 2D-CNNs. Future research avenues may include advanced visualization techniques and extending CNNs to multiclass classification, expanding their utility in medical diagnosis.