Suchergebnisse

Electrocardiogram (ECG) classification plays a crucial role in the diagnosis and management of cardiovascular diseases. Deep learning-based approaches have shown promising results in automated ECG classification. However, the complexity of ECG signals, including variations in morphology, duration, and amplitude, poses significant challenges for existing deep learning models. In this regard, recent advancements in vision transformer models have shown remarkable performance in images processing and computer vision tasks. In this paper, we propose a deep vision transformer-based approach for ECG classification, which combines the power of convolutional neural networks and self-attention mechanisms. Our proposed model was tuned and enhanced by four hyper-parameters of the proposed model, it can effectively detect internally the main features of ECG images and achieve performance on benchmark ECG datasets. The proposed model can aid in the early detection and diagnosis of cardiovascular diseases, thus improving patient outcomes the final accuracy was 98.23% in dataset