Application of deep neural network with stacked denoising autoencoder for ECG signal classification
Applying deep neural networks with stacked denoising autoencoders (SDAEs) for ECG signal classification presents a promising approach for improving the accuracy of arrhythmia diagnosis. This study aims to develop a robust model that enhances the classification of ECG signals by effectively denoising...
Saved in:
| Published in: | Journal of Intelligent Decision Support System (IDSS) Vol. 7; no. 2; pp. 173 - 187 |
|---|---|
| Main Authors: | , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
30.06.2024
|
| ISSN: | 2721-5792, 2721-5792 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Applying deep neural networks with stacked denoising autoencoders (SDAEs) for ECG signal classification presents a promising approach for improving the accuracy of arrhythmia diagnosis. This study aims to develop a robust model that enhances the classification of ECG signals by effectively denoising the input data and extracting rich feature representations. The research employs a method involving data preprocessing, feature extraction using SDAEs, and classification with a deep neural network (DNN) validated on the MIT-BIH Arrhythmia Database. The results demonstrate that the proposed model achieves an impressive accuracy of 98.91%, significantly outperforming traditional machine learning methods. The implications of this research are substantial, offering a reliable and automated tool for arrhythmia diagnosis that can be utilized in clinical settings to improve patient care. The study highlights the model's potential for real-time clinical application, although further validation on more extensive and diverse datasets is necessary to confirm its generalizability and robustness. This research contributes to the field by integrating advanced SDAEs with deep learning, paving the way for more accurate and efficient ECG signal classification systems |
|---|---|
| ISSN: | 2721-5792 2721-5792 |
| DOI: | 10.35335/idss.v7i2.247 |