Ballali Ebbi, Hammada (2024) Development of a Bagging-based Ensemble Model for ECG Classification. Masters thesis, University of Wales Trinity Saint David.
|
Text
Ebbi_Hammada_MSc_Thesis.pdf - Accepted Version Available under License CC-BY-NC-ND Creative Commons Attribution Non-commercial No Derivatives. Download (1MB) | Preview |
Abstract
The importance of computational methods, particularly the application of machine learning models in cardiovascular disease classification and recognition, is rapidly growing. CNN, LSTM, and Transformer models have demonstrated in various studies that, when implemented with robust architectures and supported by ample datasets, they can achieve highly accurate results. This study explores the application of bagging techniques to three base models: CNN, LSTM, and Transformer, for both binary classification on the PTB dataset and multiclass classification on the MITBIH datasets. The findings indicate that the CNN model outperforms the other two models under the selected parameters and across ten epochs achieving 0.95 for binary classification and 0.96 for multiclass classification. Additionally, the use of bagging techniques results in a slight deterioration, likely due to the weaker performance of the Transformer and LSTM models.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisions: | Theses and Dissertations > Masters Dissertations |
| Depositing User: | Victoria Hankinson |
| Date Deposited: | 09 Jan 2025 09:21 |
| Last Modified: | 09 Jan 2025 09:21 |
| URI: | https://repository.uwtsd.ac.uk/id/eprint/3304 |
Administrator Actions (login required)
 |
Edit Item - Repository Staff Only |