Development of a Bagging-based Ensemble Model for ECG Classification

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.

Name dc:type.qualificationname

msc

Level dc:type.qualificationlevel

masters

Grantor dc:publisher.institution

University of Wales Trinity Saint David

Year dc:date.issued

2024

Author dc:creator

• Ballali Ebbi, Hammada

• TK Peirianneg drydanol. Peirianneg Niwclear Electronig

Dc Identifier Grantnumber

UWTSD

OAI identifier oai:identifier

oai:repository.uwtsd.ac.uk:3304