Ventricular Ectopic beats detection based wavelet scattering network and ensemble bagged trees for smart medical systems.

This paper introduces an automated method for classifying electrocardiograms (ECG) with the aim of enhancing both accuracy and speed in interpreting ECG results, thus contributing to the early detection of cardiovascular diseases (CVD). The model in this study employs a deep feature extraction technique combined with Ensemble Bagged Trees (EBT) to identify Ventricular Ectopic Beats (VEB). Data is sourced from the MIT-BIH Arrhythmia database, and model performance is assessed through ten-fold cross-validation. On the validation dataset, the proposed model achieves an accuracy of 98.24% and an F1 score of 97.66%. When independently tested on the MIT-BIH dataset, it demonstrates an accuracy of 98.31% and an F1 score of 89.22%. These outcomes highlight the model's ability to attain exceptional accuracy and F1 scores on both validation and testing datasets. [ABSTRACT FROM AUTHOR]