Key result
A model based on discrete wavelet transform and a support vector machine classifier achieved a best classification accuracy of 87.50% for differentiating normal and abnormal ECG signals.
Why the study?
Does a model using discrete wavelet transform and a support vector machine classifier improve the classification accuracy of normal versus abnormal ECG signals?
Does a model using discrete wavelet transform and a support vector machine classifier improve the classification accuracy of normal versus abnormal ECG signals?
A machine learning model combining discrete wavelet transform for feature extraction and a support vector machine classifier can accurately distinguish between normal and abnormal ECG signals.
Offers feasible ECG classification support; leaves open prospective validation before clinical use.
The electrocardiography allowed us to make a diagnosis of several cardiovascular diseases by representing the electrical activity of the heart over time; this representation is called the electrocardiogram (ECG) signal. In this study we have proposed a model based on the processing of the ECG signal by the wavelet decomposition using discrete wavelet transform (DWT). This decomposition firstly makes it possible to denoise the signal then to extract the statistical features from the approximation coefficients of the denoised signal and finally to classify the data obtained in a support vector machine (SVM) classifier with cross validation for more credibility. After having tested this model with different mother wavelets at different scales, the accuracies at the fourth scale are high and the best accuracy obtained is 87.50%.
No takes yet. Share an insight, caveat, or question.
Toulni et al. (2021) studied Arrhythmia (n=48). Discrete wavelet transform (DWT) and support vector machine (SVM) classifier vs. Other wavelets and classifiers was evaluated on Classification accuracy. A model based on discrete wavelet transform and a support vector machine classifier achieved a best classification accuracy of 87.50% for differentiating normal and abnormal ECG signals.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: