Evaluation of Electrocardiogram Signals Classification Using CNN, SVM, and LSTM Algorithm: A review

Abstract

The non-stationary signals of Electrocardiogram (ECG) are widely utilized to assess heartbeat rate and tune the major goal of this study is to give an overview of ECG classification Machine learning and neural network methods are employed. Furthermore, the major stage in ECG classification is feature extraction, which is used to identify a group of important characteristics that may achieve the highest level of accuracy. The optimization approach is used in conjunction with classifiers to get the optimal value for Its discriminant purpose was best served by using classifying parameters that best fit the discriminant purpose. Finally, this study evaluates the signal classification for ECG heartbeat using a Convolution Neural Network (CNN), Support Vector Machine (SVM), and Long Short Term Memory (LSTM), compare between them and present that the best method is LSTM for these cases based on the dataset. The author is certain that this study would be beneficial to researchers, scientists, and Engineers who operate in this field to discover relevant references.