<![CDATA[This study is one of the initial approaches in implementing Backpropagation Neural Network for ECG signal classification. The condition of the human heart can be known based on the results of electrocardiogram medical records, so that with the results of electrocardiogram medical records it can be known whether the heart is normal or abnormal. Symptoms of abnormal heart disease in the heart often come suddenly. Early recognition of heart disease with further procedures and treatment can prevent an increase in the risk of fatal heart attacks. This study has a very important goal in an effort to detect and classify heart abnormalities more efficiently. By utilizing artificial neural networks (ANN) and backpropagation methods, it can utilize computing capabilities to analyze patterns in electrocardiogram (ECG) data. The results show that the classification of heart abnormalities with an epoch value of 2000, a learning rate of 0.01 with normal and abnormal targets, obtained the number of Hidden Neurons as many as 25, the number of weight patterns 44 and a mean squared error (MSE) value of with an accuracy of 0.61364 from 25 inputs.]]>
Copyrights © 2025
