. Detection of healthy and unhealthy ECG signal using optimized convolutional neural network

Subject Areas : journal of Artificial Intelligence in Electrical Engineering

mohammad fatehi ¹ , mehdi khajooee ² , nahid adlband ³ , mohammad moradi ⁴

1 - 4. Department of Biomedical Engineering, Kazerun Branch, Islamic Azad University, Kazerun, Iran.
2 - 2. Department of Biomedical Engineering, Kazerun Branch, Islamic Azad University, Kazerun, Iran
3 - 1. Department of Electrical Engineering, Kazerun Branch, Islamic Azad University, Kazerun, Iran
4 - Department of Electrical Engineering, chamran Branch, chamran University, Kerman, Iran

Received: 2022-07-27 Accepted : 2022-09-05 Published : 2022-12-01

Keywords: heart diseases, deep learning, ECG signal, optimized convolutional neural network,

Abstract :

According to the information of the World Health Organization, today heart diseases are considered the most important threat to humans and are the first cause of death in the world. According to the latest global statistics, 46% of deaths are related to the heart. According to reports and research, a large number of causes of death are caused by heart diseases, while 25% of cases are reversible. Correct and timely diagnosis of patients with acute heart problems can largely prevent sudden death and further problems.Due to the fact that recording an electrocardiogram is inexpensive and fruitful, the use of an electrocardiogram can help a lot in many heart diseases and other diseases.Deep learning is one of the new methods with high accuracy in diagnosis and classification, which is based on the convolutional neural network.Convolutional neural networks have a very high processing and training time, which can be optimized and reduced in order to reduce the time, so that acceptable results can be obtained with high accuracy.In this article, using the optimized convolutional neural network, the healthy and unhealthy signal was obtained with 99.9% accuracy and 99.7% sensitivity with 10-fold cross-validation.According to the obtained results, it can be said that the proposed method has the ability to separate healthy and unhealthy signals with acceptable accuracy.