Detecting atrial fibrillation from ECG signal using hybrid convolutional neural network with ant-lion optimization

Atrial fibrillation (AF) is the most prevalent cardiac arrhythmia and it is considered one of the most important risk factors for death, stroke, hospitalization, and heart failure. It is possible to detect AF by analyzing the electrocardiogram (ECG) of patients. To work on clean signals and reduce errors resulting from noise, we have used a Butterworth filter. The short-term Fourier transform was used to analyze ECG segments to obtain ECG spectrogram images. Convolutional neural network (CNN) models have been proposed for improving the automatic detection of AF. The number of convolutional layers varies in different CNN models, and as the model becomes deeper, more hyperparameters are added. So in this article, the Ant-Lion optimization algorithm was used to optimize hyperparameters of CNN. The results of experiments performed on the MIT-BIH AF database showed that the proposed method achieved 99.72%, 98.95%, and 99.4% for sensitivity, specificity, and accuracy, respectively, so the proposed method outperforms the deep CNNs. Hence, the proposed method is an accurate and efficient method for the detection of AF.