Detection of Heart Abnormalities Based On ECG Signal Characteristics using Multilayer Perceptron with Firefly Algorithm-Simulated Annealing

Abstract

Heart disease is one of the causes of death worldwide. Therefore, detecting heart disease is very important to reduce the increased mortality rate. One of the methods used to detect the abnormalities or disorders of the heart is to use computer assistance to determine the characteristics of an electrocardiogram. Electrocardiogram (ECG) is a test that detects and records the activity of the heart through small metal electrodes attached to the skin of one's chest, arms and legs. This test shows how fast the heart beats and whether the rhythm is stable or not. The purpose of this thesis is to apply a multi-layer perceptron model with firefly algorithm and simulated annealing in detecting cardiac abnormalities based on the ECG signal characteristics. The initial step of this research is image processing. The stages of ECG image processing are grayscale, thresholding, edge detection, segmentation and normalization processes. The results of this image processing are used as input matrices in the perceptron multilayer network training using firefly algorithm and simulated annealing. In the training process, we will get optimal weights and biases for validation tests on test data. The training data in this thesis uses 20 ECG images and in the validation test process uses 10 ECG images. The validation results in the validation test show that the accuracy in detecting heart abnormalities based on the characteristics of ECG signals using multi- layer perceptron with firefly algorithm and simulated annealing is 100%.