<![CDATA[Heart disease is a major cause of death worldwide. Electrocardiogram (ECG) is a common method used to detect heart abnormalities. Analyzing ECG signals requires expertise and can be time-consuming. This study investigated the use of machine learning to classify ECG images for heart disease detection. The proposed method utilizes Gray Level Co-occurrence Matrix (GLCM) for feature extraction such as Dissimilarity, contrast, energy, ASM, homogeneity and Correlation. Meanwhile using Support Vector Machine (SVM) for the classification. We achieved an accuracy of 99.61% using this approach. The results suggest that the combination of GLCM and SVM can be a valuable tool for ECG image classification and potentially aid in early and accurate diagnosis of heart disease. Keywords: Electrocardiography, Support Vector Machine, Gray Level Co-Occurrence Matrix, Classification, Myocardial Infarction]]>
Copyrights © 2024
