Optimization Neural Network With PCA And PSO On Heart Disease Classification
Andre Tri Saputra, Bagus Prindo Sugiharto Putro, Wicaksono Agung Saputro, Muljono Muljono · 2020 International Seminar on Application for Technology of Information and Communication (iSemantic) · 2020
Heart disease is disease caused by heart disease that causes abnormalities, forms of abnormalities such as heart rhythm, heart valves, minor or congenital abnormalities from birth and the resulting blockage of blood vessels is energy supply. Researchers here use classification to help predict heart disease. The results of data classification in the evaluation use the ROC curve and Confusion Matrix to determine the level of accuracy using Neural Network algorithms with PCA and PSO. PCA (Principal Component Analysisis) extraction from variable to reduce the variable without loss information contained in the original or original data while (Particle Swarm Optimization) is an optimization technique that is inspired by the behavior of flocks of birds or fish.. Its characteristics are generally simple concepts, efficient calculations, and easy implementation. for optimization dimensions with the results of the AUC ROC curve of 98.05% of 0.977, it can be used according to the needs of the Neural Network algorithm with PCA and PSO optimization has good results in predicting heart disease patients.