Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

Optimization of a Neural Network with PCA and PSO for Heart Disease Classification

Rektorat UDINUS 2020 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2020
Goals
Record
b4577e9a-4d06-44d0-9559-f431f5e1f925
Published
2026-10-30

Universitas Dian Nuswantoro conducted an activity on heart disease classification using a Neural Network algorithm optimized with Principal Component Analysis (PCA) and Particle Swarm Optimization (PSO). The activity involved UDINUS researchers Saputra, Andre; Prindo Sugiharto Putro, Bagus; Saputro, Wicaksono Agung; and Muljono, Muljono. The activity addressed heart disease, which is described in the source as causing abnormalities, including abnormalities in heart rhythm and heart valves, minor or congenital abnormalities from birth, and blockage of blood vessels related to energy supply.

UDINUS used classification to help predict heart disease. PCA was used for extraction from variables to reduce the variables without loss of information contained in the original data. PSO was used as an optimization technique inspired by the behavior of flocks of birds or fish. The source describes PSO as having simple concepts, efficient calculations, and easy implementation, and identifies it as being used for optimization dimensions. The classification results were evaluated using a Receiver Operating Characteristic (ROC) curve and a Confusion Matrix to determine the level of accuracy.

The reported result was an AUC ROC curve of 98.05% of 0.977. The source states that the result can be used according to the needs of the Neural Network algorithm and that the Neural Network algorithm with PCA and PSO optimization had good results in predicting heart disease patients. This activity therefore relates to the stated goal through the application of computational classification and evaluation to heart disease prediction. It frames UDINUS research as an activity using neural network classification, PCA extraction, PSO optimization, the ROC curve, and the Confusion Matrix for the stated health-related research purpose.

Reference https://www.scopus.com/pages/publications/85096845048?origin=resultslist