Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

Improving Classifier Performance Using Particle Swarm Optimization on Heart Disease Detection

Rektorat UDINUS 2018 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2018
Goals
Record
f18f5895-122c-4e86-ac2a-149a4dbddf85
Published
2026-10-30

Universitas Dian Nuswantoro conducted a study on improving classifier performance for heart disease detection through particle swarm optimization. The activity used a public heart disease dataset from the UCI Machine Learning Repository. The dataset was used in the context of data mining and clinical disease diagnosis. The source describes data mining as an evolving technology that extracts information from very large datasets to generate useful knowledge.

The study proposed improvements to Naive Bayes, Decision Tree, and k-Nearest Neighbor classifiers for heart disease detection. Particle swarm optimization was used to select significant features as data entries for the classification phase. This feature-selection approach was intended to improve classifier performance. The experimental results reported that the built model increased the accuracy of heart disease detection when prime features were selected. The source states that the main objective and advantage of the study were to provide a significant improvement in classifier performance, resulting in correct diagnosis on time.

This UDINUS activity relates to the stated goal through its focus on health research and heart disease detection. The source identifies the dataset, data-mining context, classifiers, feature-selection method, classification phase, and reported experimental finding. It does not provide details about the activity's date, location, institutional programme, implementation, or outcomes beyond the reported model performance. Accordingly, the activity is presented as UDINUS research applying particle swarm optimization to classifier improvement for heart disease detection.

Reference https://www.scopus.com/pages/publications/85060061285?origin=resultslist