EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

MODEL HYBRID PSO, CORELATION FEATURE SELECTION DAN KNN UNTUK DETEKSI PENYAKIT JANTUNG

Dion Ikhzanza Rabbil, Taghfirul Azhima Yoga Siswa, Wawan Joko Pranoto

JIKO (Jurnal Informatika dan Komputer) · 20.06.2026 · 10 (2) · 262

DOI: 10.26798/jiko.v10i2.2662 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JIKO (Jurnal Informatika dan Komputer), online erschienen am 20.06.2026. Verfasst von Dion Ikhzanza Rabbil und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The high mortality rate caused by disorders of the cardiovascular system highlights the need for accurate early detection methods to support medical decision-making. This study aims to develop and evaluate a heart disease classification model using the K-Nearest Neighbor (KNN) algorithm optimized with Particle Swarm Optimization (PSO). In its implementation, the KNN algorithm employs the Manhattan distance parameter to measure the similarity between data instances. The dataset used in this study is a secondary heart disease dataset consisting of 302 records after preprocessing. The preprocessing stage includes data cleaning, numerical feature standardization using StandardScaler, and correlation-based feature selection to identify attributes that have significant relationships with the target variable. Model evaluation is conducted using a 10-fold cross-validation scheme and assessed using accuracy, precision, recall, and F1-score. The experimental results show that the baseline KNN model achieves an accuracy of 81.16%, while the PSO-optimized KNN model demonstrates improved performance with an accuracy of 82.81%, precision of 79.02%, recall of 92.13%, and an F1-score of 84.84%. These findings indicate that the application of PSO effectively enhances the performance and stability of the KNN algorithm in heart disease classification.

Zitieren

APA

Rabbil, D. I., Siswa, T. A. Y., & Pranoto, W. J. (2026). MODEL HYBRID PSO, CORELATION FEATURE SELECTION DAN KNN UNTUK DETEKSI PENYAKIT JANTUNG. JIKO (Jurnal Informatika dan Komputer), 10(2), 262. https://doi.org/10.26798/jiko.v10i2.2662

Vancouver

Rabbil DI, Siswa TAY, Pranoto WJ. MODEL HYBRID PSO, CORELATION FEATURE SELECTION DAN KNN UNTUK DETEKSI PENYAKIT JANTUNG. JIKO (Jurnal Informatika dan Komputer). 2026;10(2):262. doi:10.26798/jiko.v10i2.2662

BibTeX
@article{Rabbil2026,
  author = {Rabbil, Dion Ikhzanza and Siswa, Taghfirul Azhima Yoga and Pranoto, Wawan Joko},
  title = {MODEL HYBRID PSO, CORELATION FEATURE SELECTION DAN KNN UNTUK DETEKSI PENYAKIT JANTUNG},
  journal = {JIKO (Jurnal Informatika dan Komputer)},
  year = {2026},
  volume = {10},
  number = {2},
  pages = {262},
  doi = {10.26798/jiko.v10i2.2662}
}
Kostenlos starten →