PENERAPAN METODE SUPPORT VECTOR MACHINE BERBASIS PARTICLE SWARM OPTIMIZATION UNTUK PREDIKSI PENYAKIT JANTUNG
| Main Author: | Nurajizah, Siti |
|---|---|
| Format: | Article info application/pdf Journal |
| Bahasa: | eng |
| Terbitan: |
PPPM STMIK Nusa Mandiri
, 2013
|
| Online Access: |
http://ejournal.nusamandiri.ac.id/ejurnal/index.php/techno/article/view/116 http://ejournal.nusamandiri.ac.id/ejurnal/index.php/techno/article/view/116/112 |
Daftar Isi:
- Heart disease is one of the world's deadliest diseases. Heart disease occurs due to narrowing or blockage of the coronary arteries caused by the buildup of fatty substances (cholestero, triglycerides), more and more and accumulate beneath the inner lining of the arteries. Several studies have been conducted to diagnose patients is not yet known but the exact method to predict heart disease. This study uses support vector machine and support vector machine -based method particle swarm optimization to get the rules for the prediction of cardiovascular disease and provide a more accurate value of the result accuracy. After testing two models of Support Vector Machine and Support Vector Machine -based Particle Swarm Optimization and the results by using Support Vector Machine get accuracy values 81.85 % and AUC values 0.899, while testing with Support Vector Machine -based particle swarm optimization to get accuracy values 88.61 % and AUC values 0.919. Both of these methods have difference values of 6.76 % and the difference in AUC value of 0.02.