PENERAPAN PARTICLE SWARM OPTIMIZATION (PSO) UNTUK SELEKSI ATRIBUT DALAM MENINGKATKAN AKURASI PREDIKSI DIAGNOSIS PENYAKIT HEPATITIS DENGAN METODE ALGORITMA C4.5

Lis Saumi Ramdhani

Abstract


Hepatitis is a chronic disease that is chronic, at which time the person has been infected, the condition is
still healthy and not showing signs and symptoms Typical but transmission continues to run. So from that
process are still many people who do not recognize the symptoms of hepatitis. There have been many
researchers who conducted the study to predict hepatitis, one of which applies the method C4.5. In this
research, C4.5 algorithm optimization using Particle Swarm Optimization to improve prediction
accuracy. After testing the two models namely the algorithm C4.5 and C4.5 Optimization using Particle
Swarm Optimization, the results obtained are algorithms. Thus obtained test using values obtained C4.5
where accuracy is 79,33% and the AUC value is 0,655, while Optimization testing using C4.5Particle
Swarm Optimization with accuracy values obtained 85,00% and AUC values were 0,718 at the level of
diagnosis fair classification. So that the two methods have different levels of accuracy that is equal to
5,67% and the difference in AUC value of 0,063.



DOI: https://doi.org/10.31294/swabumi.v4i1.1011

INDEXING

 

    P-ISSN : 2355-990X                       E-ISSN: 2549-5178

                     

 

Dipublikasikan oleh LPPM Universitas Bina Sarana Informatika

Jl. Kramat Raya No.98, Kwitang, Kec. Senen, Kota Jakarta Pusat, DKI Jakarta 10450
Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License