Novita Damayanti, - (2024) IMPLEMENTASI METODE POHON KEPUTUSAN DENGAN ALGORITMA C4.5 DAN NAÏVE BAYES BERBASIS PARTICLE SWARM OPTIMIZATION DALAM MEMPREDIKSI PENYAKIT JANTUNG. S1 thesis, Universitas Pendidikan Indonesia.
![[img]](http://repository.upi.edu/style/images/fileicons/text.png) |
Text
S_MAT_2001332_Title.pdf Download (509kB) |
|
Text
S_MAT_2001332_Chapter1.pdf Download (170kB) |
|
Text
S_MAT_2001332_Chapter2.pdf Restricted to Staf Perpustakaan Download (456kB) |
|
Text
S_MAT_2001332_Chapter3.pdf Download (416kB) |
|
Text
S_MAT_2001332_Chapter4.pdf Restricted to Staf Perpustakaan Download (521kB) |
|
Text
S_MAT_2001332_Chapter5.pdf Download (154kB) |
|
Text
S_MAT_2001332_Appendix.pdf Restricted to Staf Perpustakaan Download (8MB) |
Abstract
Penyakit jantung merupakan salah satu penyakit tidak menular yang mematikan. Penelitian ini bertujuan untuk memprediksi penyakit jantung dengan melihat indikasi-indikasi apa saja yang dapat menyebabkan seseorang terkena penyakit jantung menggunakan metode pohon keputusan dengan algoritma C4.5 dan Naïve Bayes berbasis Particle Swarm Optimization. Penelitian dilakukan dengan menggunakan metodologi CRISP-DM (Cross Industry Standard Process for Data Mining). Data yang digunakan merupakan data hasil wawancara lembaga CDC (Centers of Disease Control and Prevention). Pada tahap awal akan dilakukan pemilihan atribut yang berpengaruh menggunakan Particle Swarm Optimization (PSO). Selanjutnya atribut terpilih akan dimodelkan dengan metode pohon keputusan dengan algoritma C4.5 dan Naïve Bayes. Selanjutnya dilakukan proses validasi dan evaluasi untuk mengukur kinerja model yang telah dibangun. Hasil penilitian menunjukkan bahwa kedua model memiliki nilai akurasi yang sama. Akan tetapi, nilai recall dan F1-Score dari model pohon keputusan dengan algoritma C4.5 lebih besar dibandingkan model Naïve Bayes. Dalam penelitian ini, model pohon keputusan lebih baik dalam memprediksi penyakit jantung dibandingkan model Naïve Bayes. Heart disease is one of the deadly non-contagious diseases. This study aims to predict heart disease by looking at what indications can cause a person to develop heart disease using the decision tree method with the C4.5 Algorithm and Naïve Bayes based on Particle Swarm Optimization. The research was conducted using the CRISP-DM (Cross Industry Standard Process for Data Mining) methodology. The data used is from interviews with CDC (Centers of Disease Control and Prevention) institutions. At the initial stage, the selection of influential attributes will be carried out using Particle Swarm Optimization (PSO). Furthermore, the selected attributes will be modeled with the decision tree method with C4.5 algorithm and Naïve Bayes method. Furthermore, the validation and evaluation process is carried out to measure the performance of the model that has been built. The results show that both models have the same accuracy value. However, the recall and F1-Score values of the decision tree model with the C4.5 algorithm are greater than the Naïve Bayes model. In this study, the decision tree model is better than Naïve Bayes model in predicting heart disease.
| Item Type: | Thesis (S1) |
|---|---|
| Additional Information: | https://scholar.google.com/citations?user=Z8pPO8kAAAAJ&hl=en ID SINTA Dosen Pembimbing: Khusnul Novianingsih: 258640 Ririn Sispiyati: 5986406 |
| Uncontrolled Keywords: | Penyakit Jantung, Pohon Keputusan, Algoritma C4.5, Naïve Bayes, Particle Swarm Optimization. Heart Disease, Decision Tree, C4.5 Algorithm, Naïve Bayes, Particle Swarm Optimization. |
| Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics R Medicine > RC Internal medicine |
| Divisions: | Fakultas Pendidikan Matematika dan Ilmu Pengetahuan Alam > Jurusan Pendidikan Matematika > Program Studi Matematika (non kependidikan) |
| Depositing User: | Novita Damayanti |
| Date Deposited: | 06 Sep 2024 01:42 |
| Last Modified: | 06 Sep 2024 01:42 |
| URI: | http://repository.upi.edu/id/eprint/123024 |
Actions (login required)
 |
View Item |