Zidni, Robby and Sutedi, Sutedi (2025) PERBANDINGAN TINGKAT AKURASI ALGORITMA NEURAL NETWORK, SUPPORT VECTOR MACHINE, DAN RANDOM FOREST DALAM MEMPREDIKSI PENYAKIT DIABETES MELITUS MENGGUNAKAN MACHINE LEARNING. Skripsi thesis, Institut Informatika dan Bisnis Darmajaya.
![[img]](http://repo.darmajaya.ac.id/style/images/fileicons/text.png) |
Text
Cover.pdf Download (237kB) |
|
Text
Intisari.pdf Download (253kB) |
|
Text
Abstract.pdf Download (154kB) |
|
Text
Halaman Persetujuan.pdf Download (1MB) |
|
Text
Halaman Pengesahan.pdf Download (2MB) |
|
Text
Daftar isi.pdf Download (224kB) |
|
Text
Bab 1.pdf Download (277kB) |
|
Text
Bab 2.pdf Download (591kB) |
|
Text
Bab 3.pdf Download (414kB) |
|
Text
Bab 5.pdf Download (209kB) |
|
Text
Bab 4.pdf Download (1MB) |
|
Text
Cover.pdf Download (237kB) |
|
Text
Lembar pernyataan.pdf Download (61kB) |
|
Text
Halaman Persetujuan.pdf Download (1MB) |
|
Text
Halaman Pengesahan.pdf Download (2MB) |
|
Text
Halaman persembahan.pdf Download (96kB) |
|
Text
Riwayat hidup.pdf Download (146kB) |
|
Text
Halaman persembahan.pdf Download (96kB) |
|
Text
Motto.pdf Download (93kB) |
|
Text
Intisari.pdf Download (253kB) |
|
Text
Abstract.pdf Download (154kB) |
|
Text
Prakata.pdf Download (97kB) |
|
Text
Daftar isi.pdf Download (224kB) |
|
Text
Daftar gambar.pdf Download (231kB) |
|
Text
Daftar tabel.pdf Download (142kB) |
|
Text
Daftar gambar.pdf Download (231kB) |
|
Text
Bab 1.pdf Download (277kB) |
|
Text
Bab 2.pdf Download (591kB) |
|
Text
Bab 3.pdf Download (414kB) |
|
Text
Bab 4.pdf Download (1MB) |
|
Text
Bab 5.pdf Download (209kB) |
|
Text
Daftar pustaka.pdf Download (176kB) |
Abstract
Diabetes is often referred to as a silent killer because its symptoms are not immediately apparent and are frequently only discovered after serious complications arise. This contributes to the continuously increasing prevalence of diabetes. The ability to predict an individual’s likelihood of developing diabetes quickly and accurately is expected to help reduce its growing prevalence. This study aimed to compare the accuracy levels of Neural Networks, Random Forests, and Support Vector Machine algorithms in predicting diabetes. The data used in this study were obtained from a public dataset on Kaggle, consisting of 100,000 records with nine attributes: gender, age, hypertension, heart disease, smoking history, BMI, HbA1c level, blood glucose level, and diabetes. The preprocessing stages included resampling, normalization, encoding, and data splitting. Evaluation metrics used in this study were accuracy, precision, recall, and F1-score. The analysis concluded that the accuracy values for the Neural Network, Random Forest, and Support Vector Machine algorithms were 88.29%, 90.2%, and 88.76%, respectively. Therefore, the Random Forest algorithm yielded the highest accuracy among the three. Keywords: Comparison, Prediction, Algorithm, Machine Learning
| Item Type: | Thesis (Skripsi) |
|---|---|
| Subjects: | Ilmu Komputer eSkripsi |
| Divisions: | Skripsi/TA & PKPM/KP - Fakultas Ilmu Komputer > Sistem Informasi |
| Depositing User: | Zidni Robby Rodhiya |
| Date Deposited: | 10 Sep 2025 03:35 |
| Last Modified: | 10 Sep 2025 03:35 |
| URI: | http://repo.darmajaya.ac.id/id/eprint/22647 |
Actions (login required)
 |
View Item |