Nur Afiifah Az-Zahra, . (2024) KLASIFIKASI TIPE PENYAKIT DIABETES MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE (SVM). Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (12kB) |
|
Text
AWAL.pdf Download (824kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (31kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (400kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (183kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (579kB) |
|
Text
BAB 5.pdf Download (11kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (241kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (200kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (723kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (32kB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (554kB) |
Abstract
Diabetes mellitus is a chronic disease that has become one of the leading causes of death in Indonesia. In 2019, diabetes was the third highest cause of death in Indonesia, with approximately 57.42 deaths per 100,000 population. The prevalence of diabetes cases in Indonesia has increased significantly, including a seventy-fold increase in prevalence among children since 2010. Given the serious impact on public health, accurate classification between type 1 and type 2 diabetes is essential to prevent adverse effects. The use of Support Vector Machine (SVM) algorithms in machine learning offers a solution for fast and accurate classification based on clinical data. This study aims to determine the performance of the SVM algorithm in classifying diabetes based on patient data from Puskesmas Pekayon Jaya, Bekasi, West Java. The results show that using SMOTE and hyperparameter tuning significantly improves model accuracy. The best experiment showed training data accuracy of 99%, validation accuracy of 89%, and test accuracy of 91%, with optimal parameters C = 1000, Gamma = scale, and kernel RBF. In conclusion, the SMOTE method and hyperparameter tuning are effective in handling data imbalance and improving model accuracy. Proper data partitioning also positively impacts accuracy.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2010511085] [Pembimbing 1: Ika Nurlaili Isnainiyah] [Pembimbing 2: Nurul Afifah Arifuddin] [Penguji 1: Indra Permana Solihin] [Penguji 2: Muhammad Adrezo] |
| Uncontrolled Keywords: | Support Vector Machine, Diabetes, Classification, SMOTE, Imbalance Dataset |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | NUR AFIIFAH AZ-ZAHRA |
| Date Deposited: | 29 Aug 2024 07:40 |
| Last Modified: | 29 Aug 2024 07:40 |
| URI: | http://repository.upnvj.ac.id/id/eprint/31709 |
Actions (login required)
 |
View Item |