Fahrudin, Gantar Fitra (2024) IMPROVMENT MODEL MACHINE LEARNING KLASIFIKASI SUPPORT VECTOR MACHINE PADA DIAGNOSIS PENYAKIT JANTUNG. Diploma thesis, Politeknik Negeri Sriwijaya.
|
Text
cover.pdf Download (273kB) | Preview |
|
![[img]](http://eprints.polsri.ac.id/style/images/fileicons/text.png) |
Text (BAB I PENDAHULUAN)
bab 1.pdf Restricted to Repository staff only Download (86kB) | Request a copy |
|
|
Text (BAB II TINJAUAN PUSTAKA)
bab 2.pdf Restricted to Repository staff only Download (147kB) | Request a copy |
|
|
Text (BAB III METODOLOGI PENELITIAN)
bab 3.pdf Restricted to Repository staff only Download (122kB) | Request a copy |
|
|
Text (Bab IV Pembahasan)
bab 4.pdf Restricted to Repository staff only Download (461kB) | Request a copy |
|
|
Text (BAB V KESIMPULAN)
bab 5.pdf Restricted to Repository staff only Download (6kB) | Request a copy |
|
|
Text
dapus.pdf Restricted to Repository staff only Download (88kB) | Request a copy |
Abstract
Heart disease is one of the serious health problems that cause a high risk of death worldwide. Triggering factors include high cholesterol, diabetes and high blood pressure. Therefore, early prediction of heart disease is a very important first step to reduce the risk of death. This study proposes a new heart disease classification model based on Support Vector Machine (SVM) algorithm to improve disease detection performance. To reduce errors in diagnosis accuracy, we apply feature selection and grid search techniques. The performance of the improved model is validated by comparing it with the simple model using confusion matrix. The improved model achieved an accuracy of 96.56%, showing an 8.91% improvement in accuracy over the previous model which only achieved an accuracy rate of 87.65%. In addition, the number of features used was reduced from 14 to 8, thus reducing the computational burden from 100% to about 32%. These results show that the improved SVM offers better performance and is more efficient than other research methods in heart disease classification
| Item Type: | Thesis (Diploma) |
|---|---|
| Uncontrolled Keywords: | Support Vector Machine; Supervised Learning; Clasification; Heart Disease. |
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisions: | Telecommunication Engineering > Undergraduate Theses |
| Depositing User: | Mr Bambang Anthony |
| Date Deposited: | 22 Jul 2026 02:21 |
| Last Modified: | 22 Jul 2026 02:21 |
| URI: | http://eprints.polsri.ac.id/id/eprint/22276 |
Actions (login required)
 |
View Item |
