Sanusi, Anwar (2023) Penerapan Algoritma Adaboost Pada C50 Untuk Peningkatan Kinerja Klasifikasi Penyakit Liver. Undergraduate thesis, UPN Veteran Jawa Timur.
|
Text (COVER)
19081010068.-cover.pdf Download (2MB) | Preview |
|
|
Text (BAB 1)
19081010068.-bab1.pdf Download (681kB) | Preview |
|
![[img]](http://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (BAB 2)
19081010068.-bab2.pdf Restricted to Registered users only until 24 July 2025. Download (981kB) |
|
|
Text (BAB 3)
19081010068.-bab3.pdf Restricted to Registered users only until 24 July 2025. Download (1MB) |
|
|
Text (BAB 4)
19081010068.-bab4.pdf Restricted to Registered users only until 24 July 2025. Download (1MB) |
|
|
Text (BAB 5)
19081010068.-bab5.pdf Download (182kB) | Preview |
|
|
Text (DAFTAR PUSTAKA)
19081010068.-daftarpustaka.pdf Download (540kB) | Preview |
Abstract
The liver is one of the vital organs important for humans. It plays a crucial role in the body's metabolism, such as regulating hormone cycles, detoxification, and neutralizing poisons, as well as regulating the structure and composition of the blood, among others. Liver disease is a common ailment that frequently occurs worldwide. Often, this disease develops without preceding specific symptoms, a condition known as asymptomatic. Therefore, liver disease is often referred to as a 'silent killer.' As a result, the process of diagnosing and treating liver disease must be done quickly and accurately. Data mining technology can be beneficial in swiftly detecting liver disease from laboratory diagnosis results. One suitable classification algorithm that can be used is the C50 algorithm. However, the C50 algorithm may experience overfitting on complex medical data, necessitating a boosting process using AdaBoost. The AdaBoost algorithm can make the C50 algorithm more susceptible to overfitting. Another advantage of the AdaBoost algorithm is its ability to handle imbalanced datasets in target labels. After conducting research, it was found that the C50 algorithm can classify with an accuracy of 71.72%, and when boosted by AdaBoost, its accuracy can be maximized to 76.55%.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | T Technology > T Technology (General) | ||||||||||||
| Divisions: | Faculty of Computer Science | ||||||||||||
| Depositing User: | Anwar Sanusi | ||||||||||||
| Date Deposited: | 03 Aug 2023 02:09 | ||||||||||||
| Last Modified: | 03 Aug 2023 02:09 | ||||||||||||
| URI: | http://repository.upnjatim.ac.id/id/eprint/16172 |
Actions (login required)
 |
View Item |