Sheva NaufalRifqi, . (2022) OPTIMASI RANDOM FOREST UNTUK DIAGNOSIS PENYAKIT GINJAL KRONIK DENGAN MENGGUNAKAN PARTICLE SWARM OPTIMIZATION. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (47kB) |
|
Text
AWAL.pdf Download (812kB) |
|
Text
BAB 1.pdf Download (124kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (229kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (211kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (300kB) |
|
Text
BAB 5.pdf Download (110kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (117kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (127kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (202kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (9MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (364kB) |
Abstract
Chronic Kidney Disease (CKD) is one of the diseases whose sufferers continue to increase on a global scale. This chronic kidney disease causes the ability of the electrolyte fluid in the body to not be able to maintain metabolism in the body properly. The causes of this disease continue to increase because it is highly progressive and irreversible. To overcome this, we need a method that is fast and accurate in diagnosing kidney disease, so that the treatment of the sufferer can be handled quickly. One of the appropriate methods in predicting the diagnosis of chronic kidney disease is to build a classification model using various algorithms, one of which is by using a random forest. This Random Forest algorithm is widely used in building classification models, but in its application other methods are needed to optimize the algorithm to be more accurate. To overcome this problem, the Particle Swarm Optimization algorithm is used to perform feature selection on data that has many features. The results of the evaluation in performance testing using Particle Swarm Optimization in classifying CKD and Non CKD, the quality of accuracy is 99.167%. The choice of features has proven to be very effective in its optimization, because the selected features make the data more optimal for processing and produce better accuracy.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil:1810511080] [Pembimbing 1 : Anita Muliawati] [Pembimbing 2 : Desta Sandya Prasvita] [Penguji 1 : Yuni Widiastiwi] [Penguji 2 : Mayanda Mega Santoni] |
| Uncontrolled Keywords: | chronic kidney, random forest, particle swarm optimization |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | Sheva Naufalrifqi |
| Date Deposited: | 01 Aug 2022 06:19 |
| Last Modified: | 01 Aug 2022 06:19 |
| URI: | http://repository.upnvj.ac.id/id/eprint/19799 |
Actions (login required)
 |
View Item |