Maulana Luthfi, . (2023) PERBANDINGAN KINERJA ALGORITMA KLASIFIKASI UNTUK PREDIKSI PENYAKIT TIROID. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (68kB) |
|
Text
AWAL.pdf Download (884kB) |
|
Text
BAB I.pdf Download (80kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (179kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (161kB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (568kB) |
|
Text
BAB V.pdf Download (71kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (69kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (23kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (7MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (4MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (409kB) |
Abstract
Thyroid is a very important part of the body for humans. Thyroid disorders are often difficult to detect because their symptoms are very similar to those of other diseases. As a result, patients often do not realize they have problems with the thyroid gland. This study aims to predict thyroid disease using thyroid disease data from the Garavan Institute and J. Ross Quinlan. The data will be processed using the data mining process using the classification method. The classification methods used in this study are the K-Nearest Neighbor, Naïve Bayes, Decision Tree, and Random Forest algorithms. This study also uses undersampling techniques to overcome the unequal number of classes. The output of the system is a performance measure that is presented in the form of a proportion based on the values in the confusion matrix of each algorithm against thyroid disease data. Based on the results obtained, the performance of the Random Forest algorithm obtained the best results compared to other algorithms. Random Forest got an accuracy proportion of 95.16%, while KNN, Naïve Bayes, and Decision Tree only got an accuracy proportion of 87.10%, 93.55% and 90.32%. However, when viewed from the training process time and the testing model, Decision Tree has the fastest processing time compared to other algorithms. Decision Tree takes 0.0091 seconds, while KNN, Naïve Bayes, and Random Forest takes 0.0273 seconds, 0.0103 seconds and 0.0162 seconds. Therefore if you want to get the maximum value, you can use the Random Forest algorithm. However, if you want to use a faster processing time, you can use the Decision Tree algorithm to predict thyroid disease sufferers.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 1910511078] [Pembimbing: Didit Widiyanto] [Penguji 1: Bayu Hananto] [Penguji 2: Ika Nurlaili Isnainiyah] |
| Uncontrolled Keywords: | Thyroid, Data Mining, K-Nearest Neighbor, Naïve Bayes, Decision Tree, Random Forest, Undersampling, Confusion Matrix, Performance Measure |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | Maulana Luthfi |
| Date Deposited: | 21 Aug 2023 04:04 |
| Last Modified: | 21 Aug 2023 04:04 |
| URI: | http://repository.upnvj.ac.id/id/eprint/25121 |
Actions (login required)
 |
View Item |