Ariansyah, Fery Almas (2024) Klasifikasi Pneumonia Menggunakan Metode LBP-GLCM Dan Naive Bayes. Undergraduate thesis, UPN Veteran Jawa Timur.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
20081010017-cover.pdf Download (773kB) |
|
Text (Bab 1)
20081010017-bab1.pdf Download (68kB) |
|
Text (Bab 2)
20081010017-bab2.pdf Restricted to Repository staff only until 3 June 2028. Download (368kB) |
|
Text (Bab 3)
20081010017-bab3.pdf Restricted to Repository staff only until 3 June 2028. Download (469kB) |
|
Text (Bab 4)
20081010017-bab4.pdf Restricted to Repository staff only until 3 June 2028. Download (1MB) |
|
Text (Bab 5)
20081010017-bab5.pdf Download (13kB) |
|
Text (Daftar Pustaka)
20081010017-daftarpustaka.pdf Download (158kB) |
|
Text (Lampiran)
20081010017-lampiran.pdf Restricted to Repository staff only until 3 June 2028. Download (499kB) |
Abstract
This study evaluates the effectiveness of the Local Binary Pattern (LBP) - Gray Level Co-occurrence Matrix (GLCM) feature extraction method as well as the Naive Bayes classification algorithm to identify lung X-Ray images that indicate pneumonia. The main challenge is to improve the accuracy of disease diagnosis through X-Ray image analysis. The purpose of this study is to apply an effective method to classify chest X-ray images into pneumonia and normal types using LBP-GLCM feature extraction and Naive Bayes method. Furthermore, this study aims to determine the performance of pneumonia classification in chest X-ray images using the LBP-GLCM method and the Naive Bayes method. This study was conducted using a data set of lung X-ray images, focusing on. 100 and 500 images, as well as variations in the number of test data. The experimental results show that the highest accuracy is found in the 30% test variant, with an accuracy rate of 93% in the 100 image dataset and 86% in the 500 image dataset. In conclusion, the LBP-GLCM and Naive Bayes methods can significantly contribute to medical diagnosis with a satisfactory accuracy rate, which can help improve the efficiency of daily clinical practice. Translated with DeepL.com (free version)
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | T Technology > T Technology (General) | ||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Informatics | ||||||||||||
| Depositing User: | Fery Almas Ariansyah (Fery) | ||||||||||||
| Date Deposited: | 04 Jun 2024 02:49 | ||||||||||||
| Last Modified: | 04 Jun 2024 02:49 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/23855 |
Actions (login required)
 |
View Item |