Qahtan Said, . (2020) IDENTIFIKASI TUBERKULOSIS PARU BERDASARKAN FOTO SINAR-X THORAX MENGGUNAKAN JARINGAN SYARAF TIRUAN BACKPROPAGATION. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (17kB) |
|
Text
AWAL.pdf Download (927kB) |
|
Text
BAB 1.pdf Download (28kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (540kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (25kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (865kB) |
|
Text
BAB 5.pdf Download (14kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (51kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (51kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (3MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository UPNVJ Only Download (464kB) |
Abstract
TB treatment is not easy, it takes about six months of treatment with OAT. In addition, TB diagnosis requires high accuracy. This if done manually will require a lot of time and the possibility of human error causes the possibility of overdiagnosis or underdiagnosis. To overcome this, we need an application that can identify whether the lung is indicated tuberculosis or not automatically. This study aims to compare the performance of GLCM, Gabor Filter and the combination in identifying pulmonary tuberculosis with digital image processing methods which consist of several stages. These stages began with collecting pulmonary X-ray images from 662 NLM data banks and then selecting only successfully segmented images, which were 558 images. Then the input image will be done to improve the image quality, segmentation, RoI extraction, texture extraction feature GLCM and Gabor Filter, then classify the image with two classes, namely: tuberculosis and normal using artificial neural network Backpropagation Levenberg Marquardt. After testing the performance with several experiments, the best performance is obtained by using feature extraction GLCM + Gabor Filter features (combined) with an average accuracy of 84.82%, precission of 86.13%, and recall of 83.48%. This research is expected to be a reference for other researchers to determine the right pulmonary TB identification model.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 1610511021] [Pembimbing 1: Iin Ernawati] [Pembimbing 2: Mayanda Mega Santoni] [Penguji 1: Yuni Widiastiwi] [Penguji 2: Bambang Tri Wahyono] |
| Uncontrolled Keywords: | Keywords : Backpropagation, GLCM, Gabor Filter, Tuberculosis |
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | Qahtan Said |
| Date Deposited: | 12 Jan 2022 05:04 |
| Last Modified: | 12 Jan 2022 05:04 |
| URI: | http://repository.upnvj.ac.id/id/eprint/6810 |
Actions (login required)
 |
View Item |