|
UPT. PERPUSTAKAAN
Universitas Esa Unggul
Kampus Emas UEU - Jakarta Barat
|
Phone |
: |
021-5674223, ext 282 |
Fax |
: |
|
E-mail |
: |
[email protected] |
Website |
: |
http://library.esaunggul.ac.id
|
Support (Customer Service) :
|
[email protected] |
|
|
Welcome..guys!
|
Have a problem with your access?
Please, contact our technical support below:
|
LIVE SUPPORT
Astrid Chrisafi
|
! ATTENTION !
To facilitate the activation process, please fill out the member application form correctly and completely
Registration activation of our members will process up to max 24 hours (confirm by email). Please wait patiently
Still Confuse?
Please read our User Guide
|
|
UEU » Undergraduate Theses » Teknik Informatika Posted by [email protected] at 09/07/2021 15:04:45 • 950 Views
KLASIFIKASI PENYAKIT RETINOPATI DIABETIK
DARI GAMBAR RETINA MENGGUNAKAN
DEEP LEARNING (RESNET)Created by :
AGUS SUNARKO ( 20160801133 )
Subject: | PENYAKIT RETINOPATI DIABETIK | Alt. Subject : | DISEASE RETINOPATY DIABETIC | Keyword: | Retinopati Diabetik Deep Learning resnet |
Description:
Retinopati Diabetik terjadi karena adanya pelebaran hingga kebocoran pada
pembuluh darah di area retina mata. Hal ini disebabkan oleh peningkatan kadar gula
darah sehingga kadar hormon insulin dalam tubuh berkurang. International
Diabetes Melitus Federation (IDF) melaporkan bahwa Indonesia berada di urutan
ketiga negara sebanyak 29,1 juta penduduk menderita Diabetes Melitus dalam
rentang usia 20 - 79 tahun. Dalam penelitian ini, dilakukan pendeteksian terhadap
tingkat keparahan retinopati diabetik yang terdiri dari normal, mild, moderate,
severe dan proliferative berdasarkan gambar retina. Metode yang diusulkan
merupakan salah satu metode dalam deep learning, yaitu convolutional neural
network (CNN) dengan arsitektur deep residual network (ResNet). Penelitian
dilakukan dengan melatih model ResNet-18, ResNet-34, ResNet-50, ResNet-101
dan ResNet-152. Hasil penelitian menunjukkan bahwa arsitektur dengan jumlah
layer terbanyak merupakan model pembelajaran fitur terbaik. Sehingga dari model
ResNet-152 yang dilatih, diperoleh tingkat akurasi sebesar 99,82% dengan waktu
selama �13 detik dalam melakukan identifikasi tingkat keparahan retinopati
diabetik pada gambar retina.
Contributor | : |
- Habibullah Akbar,S,Si.,M.Sc,Ph.D
| Date Create | : | 09/07/2021 | Type | : | Text | Format | : | PDF | Language | : | Indonesian | Identifier | : | UEU-Undergraduate-20160801133 | Collection ID | : | 20160801133 |
Source : Undergraduate Theses of Technical Information
Relation Collection: Fakultas Ilmu Komputer
Coverage : Civitas Akademika Universitas Esa Unggul
Rights : @Perpustakaan Universitas Esa Unggul 2021
Publication URL : https://digilib.esaunggul.ac.id/klasifikasi-penyakit-retinopati-diabetikdari-gambar-retina-menggunakandeep-learning-resnet-20713.html
[ Free Download - Free for All ]
- UEU-Undergraduate-20713-Cover.Image.Marked.pdf - 170 KB
- UEU-Undergraduate-20713-Halaman Pengesahan.Image.Marked.pdf - 168 KB
- UEU-Undergraduate-20713-Halaman Persetujuan Publikasi.Image.Marked.pdf - 269 KB
- UEU-Undergraduate-20713-Halaman Persetujuan.Image.Marked.pdf - 258 KB
- UEU-Undergraduate-20713-Halaman Pernyataan Keaslian.Image.Marked.pdf - 224 KB
- UEU-Undergraduate-20713-Abstrak.Image.Marked.pdf - 161 KB
- UEU-Undergraduate-20713-Kata Pengantar.Image.Marked.pdf - 227 KB
- UEU-Undergraduate-20713-Daftar Isi.Image.Marked.pdf - 199 KB
- UEU-Undergraduate-20713-Daftar Pustaka.Image.Marked.pdf - 236 KB
- UEU-Undergraduate-20713-Bab1.Image.Marked.pdf - 319 KB
[ FullText Content - Please, register first ]
1. UEU-Undergraduate-20713-Bab2.Image.Marked.pdf - 1230 KB 2. UEU-Undergraduate-20713-Bab3.Image.Marked.pdf - 1726 KB 3. UEU-Undergraduate-20713-Bab4.Image.Marked.pdf - 3132 KB 4. UEU-Undergraduate-20713-Bab5.Image.Marked.pdf - 162 KB
10 Similar Document...
No similar subject found !
10 Related Document...
No related subject found !
|
POLLINGBagaimana pendapat Anda tentang repository kami ?
Visitors Today : 1
Total Visitor : 1970017
Hits Today : 38385
Total Hits : 154831384
Visitors Online: 1
Calculated since 16 May 2012
You are connected from 172.17.121.29 using Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; [email protected])
|