ANALISIS CITRA PENYAKIT DIABETIC RETINOPATHY BERDASARKAN ALGORITME JARINGAN SYARAF TIRUAN

Setiawan, Gesha Agus (2019) ANALISIS CITRA PENYAKIT DIABETIC RETINOPATHY BERDASARKAN ALGORITME JARINGAN SYARAF TIRUAN. Other thesis, Universitas Amikom Purwokerto.

[img] Text
Cover.pdf

Download (930kB)
[img] Text
DAFTAR ISI.pdf

Download (353kB)
[img] Text
ABSTRAK.pdf

Download (336kB)
[img] Image
BAB I.pdf
Restricted to Registered users only

Download (356kB)
[img] Image
BAB II.pdf
Restricted to Registered users only

Download (1MB)
[img] Image
BAB III.pdf
Restricted to Registered users only

Download (1MB)
[img] Image
BAB IV.pdf
Restricted to Registered users only

Download (1MB)
[img] Image
BAB V.pdf
Restricted to Registered users only

Download (509kB)
[img] Image
DAFTAR PUSTAKA.pdf
Restricted to Registered users only

Download (516kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository staff only

Download (1MB)

Abstract

Diabetes retinopathy is a complication of diabetes in the form of damage to the retina. High levels of glucose in the blood are the cause of small capillary blood vessels to rupture and blindness. The signs of this disease can only be seen using retinal fundus images. Identifying diabetic retinopathy by computerized process and analysis is needed, one of which uses artificial neural network methods to determine its performance so that it will help the doctor in analyzing the disease and diagnosing a patient suffering from diabetes retinopathy. Texture feature extraction method using Gabor filter can represent feature value information that is skewness, kurtosis, mean, entrophy, and variance to be processed at the identification stage using artificial neural network methods. The comparison results of the DIARETDB0 dataset testing 130 fundus images using the backpropagation ANN method before randomizing the data yielded an accuracy value of 82.30%, a precision value of 71.28%, a recall value of 82.30%, and an f-measure of 76.39%. Whereas after randomizing the data 30 times, getting the results of a higher accuracy value than before randomizing the data is an accuracy value of 83.07%, a precision value of 71.39%, a recall value of 83.07% and for the f-measure value of 76.78% and shows the tests carried out included in a good classification.

Item Type: Thesis (Other)
Additional Information: Dosen Pembimbing: Tri Astuti, S.Kom., M.Eng.
Uncontrolled Keywords: Diagnosis, Diabetic Retinopathy, Artificial Neural Network, Algorithm, Backpropagation, Feature Extraction
Subjects: R Medicine > R Medicine (General)
T Technology > T Technology (General)
Divisions: Fakultas Ilmu Komputer > Informatika
Depositing User: UPT Perpustakaan Pusat Universitas Amikom Purwokerto
Date Deposited: 22 Sep 2020 06:03
Last Modified: 22 Sep 2020 06:03
URI: http://eprints.amikompurwokerto.ac.id/id/eprint/230

Actions (login required)

View Item View Item