UI - Skripsi Membership :: Back

UI - Skripsi Membership :: Back

Klasifikasi diabetik retinopati dengan menggunakan pendekatan shallow learning = Classification of diabetic retinopathy using shallow learning approach

Singgih Pansawira; Alhadi Bustaman, supervisor; Devvi Sarwinda, examiner; Gatot Fatwanto Hertono, examiner; Gianinna Ardaneswari, examiner ([Publisher not identified] , 2018)

 Abstract

ABSTRACT
Diabetik Retinopati adalah salah satu penyebab utama kebutaan dari penderita diabetes. Untuk mencegah kebutaan dan memberikan pengobatan yang efektif, diperlukan suatu metode pendeteksian yang lebih dini untuk Diabetik Retinopati. Terdapat beberapa metode inspeksi manual untuk mendeteksi Diabetik Retinopati, tetapi membutuhkan banyak waktu dan usaha yang berat. Dalam penelitian ini, diajukan metode pendeteksian Diabetik Retinopati dengan menggunakan pendekatan Shallow Learning yang mencakup Neural Network, Support Vector Machines, dan Random Forest. Data yang digunakan untuk membangun model classifier terdiri dari kelas Diabetik Retinopati DB, kelas Age-related Macular Degeneration AMD, dan kelas Normal. Dari hasil percobaan, pendekatan klasifikasi dengan metode Support Vector Machines memiliki hasil yang lebih baik dibandingkan dengan metode Random Forest dan Neural Network. Pada klasifikasi multi-class DB, Normal, dan AMD, metode Support Vector Machines memperoleh nilai akurasi 100 dan sensitivity 100 pada 75 data training, dan memperoleh nilai akurasi 94,87 dan sensitivity 93,33 pada 25 data testing.

ABSTRACT
Diabetic Retinopathy is one of the leading causes of blindness from diabetic patients. To prevent blindness and provide an effective treatment, an early detection of Diabetic Retinopathy is needed. Methods for detecting Diabetic Retinopathy by manual inspections exist, but very time consuming and require tedious work. In this study, Diabetic Retinopathy detection method is proposed, by using Shallow Learning approach that consists of Neural Network, Support Vector Machines, and Random Forest. The data used to build the classifier models are Diabetic Retinopathy DB class, Age related Macular Degeneration AMD class, and Normal class. From experimental results, classification approach using Support Vector Machines yielded better results compared to Random Forest and Neural Network. On multi class DB, Normal, and AMD classification, Support Vector Machines method obtained 100 accuracy and 100 sensitivity for 75 training data, and 94,87 accuracy and 93,33 sensitivity for 25 testing data.

 Digital Files: 1

Shelf
 S-Singgih Pansawira.pdf :: Download

LOGIN required

 Keyword

 Metadata

Collection Type : UI - Skripsi Membership
Call Number : S-Pdf
Main entry-Personal name :
Additional entry-Personal name :
Additional entry-Corporate name :
Study Program :
Subject :
Publishing : [Place of publication not identified]: [Publisher not identified], 2018
Cataloguing Source LibUI ind rda
Content Type text
Media Type computer
Carrier Type online resource
Physical Description xiii, 52 pages : illustration
Concise Text
Holding Institution Universitas Indonesia
Location Perpustakaan UI
  • Availability
  • Review
  • Cover
Call Number Barcode Number Availability
S-Pdf 14-21-837630787 TERSEDIA
Review:
No review available for this collection: 20475172
Cover