IMPLEMENTASI BACKPROPAGATION UNTUK MENDIAGNOSA PENYAKIT DIABETES

Priyono, Angger (2019) IMPLEMENTASI BACKPROPAGATION UNTUK MENDIAGNOSA PENYAKIT DIABETES. Tugas Akhir thesis, University of Technology Yogyakarta.

[img]
Preview
Text
Naskah Publikasi-Angger Ary Priyono-5150411207.pdf

Download (829kB) | Preview

Abstract

Some diseases will be a problem when age begins to increase, one of which is diabetes. To find out the potential for diabetes carried out by some identification and later it will be concluded the results of the examination carried out. The conclusion from the examination results can be done by the system by learning the system or machine learning with existing data. Learning is carried out aimed at making the system able to recognize patterns of input and output based on a history of existing diagnoses. One method used is backpropagation. Backpropagtion is one of the methods available in artificial neural networks that is used to make predictions on complex problems. The implementation of backpropagation has been done to predict prediction with several tests of learning rate, hidden layer, epoch, MSE and an experiment to draw a good initial weight with accuracy results obtained by 80% - 90%. Keywords: Prediction, Machine Learning, Neural Network, Backpropation

Item Type: Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects: T Technology > T Technology (General)
Divisions: Fakultas Teknologi Informasi dan Elektro > S1 Informatika
Depositing User: Kaprodi S1 Informatika UTY
Date Deposited: 27 Oct 2019 23:11
Last Modified: 27 Oct 2019 23:11
URI: http://eprints.uty.ac.id/id/eprint/3563

Actions (login required)

View Item View Item