Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Zulianur Khaqiqiyah
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Identifikasi Tingkat Resiko Penyakit Lemak Darah Menggunakan Algoritme Backpropagation Zulianur Khaqiqiyah; Budi Darma Stiawan; Marji Marji
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 4 (2018): April 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (980.963 KB)

Abstract

Blood fat or often known as lipid profile is one of the sources of energy in the body in the form of fat components that lie inside the blood vessels. Blood fat serves as a carrier of vitamins, forming cell walls and steroid hormones. But the amount of high blood fats can be resulting in the risk of dangerous diseases, such as heart disease and pancreatitis. To prevent further disease, then this study was made to determine the level of risk of internal blood lipid in a human body. The algorithm that is use for the classification process is one of the algorithms on the artificial neural network, that is Backpropagation. In the testing process carried out on the number of iterations, the effect of the value learning rate, and amount of training data. In this study the number of neurons used are 4 input layer, 4 hidden layer, and 3 output layers. Based on the process testing that has been done, obtained the highest accuracy of 89.20% with the value of learning rate is at 0.2, at the maximum iteration of 800 and 1000. Comparison of data used is 70 trainer data and 50 test data, with target of MSE is 0.0001. While the lowest accuracy obtained is worth 65.96% with comparison of data used is 10 trainer data and 30 test data, with the value of learning rate 0.2 and 1000 iterations at the maximum.
Co-Authors Budi Darma Stiawan Marji Marji