Open AccessImplementation artificial neural network nguyen widrow algorithm for lupus prediction
Author(s) -
Siti Aisyah,
Mawaddah Harahap,
Abdi Dharma,
Mardi Turnip
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1361/1/012067
Subject(s) - initialization , artificial neural network , computer science , algorithm , artificial intelligence , machine learning , pattern recognition (psychology) , programming language
Lupus is a type of skin disease known as 1000 face disease. This term arises due to this chronic disease causing symptoms and signs that are almost similar to other diseases. Artificial neural network is one method that can be used to help the medical world in managing clinical data. Nguyen Widrow is one of the algorithms and artifical neural network that can be used to make predictions and improve the iteration process. this study applying Nguyen Widrow algorithm in predicting lupus by Matlab. Based on the results of the training process, the Nguyen Widrow initialization algorithm is able to recognize patterns of 80% or range 16 of the 20 datasets. As for the results of testing Nguyen Widrow initialization algorithm with the initials activation function hidden = logsig, activating output logsig, target error 0.1 and learning rate 0.1, Epoch 10000 able to recognize 100% of patterns from 10 existing datasets. So from that it can be concluded that the Nguyen Widrow initialization algorithm can be used to predict disease patterns.