Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 2 No 11 (2018): November 2018

Klasifikasi Risiko Gagal Ginjal Kronis Menggunakan Extreme Learning Machine

Dimas Prenky Dicky Irawan (Fakultas Ilmu Komputer, Universitas Brawijaya)
Imam Cholisoddin (Fakultas Ilmu Komputer, Universitas Brawijaya)
Edy Santoso (Fakultas Ilmu Komputer, Universitas Brawijaya)



Article Info

Publish Date
17 Jul 2018

Abstract

Kidney is an organ in humans that have a very important role in the process of managing fluid and electrolyte needs. Chronic renal failure is a disease of kidney that occurs due to kidney infection and the existence of blockage due to kidney stones. To perform the classification of chronic renal failure medical personnel are still not maximally in handling it, to deal with this problem researchers use the Extreme Learning Machine to perform the classification of chronic renal failure. The Extreme Learning Machine is a classification algorithm in which this algorithm is part of a neural network that has a good learning speed and also according to existing research results in a good accuracy value when compared to using other algorithms. This study obtained a comparison of the value of training data as well as the optimal test data with a 70:30 ratio value, many hidden layer neurons of 10 and using the bipolar sigmoid activation function of these parameters resulted in an accuracy of 99.13%. From the results of accuracy obtained, indicating that the method of Extreme Learning Machine is good enough to be used for the process of classification of chronic renal failure.

Copyrights © 2018






Journal Info

Abbrev

j-ptiik

Publisher

Subject

Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Description

Jurnal Pengembangan Teknlogi Informasi dan Ilmu Komputer (J-PTIIK) Universitas Brawijaya merupakan jurnal keilmuan dibidang komputer yang memuat tulisan ilmiah hasil dari penelitian mahasiswa-mahasiswa Fakultas Ilmu Komputer Universitas Brawijaya. Jurnal ini diharapkan dapat mengembangkan penelitian ...