Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Edo Ergi Prayogo
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 
Klasifikasi Bidang Keunggulan Mahasiswa menggunakan Metode Backpropagation dan Seleksi Fitur Information Gain (Studi Kasus : Departemen Teknik Informatika Universitas Brawijaya) Edo Ergi Prayogo; Indriati Indriati; Candra Dewi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 7 No 1 (2023): Januari 2023
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The field of excellence of students is a skill that can be possessed by students after completing their college years, especially for students of Informatics Engineering at Brawijaya University. To uncover this potential for excellence, there is a learning system that focuses on students taking certain elective courses that are still close in terms of the study materials suitable for their interests and abilities. The goal is to make Informatics Engineering students have the desired graduate profile. The large number of choices for fields of excellence makes students confused about determining the appropriate field of excellence. To help students determine this field of excellence, the author chose to use the Backpropagation Classification Method and the Information Gain Feature Selection. Testing was conducted a total of 5 times, and then averaged. The testing used begins with K-Fold Cross Validation to test the stability of the dataset, by dividing the data into 5 random Folds and then finding the Fold with the best evaluation value. Subsequently, testing is carried out on the Learning Rate and Hidden Neuron parameters, with the final test being feature selection. The best testing parameters are a learning rate of 0.1, 20 hidden neurons, and 100% features without any features being removed. The results of the testing obtained are an average accuracy of 86.34%, precision of 87.95%, recall of 86.69%, and f-measure of 87.12%. The results obtained show that the Backpropagation Method can be used to classify the field of excellence of Informatics Engineering students, but the use of the Information Gain feature selection does not provide an improvement in the evaluation value obtained.
Co-Authors Candra Dewi Indriati Indriati