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
Teddy Syach Pratama
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 
Sistem Pakar Sistem Pakar untuk Deteksi Dini Tingkat Depresi Mahasiswa menggunakan Metode Support Vector Machine (Studi Kasus: Fakultas Ilmu Komputer Universitas Brawijaya) Teddy Syach Pratama; Arief Andy Soebroto
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 6 No 1 (2022): Januari 2022
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

A student is someone who has been attending one of the highest educational institutions for some time. Students have several levels, namely the beginning and the final level. Where the final level is a step to prepare yourself to compile a thesis or final assignment as a condition of graduation becomes one of the toughest obstacles. In several studies conducted in 2019 at one of the universities, 15 students with an average age of 21 partially had mild depression rates of (51.7%), moderate (41.4%), there were 2 high-level depressed students (Mir et al., 2019). As a final-level student depression is a disease that can affect all final students including students instead of the end level. Therefore, depression in students must be treated quickly and appropriately. However, the obstacles to handling require experts or psychologists, plus the lack of people who understand about mental disorders in students. Therefore, a system is needed that can detect early levels of depression in students to be able to stop more serious problems. The study will implement an expert system for early detection of student depression levels using the Support Vector Machine method with a web-based kernel-RBF. . Using 257 data in his tests obtained an average accuracy value of 90.6% and a precision value of 87.8%, recall 83.2%, f1-score 85% and obtained the best SVM parameter value at the value of complexity (C) = 2, gamma (y) = 0.1, and Maxiteration = 1000 with a data ratio of 70%:30%. With good accuracy scores, this study can be implemented to help expert system for early detection of student depression levels using the Support Vector Machine Method.
Co-Authors Arief Andy Soebroto