Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal SMARTICS Journal
Akhmad Rojali
Universitas Lambung Mangkurat
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering

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

Found 1 Documents
Search

 1 
Sistem Peringatan Dini Keterlambatan Masa Studi Mahasiswa Menggunakan Metode Support Vector Machine Muhammad Alkaff; Eka Setya Wijaya; Akhmad Rojali
SMARTICS Journal Vol 6 No 2: SMARTICS Journal (Oktober 2020)
Publisher : Universitas PGRI Kanjuruhan Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21067/smartics.v6i2.4579

Abstract

Students graduating late from college are a common problem in universities. The study of students at universities is generally designed to be completed in 3.5 to 4 years. If a student has not graduated past that time, he is considered late in completing his education. Lambung Mangkurat University, as the oldest university in Kalimantan, also experienced these problems. Therefore, an early warning system was build to predict students' possibility of being late in completing their studies. This study uses a sample of students from the Faculty of Engineering, the University of Lambung Mangkurat, to predict students who will be late graduating from Lambung Mangkurat University since semester 5. This system was to develop using a model built using the Support Vector Machine (SVM) method. Model training conducted using 755 data from Lambung Mangkurat University Faculty of Engineering students from 2010 to 2014. Then, the performance of the model tested using 234 student data from 2015 and 2016. The parameters used were the number of credits, gender, GPA on semester 1 to 4, and study programs. The test results show that the model has good performance to predict students who will be late in completing their studies with 88.2% accuracy.
Co-Authors Eka Setya Wijaya Muhammad Alkaff