Article Per Year (5 Year)
p-Index From 2019 - 2024
0.983
P-Index
This Author published in this journals
All Journal Jurnal CoreIT Indonesian Journal of Artificial Intelligence and Data Mining Jurnal Responsif : Riset Sains dan Informatika
Indriyanti Indriyanti
Universitas Bina Sarana Informatika
Computer Science & IT

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Indonesian Journal of Artificial Intelligence and Data Mining

 1 
Comparison Of Data Mining In E-Learning Learning Based On Log Aktivity On PSO-Based Nural Network Algorithms With PSO-Based SVM Elin Panca Saputra; Supriatiningsih Supriatiningsih; Indriyanti Indriyanti
Indonesian Journal of Artificial Intelligence and Data Mining Vol 3, No 2 (2020): Spetember 2020
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v3i2.10519

Abstract

The purpose of this research is to find a higher or better level of accuracy, we make a comparison between the Neural Network method based on Particle Swarm Optimization and the Particle Swarm Optimization-based support vector machine method, from evaluation on e-learning based learning systems is very important to determine the level. accuracy in learning.. In addition, the purpose of this study is to find the attributes of the highest predictive results of student learning who follow the e-learning learning system. The data we use are 641 users which are taken from the log of student learning activities from the LMS. The logs we use are Gender, Excercise, Forum, Chat, Diskusi, Upload An Assgmnt, Message, Excercise Quiz, dan Total Log. All logs will be recorded in the LMS. The data used in this study, the results of the tests we conducted, the results obtained using the PSO-based Neural Network (NN) method obtained an accuracy value of 97.35%, and the results of the AUC value were 98.60%. Then we did the second trial using the PSO-based support vectore machine (SVM) method to get an accuracy value of 88.47% and an AUC value of 93.80%. Then the conclusion is that using the neural network method is higher than using the spport vector machine method with an accuracy difference of 8.88% while the AUC accuracy value is a difference of 4.8%.
Co-Authors Erni Ermawati Fatah, Haerul Herlan Sutisna, Herlan Marliana Rahmawati Nurhanifah Nurul Ichsan Panca Saputra, Elin Risqi Nur Alfiyah Supriatiningsih Supriatiningsih Tri Wahyuni