Identification of the Success of Learning Al Islam and Kemuhammadiyahan Using Machine Learning

DOI

10.2991/iccelst-st-19.2019.1How to use a DOI?

Keywords

Al Islam and Kemuhammadiyahan, K-Nearest Neighbour, Learning Success, Machine Learning

Abstract

Learning Al Islam and Kemuhammadiyahan (AIK) is one of the compulsory learning in all levels of Muhammadiyah education which has the general goal of forming human learners who are pious, noble, advanced and superior in science and technology as the embodiment of tajdid amar makruf nahi mungkar. In order to achieve the objectives of learning in education, the measurement and evaluation of these subjects should be carried out. The Muhammadiyah University of Riau as one of the Muhammadiyah universities in Indonesia that applies AIK education in its learning curriculum has not measured the success rate of this course. Therefore this study will identify the success of AIK learning at Universitas Muhammadiyah Riau with machine learning artificial intelligence technology. The data source is the students' grades in this AIK course, then by using the Machine Learning method K-Nearest Neighbor classification algorithm will measure the success rate of learning. From 149 sample data that were conducted training and testing (90% of training data and 10% of test data) as well as conducting several trials of K parameter values, the best accuracy results obtained at parameter k = 2 with an accuracy value of 71.43%.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Edi Ismanto
AU  - Eka Pandu Cynthia
PY  - 2019/12
DA  - 2019/12
TI  - Identification of the Success of Learning Al Islam and Kemuhammadiyahan Using Machine Learning
BT  - Proceedings of the International Conference of CELSciTech 2019 - Science and Technology track (ICCELST-ST 2019)
PB  - Atlantis Press
SP  - 1
EP  - 6
SN  - 2352-5401
UR  - https://doi.org/10.2991/iccelst-st-19.2019.1
DO  - 10.2991/iccelst-st-19.2019.1
ID  - Ismanto2019/12
ER  -