International Journal of Computational Intelligence Systems

Volume 12, Issue 2, 2019, Pages 1575 - 1584

Building an Artificial Neural Network with Backpropagation Algorithm to Determine Teacher Engagement Based on the Indonesian Teacher Engagement Index and Presenting the Data in a Web-Based GIS

Authors
Sasmoko Buddhtha1, 2, *, Christina Natasha3, Edy Irwansyah3, Widodo Budiharto3
1 Primary Teacher Education Department, Faculty of Humanities, Bina Nusantara University, Jakarta, Indonesia 11480
2 Research Interest Group in Educational Technology, Bina Nusantara University, Jakarta, Indonesia 11480
3 Computer Science Department, School of Computer Science, Bina Nusantara University, Jakarta, Indonesia 11480
*Corresponding author. Email: sasmoko.36@gmail.com
Corresponding Author
Sasmoko Buddhtha
Received 27 May 2019, Accepted 14 August 2019, Available Online 15 November 2019.
DOI
https://doi.org/10.2991/ijcis.d.191101.003How to use a DOI?
Keywords
Artificial neural networks, Backpropagation, Stochastic learning, Steepest gradient descent, Indonesian Teacher Engagement Index, Executive information system
Abstract

Teacher engagement is a newly-emerged concept in the field of Indonesian teacher education. To support this concept, we designed an artificial neural network (ANN) using backpropagation, stochastic learning, and steepest gradient descent algorithms to determine teacher engagement based on the Indonesian Teacher Engagement Index (ITEI). The resulting ANN may be used in a data-gathering website for teachers to use for self-evaluation and self-intervention. The optimal architecture for the ANN has 44 input nodes, 26 first hidden layer nodes, 20 second hidden layer nodes, and 7 output nodes, with a learning rate of 0.05 and trained over 5000 iterations. The sample data used for training was gathered by ITEI researchers and the Executive Board of Indonesian Teachers Association (Pengurus Besar Persatuan Guru Republik Indonesia, PB-PGRI) and includes data of teachers from all around Indonesia. The maximum accuracy of this ANN was 97.98%. The sample data were then used to create an executive information system presented in the form of a map created using ArcGIS Pro software.

Copyright
© 2019 The Authors. Published by Atlantis Press SARL.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

Journal
International Journal of Computational Intelligence Systems
Volume-Issue
12 - 2
Pages
1575 - 1584
Publication Date
2019/11
ISSN (Online)
1875-6883
ISSN (Print)
1875-6891
DOI
https://doi.org/10.2991/ijcis.d.191101.003How to use a DOI?
Copyright
© 2019 The Authors. Published by Atlantis Press SARL.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - JOUR
AU  - Sasmoko Buddhtha
AU  - Christina Natasha
AU  - Edy Irwansyah
AU  - Widodo Budiharto
PY  - 2019
DA  - 2019/11
TI  - Building an Artificial Neural Network with Backpropagation Algorithm to Determine Teacher Engagement Based on the Indonesian Teacher Engagement Index and Presenting the Data in a Web-Based GIS
JO  - International Journal of Computational Intelligence Systems
SP  - 1575
EP  - 1584
VL  - 12
IS  - 2
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.d.191101.003
DO  - https://doi.org/10.2991/ijcis.d.191101.003
ID  - Buddhtha2019
ER  -