Classifying the Complexity of Competency in Elementary School based on Supervised Learners

Umi Laili Yuhana, L. Kóczy, Tri Arief Sardjono, I. Ketut Eddy Purnama, Eko Mulyanto Yuniarno, Mauridhi Hery Purnomo

Research output: Conference contribution

Abstract

Complexity of competency (CoC) expresses the difficulty level of a competency. The CoC is one of the important parameters for determining the minimum passing level of competency in an assessment system. In Indonesia, the value of CoC is defined by experts based on conditions of subject, students and teachers in each school. The definition process is determined subjectively, where different experts may evaluate CoC in different ways. This is a problem of data classification that requires an automated tool that copes with the amount of data and produces uniform results. To apply an intelligent classifier is essential to solve the issue. This study aims to find the best method for classifying the complexity of competency in Elementary School. Four supervised learning techniques, namely, Naïve Bayes, Multilayer Perceptron, Sequential Minimal Optimization, and RIPPER, were implemented to analyze the dataset. Based on an experiment with 203 data, we found that the Multilayer Perceptron achieved the best performance in the sense of Mean Absolute Error, Root Mean Squared Error, and Receiver Operating Characteristic value. At the same time SMO is better than all other methods in precision, recall, and F-Measure.

Original languageEnglish
Title of host publication2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages280-284
Number of pages5
ISBN (Electronic)9781538675090
DOIs
Publication statusPublished - máj. 9 2019
Event2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Surabaya, Indonesia
Duration: nov. 26 2018nov. 27 2018

Publication series

Name2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding

Conference

Conference2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018
CountryIndonesia
CitySurabaya
Period11/26/1811/27/18

Fingerprint

Multilayer neural networks
Supervised learning
Perceptron
Classifiers
Multilayer
Students
Data Classification
Operating Characteristics
Supervised Learning
Bayes
Mean Squared Error
Experiments
Receiver
Express
Classifier
Competency
Roots
Optimization
Evaluate
Experiment

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Hardware and Architecture
  • Information Systems and Management
  • Media Technology
  • Control and Optimization

Cite this

Yuhana, U. L., Kóczy, L., Sardjono, T. A., Purnama, I. K. E., Yuniarno, E. M., & Purnomo, M. H. (2019). Classifying the Complexity of Competency in Elementary School based on Supervised Learners. In 2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding (pp. 280-284). [8710883] (2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CENIM.2018.8710883

Classifying the Complexity of Competency in Elementary School based on Supervised Learners. / Yuhana, Umi Laili; Kóczy, L.; Sardjono, Tri Arief; Purnama, I. Ketut Eddy; Yuniarno, Eko Mulyanto; Purnomo, Mauridhi Hery.

2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding. Institute of Electrical and Electronics Engineers Inc., 2019. p. 280-284 8710883 (2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding).

Research output: Conference contribution

Yuhana, UL, Kóczy, L, Sardjono, TA, Purnama, IKE, Yuniarno, EM & Purnomo, MH 2019, Classifying the Complexity of Competency in Elementary School based on Supervised Learners. in 2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding., 8710883, 2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding, Institute of Electrical and Electronics Engineers Inc., pp. 280-284, 2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018, Surabaya, Indonesia, 11/26/18. https://doi.org/10.1109/CENIM.2018.8710883
Yuhana UL, Kóczy L, Sardjono TA, Purnama IKE, Yuniarno EM, Purnomo MH. Classifying the Complexity of Competency in Elementary School based on Supervised Learners. In 2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding. Institute of Electrical and Electronics Engineers Inc. 2019. p. 280-284. 8710883. (2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding). https://doi.org/10.1109/CENIM.2018.8710883
Yuhana, Umi Laili ; Kóczy, L. ; Sardjono, Tri Arief ; Purnama, I. Ketut Eddy ; Yuniarno, Eko Mulyanto ; Purnomo, Mauridhi Hery. / Classifying the Complexity of Competency in Elementary School based on Supervised Learners. 2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 280-284 (2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding).
@inproceedings{2f1f6f31f5e74503a37d56c495e1bc22,
title = "Classifying the Complexity of Competency in Elementary School based on Supervised Learners",
abstract = "Complexity of competency (CoC) expresses the difficulty level of a competency. The CoC is one of the important parameters for determining the minimum passing level of competency in an assessment system. In Indonesia, the value of CoC is defined by experts based on conditions of subject, students and teachers in each school. The definition process is determined subjectively, where different experts may evaluate CoC in different ways. This is a problem of data classification that requires an automated tool that copes with the amount of data and produces uniform results. To apply an intelligent classifier is essential to solve the issue. This study aims to find the best method for classifying the complexity of competency in Elementary School. Four supervised learning techniques, namely, Na{\"i}ve Bayes, Multilayer Perceptron, Sequential Minimal Optimization, and RIPPER, were implemented to analyze the dataset. Based on an experiment with 203 data, we found that the Multilayer Perceptron achieved the best performance in the sense of Mean Absolute Error, Root Mean Squared Error, and Receiver Operating Characteristic value. At the same time SMO is better than all other methods in precision, recall, and F-Measure.",
keywords = "intelligent classifier, supervised learners, the complexity of competency",
author = "Yuhana, {Umi Laili} and L. K{\'o}czy and Sardjono, {Tri Arief} and Purnama, {I. Ketut Eddy} and Yuniarno, {Eko Mulyanto} and Purnomo, {Mauridhi Hery}",
year = "2019",
month = "5",
day = "9",
doi = "10.1109/CENIM.2018.8710883",
language = "English",
series = "2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "280--284",
booktitle = "2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding",

}

TY - GEN

T1 - Classifying the Complexity of Competency in Elementary School based on Supervised Learners

AU - Yuhana, Umi Laili

AU - Kóczy, L.

AU - Sardjono, Tri Arief

AU - Purnama, I. Ketut Eddy

AU - Yuniarno, Eko Mulyanto

AU - Purnomo, Mauridhi Hery

PY - 2019/5/9

Y1 - 2019/5/9

N2 - Complexity of competency (CoC) expresses the difficulty level of a competency. The CoC is one of the important parameters for determining the minimum passing level of competency in an assessment system. In Indonesia, the value of CoC is defined by experts based on conditions of subject, students and teachers in each school. The definition process is determined subjectively, where different experts may evaluate CoC in different ways. This is a problem of data classification that requires an automated tool that copes with the amount of data and produces uniform results. To apply an intelligent classifier is essential to solve the issue. This study aims to find the best method for classifying the complexity of competency in Elementary School. Four supervised learning techniques, namely, Naïve Bayes, Multilayer Perceptron, Sequential Minimal Optimization, and RIPPER, were implemented to analyze the dataset. Based on an experiment with 203 data, we found that the Multilayer Perceptron achieved the best performance in the sense of Mean Absolute Error, Root Mean Squared Error, and Receiver Operating Characteristic value. At the same time SMO is better than all other methods in precision, recall, and F-Measure.

AB - Complexity of competency (CoC) expresses the difficulty level of a competency. The CoC is one of the important parameters for determining the minimum passing level of competency in an assessment system. In Indonesia, the value of CoC is defined by experts based on conditions of subject, students and teachers in each school. The definition process is determined subjectively, where different experts may evaluate CoC in different ways. This is a problem of data classification that requires an automated tool that copes with the amount of data and produces uniform results. To apply an intelligent classifier is essential to solve the issue. This study aims to find the best method for classifying the complexity of competency in Elementary School. Four supervised learning techniques, namely, Naïve Bayes, Multilayer Perceptron, Sequential Minimal Optimization, and RIPPER, were implemented to analyze the dataset. Based on an experiment with 203 data, we found that the Multilayer Perceptron achieved the best performance in the sense of Mean Absolute Error, Root Mean Squared Error, and Receiver Operating Characteristic value. At the same time SMO is better than all other methods in precision, recall, and F-Measure.

KW - intelligent classifier

KW - supervised learners

KW - the complexity of competency

UR - http://www.scopus.com/inward/record.url?scp=85066477258&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066477258&partnerID=8YFLogxK

U2 - 10.1109/CENIM.2018.8710883

DO - 10.1109/CENIM.2018.8710883

M3 - Conference contribution

AN - SCOPUS:85066477258

T3 - 2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding

SP - 280

EP - 284

BT - 2018 International Conference on Computer Engineering, Network and Intelligent Multimedia, CENIM 2018 - Proceeding

PB - Institute of Electrical and Electronics Engineers Inc.

ER -