Comparison of MLP-BPNN and MLP-PSO for Automatic Essay Grading System for Japanese Language Exam

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, a study was conducted for a hybrid model for Multilayer Perceptron (MLP) with Particle Swarm Optimization (PSO). The PSO was used to replace the Backpropagation method for the weight optimization. The comparison was conducted between MLP-BPNN and MLP-PSO for an automated essay grading system for Japanese language exam. The MLP-PSO model achieved a more accurate but less stable result. The MLP-PSO model with 10 particles trained for 15 steps achieves the best result out of the two MLP-PSO models tested, with an average 8.48% error for the grade population. Compared to the MLP-PSO model, it was discovered that MLP-BPNN with Adam optimizer achieves better overall performance and results concerning both the accuracy and the stability of the model.

Original languageEnglish
Title of host publication17th International Conference on Quality in Research, QIR 2021
Subtitle of host publicationInternational Symposium on Electrical and Computer Engineering
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages204-208
Number of pages5
ISBN (Electronic)9781665496964
DOIs
Publication statusPublished - 2021
Event17th International Conference on Quality in Research, QIR 2021: International Symposium on Electrical and Computer Engineering - Virtual, Online, Indonesia
Duration: 13 Oct 202115 Oct 2021

Publication series

Name17th International Conference on Quality in Research, QIR 2021: International Symposium on Electrical and Computer Engineering

Conference

Conference17th International Conference on Quality in Research, QIR 2021: International Symposium on Electrical and Computer Engineering
Country/TerritoryIndonesia
CityVirtual, Online
Period13/10/2115/10/21

Keywords

  • Machine Learning
  • Multilayer
  • Neural Network
  • Particle Swarm Optimization
  • Perceptron
  • SIMPLE-O

Fingerprint

Dive into the research topics of 'Comparison of MLP-BPNN and MLP-PSO for Automatic Essay Grading System for Japanese Language Exam'. Together they form a unique fingerprint.

Cite this