• Home
  • Search
  • Convolutional Neural Network Model based Students’ Engagement Detection in Imbalanced DAiSEE Dataset
  • Cite Icon14
  • https://doi.org/10.14569/ijacsa.2023.0140371Copy DOI Icon

Convolutional Neural Network Model based Students’ Engagement Detection in Imbalanced DAiSEE Dataset

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The COVID-19 pandemic has significantly changed learning processes. Learning, which had generally been carried out face-to-face, has now turned online. This learning strategy has both advantages and challenges. On the bright side, online learning is unbound by space and time, allowing it to take place anywhere and anytime. On the other side, it faces a common challenge in the lack of direct interaction between educators and students, making it difficult to assess students’ engagement during an online learning process. Therefore, it is necessary to conduct research with the aim of automatically detecting students’ engagement during online learning. The data used in this research were derived from the DAiSEE dataset (Dataset for Affective States in E-Environments), which comprises ten-second video recordings of students. This dataset classifies engagement levels into four categories: low, very low, high, and very high. However, the issue of imbalanced data found in the DAiSEE dataset has yet to be addressed in previous research. This data imbalance can cause errors in the classification model, resulting in overfitting and underfitting of the model. In this study, Convolutional Neural Network, a deep learning model, was utilized for feature extraction on the DAiSEE dataset. The OpenFace library was used to perform facial landmark detection, head pose estimation, facial expression unit recognition, and eye gaze estimation. The pre-processing stages included data selection, dimensional reduction, and normalization. The PCA and SVD techniques were used for dimensional reduction. The data were later oversampled using the SMOTE algorithm. The training and testing data were distributed at an 80:20 ratio. The results obtained from this experiment exceeded the benchmark evaluation values on the DAiSEE dataset, achieving the best accuracy of 77.97% using the SVD dimensional reduction technique.

Loading PDF

Similar Papers
  • Research Article

EFFECTIVENESS OF THE ONLINE LEARNING PROCESS ON MACHINING ENGINEERING LEARNING IN SMK NEGERI 2 TASIKMALAYA CITY

  • Jun 19, 2023
  • Journal of Mechanical Engineering Education
  • Wahyu Arief Husain +2
  • Research Article
  • Citations29

Students’ Views on the Use of WhatsApp during Covid-19 Pandemic: A Study at IAIN Batusangkar

  • May 19, 2021
  • IJELTAL (Indonesian Journal of English Language Teaching and Applied Linguistics)
  • Sirajul Munir +2
  • Research Article

Mengatasi Tantangan Pembelajaran Online bagi Anak Tunagrahita Selama Pandemi: Peran Orang Tua dan Strategi Efektif

  • Jun 13, 2024
  • Simpati
  • Astri Lestari +5
  • PDF
  • Research Article
  • Citations1

Study of Online Learning Studies in Natural Sciences Subject in Biology Topic during the Covid-19 Pandemic

  • Oct 31, 2022
  • Jurnal Penelitian Pendidikan IPA
  • Fatma N Utina +2
  • Research Article

STUDI EKSPLORATIF KINERJA GURU MATEMATIKA SELAMA PANDEMIC COVID-19 PADA SEKOLAH MENENGAH KEJURUAN (SMK) DI PERBAUNGAN

  • Sep 19, 2022
  • Jurnal AKTUAL
  • Eka Mayastika Sinaga
  • PDF
  • Research Article
  • Citations1

Challenges and Opportunities Implementation of Online Learning in the Pandemic Era

  • Nov 08, 2022
  • Journal of Education, Humaniora and Social Sciences (JEHSS)
  • Na'Imah Na'Imah +4
  • Book Chapter
  • Citations2

Rendering Optimizations Guided by Head-Pose Estimates and Their Uncertainty

  • Jan 01, 2005
  • Javier E Martínez +4
  • Research Article
  • Citations1

AN ANALYSIS OF STUDENTS’ ETHICS IN ONLINE LEARNING PROCESS

  • Dec 10, 2020
  • BAHAS
  • Ade Aini Nuran
  • Research Article

An Intercultural Comparative Study: Romanian and Japanese Students’ Perceptions of Online Education and Learning Practice During the COVID-19 Pandemic

  • Dec 31, 2022
  • Akdeniz Üniversitesi İletişim Fakültesi Dergisi
  • Cringuta Irina Pelea
  • Conference Article
  • Citations2

E-Learning Vs Google Classroom using WebQual 4.0 Modification: Quality of Learning Services During COVID-19 Pandemic

  • Oct 25, 2021
  • Rismayani +5
  • Research Article

Multistage Classification And Ensemble Learning Techniques For Automated Respiratory Sound Analysis: A Comprehensive Review

  • Dec 15, 2022
  • South Eastern European Journal of Public Health
  • Shahla Naureen Qureshi +1
  • PDF
  • Research Article

Learning Process at SMA Muhammadiyah Bangil During the Covid-19 Pandemic

  • Oct 06, 2021
  • Proceedings of The ICECRS
  • Mustika Itsna Finurika +1
  • Research Article
  • Citations3

Online Learning Readiness, Academic Resilience, and Subjective Well-Being of Junior High School Students during the COVID 19 Pandemic

  • Sep 04, 2021
  • Journal of Educational, Health and Community Psychology
  • Nadhila Safitri +1
  • Research Article
  • Citations1

Accelerating Energy Forecasting with Data Dimensionality Reduction in a Residential Environment

  • Mar 25, 2025
  • Energies
  • Rafael Gonçalves +5
  • PDF
  • Research Article
  • Citations19

A hybrid CNN and ensemble model for COVID-19 lung infection detection on chest CT scans.

  • Mar 09, 2023
  • PLOS ONE
  • Ahmed A Akl +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.