Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Concentration Cells02:41

Concentration Cells

23.2K
A concentration cell is a type of a  voltaic cell constructed by connecting two almost identical half-cells, both based on the same half-reaction and using the same electrode, differing only in the concentration of one redox species. A concentration cell's potential, therefore, is determined only by the concentration difference of the particular redox species.
Consider the following voltaic cell:
23.2K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Inferobasal myocardial infarction.

Coronary artery disease·2026
Same author

Wide QRS tachycardia with atypical echo beats.

Indian pacing and electrophysiology journal·2026
See all related articles

Related Experiment Video

Updated: Aug 27, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.0K

Evaluation of e-learners' concentration using recurrent neural networks.

Young-Sang Jeong1, Nam-Wook Cho2

  • 1Department of Data Science, Seoul National University of Science and Technology, 232 Gongreung-ro, Nowon, Seoul, 01811 South Korea.

The Journal of Supercomputing
|September 27, 2022
PubMed
Summary

This study introduces a new method using artificial intelligence to predict e-learning concentration from video data. Gated recurrent units showed the best performance in identifying learner focus during online classes.

Keywords:
ConcentrationE-learnerE-learningGated recurrent units(GRU)Long short-term memory (LSTM)Recurrent neural networks (RNN)

More Related Videos

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
08:05

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

7.6K
Assessing the Multiple Dimensions of Engagement to Characterize Learning: A Neurophysiological Perspective
13:57

Assessing the Multiple Dimensions of Engagement to Characterize Learning: A Neurophysiological Perspective

Published on: July 1, 2015

12.7K

Related Experiment Videos

Last Updated: Aug 27, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.0K
Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
08:05

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

7.6K
Assessing the Multiple Dimensions of Engagement to Characterize Learning: A Neurophysiological Perspective
13:57

Assessing the Multiple Dimensions of Engagement to Characterize Learning: A Neurophysiological Perspective

Published on: July 1, 2015

12.7K

Area of Science:

  • Computer Science
  • Educational Technology
  • Artificial Intelligence

Background:

  • The COVID-19 pandemic accelerated e-learning adoption, highlighting challenges in maintaining student engagement.
  • Limited teacher-student interaction in e-learning environments often leads to decreased learner concentration.
  • Developing methods to monitor and predict learner concentration is crucial for effective online education.

Purpose of the Study:

  • To develop and evaluate a methodology for predicting e-learners' concentration levels.
  • To apply recurrent neural network (RNN) models to analyze video data for concentration prediction.
  • To investigate the effectiveness of different RNN architectures, including Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU).

Main Methods:

  • Collected video data from 92 e-learners (184 videos total).
  • Extracted facial landmark and eye gaze data using the OpenFace 2.0 toolkit.
  • Utilized RNN models, specifically LSTM and GRU, to predict learner concentration based on extracted features.

Main Results:

  • Comparative experiments demonstrated the performance of different RNN models.
  • Gated Recurrent Units (GRU) achieved the highest accuracy in predicting e-learner concentration.
  • The proposed methodology effectively predicts concentration in a natural e-learning setting.

Conclusions:

  • A novel methodology for predicting e-learner concentration using AI and video analysis has been presented.
  • GRU models offer a promising approach for real-time monitoring of learner engagement in e-learning.
  • This research contributes to improving the effectiveness of online education by addressing attention deficits.