Scholarlink

<p>With the advancement of technology in the educational sector, there has been a surge in popularity of Massive Open Online Courses (MOOCs). It offers advantages of being low cost and accessible from any part of the world. The challenge of the MOOC instructor is to judge the understanding level of the learner as face to face interaction is absent as compared to a traditional classroom setup. The EEG signals can be utilized here to understand the brain activity of the learner while watching the MOOC videos. The confused student EEG dataset were utilized in this study to classify the cognitive state of the subjects while they learn from the MOOC videos. To classify the confusion state with good accuracy, a stacking model has been developed. The moving average features of the EEG signals were extracted for this research and the proposed model achieved a remarkable accuracy of 99 percent, with a consistent accuracy of 98 percent in fivefold cross-validation. These findings will contribute in the digital learning environments aimed at monitor and personalize learner’s experience.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

EEG Based Confusion Detection in Student Using a Stacking Model with Moving Average Features

  • 期刊论文

  • 发表日期：

    2026年5月24日

查看全文
  • Shweta Sharma,
  • Rajneet Kaur Bijral,
  • Ayushi Kotwal,
  • Jatinder Manhas,
  • Vinod Sharma

摘要

With the advancement of technology in the educational sector, there has been a surge in popularity of Massive Open Online Courses (MOOCs). It offers advantages of being low cost and accessible from any part of the world. The challenge of the MOOC instructor is to judge the understanding level of the learner as face to face interaction is absent as compared to a traditional classroom setup. The EEG signals can be utilized here to understand the brain activity of the learner while watching the MOOC videos. The confused student EEG dataset were utilized in this study to classify the cognitive state of the subjects while they learn from the MOOC videos. To classify the confusion state with good accuracy, a stacking model has been developed. The moving average features of the EEG signals were extracted for this research and the proposed model achieved a remarkable accuracy of 99 percent, with a consistent accuracy of 98 percent in fivefold cross-validation. These findings will contribute in the digital learning environments aimed at monitor and personalize learner’s experience.