Scholarlink

<p>Cognitive workload is a key factor in understanding human cognitive performance, especially in scenarios that require intensive information processing. This study introduces an innovative method to estimate cognitive workload using eye-tracking data and proposes a novel deep learning model called BiTCADNet (Bidirectional Temporal Convolutional self-Attention Dense Network). Experiments using the newly created dataset "Cognitive-Eye-Movement" and the publicly available dataset "CL-Drive" show that BiTCADNet significantly outperforms traditional deep learning models in terms of accuracy, precision, recall, and F1 scores are significantly better than traditional machine learning methods. The proposed method provides a more effective way to monitor and evaluate cognitive workload in real-time, opening the way for its applications in various human-computer interaction environments.</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

Cross-task cognitive workload estimation using eye tracking

  • 期刊论文

  • 发表日期：

    2025年3月5日

查看全文
  • Lin Yang,
  • Lei Wang,
  • Wenchang Xu,
  • Biao Wang,
  • Hanbin Ren,
  • Aijuan Yang

摘要

Cognitive workload is a key factor in understanding human cognitive performance, especially in scenarios that require intensive information processing. This study introduces an innovative method to estimate cognitive workload using eye-tracking data and proposes a novel deep learning model called BiTCADNet (Bidirectional Temporal Convolutional self-Attention Dense Network). Experiments using the newly created dataset "Cognitive-Eye-Movement" and the publicly available dataset "CL-Drive" show that BiTCADNet significantly outperforms traditional deep learning models in terms of accuracy, precision, recall, and F1 scores are significantly better than traditional machine learning methods. The proposed method provides a more effective way to monitor and evaluate cognitive workload in real-time, opening the way for its applications in various human-computer interaction environments.