一种用于学生行为投入检测的非侵入式多模态方法
人机交互
2019-01-18 v1 机器学习
机器学习
摘要
我们提出了一种基于三种非侵入式模态：外观、上下文表现和鼠标的学生行为投入状态（即任务中 vs 任务外）检测的多模态方法。最终的行为投入状态通过在决策层融合模态特定分类器来实现。在真实课堂中收集的学生数据集上进行了各种实验。
引用
@article{arxiv.1901.05835,
title = {Unobtrusive and Multimodal Approach for Behavioral Engagement Detection of Students},
author = {Nese Alyuz and Eda Okur and Utku Genc and Sinem Aslan and Cagri Tanriover and Asli Arslan Esme},
journal= {arXiv preprint arXiv:1901.05835},
year = {2019}
}
备注
12th Women in Machine Learning Workshop (WiML 2017), co-located with the 31st Conference on Neural Information Processing Systems (NeurIPS 2017), Long Beach, CA, USA