Scholarlink

Virtual intelligent experiments in education often struggle with limitations, such as the inability to manipulate real objects and accurately understand user intentions. This study introduces EyeGlove, a smart glove with enhanced visual capabilities, and its associated smart laboratory. The aim is to enable students to interact with real chemical laboratory equipment in a mixed-reality environment. To address challenges in prior virtual experiments, we propose the MUFD algorithm, based on fuzzy reasoning and Dempster-Shafer evidence theory, to enhance intention understanding. MUFD analyzes speech, visual, and gesture information to determine users’ experimental intentions. Experimental results show EyeGlove, supported by MUFD, effectively addresses challenging experiment steps, demonstrating robustness in handling incomplete and uncertain information. Through hands-on experiences and surveys with 20 participants, our system proves advantageous in reducing task load and enhancing subjective emotional experiences.

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

EyeGlove: Enhancing Smart Glove with Visual Information to Assist Students in Conducting Chemistry Experiments in Mixed Reality Laboratory

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Hong Cui,
  • Dehui Kong,
  • Zhiquan Feng

摘要

Virtual intelligent experiments in education often struggle with limitations, such as the inability to manipulate real objects and accurately understand user intentions. This study introduces EyeGlove, a smart glove with enhanced visual capabilities, and its associated smart laboratory. The aim is to enable students to interact with real chemical laboratory equipment in a mixed-reality environment. To address challenges in prior virtual experiments, we propose the MUFD algorithm, based on fuzzy reasoning and Dempster-Shafer evidence theory, to enhance intention understanding. MUFD analyzes speech, visual, and gesture information to determine users’ experimental intentions. Experimental results show EyeGlove, supported by MUFD, effectively addresses challenging experiment steps, demonstrating robustness in handling incomplete and uncertain information. Through hands-on experiences and surveys with 20 participants, our system proves advantageous in reducing task load and enhancing subjective emotional experiences.