基于深度学习的线上教学学生状态监测系统设计  

Design of an Online Teaching Student Status Monitoring System Based on Deep Learning

作　　者：孙锐[1,2] 黄睿 张旭东 Sun Rui;Huang Rui;Zhang Xudong(School of Computer and Information,Hefei University of Technology,Hefei,230601,China;Anhui Province Key Laboratory of Industry Safety and Emergency Technology,Hefei,230009,China)

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230601 [2]工业安全与应急技术安徽省重点实验室,安徽合肥230009

出　　处：《中国现代教育装备》2025年第5期22-25,共4页China Modern Educational Equipment

基　　金：安徽省省级质量工程项目“基于人工智能的课堂行为分析与教学评测方法研究”(编号:2022jyxm008);教育部高等教育司2023年第一批产学合作协同育人项目“面向新工科的通信工程专业创新型人才培养研究与实践”(编号:230907245071229)。

摘　　要：随着人工智能和互联网技术的发展,线上教学模式逐渐普及,它不受时间、空间限制,可以提供多样化和个性化的教学资源,丰富了现有的教学方式。但由于网络空间的限制,教师无法实时监控学生的学习状态,从而影响教学质量的提升。因此,开发了基于深度学习的线上教学学生状态监测系统,通过分析学生脸部姿态反映学生学习的专注程度。该系统采用YOLOv5网络实时检测屏幕前的学生人脸,再将数据输入学生状态分类网络中,实现对学生缺席、打哈欠、打盹状态的监测,最后采用PyQt实现前台GUI界面开发和数据统计。测试结果表明,该系统可以准确抓取人脸信息,判断学生的学习状态,具有较好的实用价值。With the development of artificial intelligence and internet technology,online teaching models have developed rapidly.It is not limited by time and space,and can provide diverse and personalized teaching resources,enriching existing teaching methods.However,due to limitations in cyberspace,teachers are unable to monitor students'learning status in real-time,which affects the improvement of teaching quality.Therefore,this paper develops an online teaching student state detection system based on deep learning.The students'facial posture can reflect the students'level of focus in learning.The system uses YOLOv5 network to detect the students'face in real-time in front of the screen,and then inputs the face into the student state classification network to monitor the students'absence,yawning,and dozing status.Finally,PyQt is used to develop the front-end GUI interface and data statistics.Tests have shown that the system can accurately capture facial information and judge students'learning status,with good practical value.

关 键 词：线上教学 深度学习 人脸检测 学习状态分类 

分 类 号：G434[文化科学—教育学]