摘要
由一名新闻记者兼机器人与机器学习每日新闻的新闻编辑-一项关于人工智能的新研究现在可用。根据《中华人民共和国广东》的新闻报道，NewsRx编辑的研究表明，"人工智能与教育的融合是大势所趋，将人工智能应用于教学已成为必要"。新闻记者从法学院的研究中得到一句话：“本研究以人工智能技术在教学中的应用为出发点，构建了一个识别学生面孔和情绪的智能课堂模型，更好地了解学生的学习状况。”该方法首先进行基于支持向量机的情感识别，然后通过后验概率实现决策层的融合，完成多模态情感识别模型的构建，最后应用PAD量表对被试在课堂各阶段的情绪进行量化分析,构建了整合多模态情绪识别的人工智能教学策略,并对其应用效果进行了检验,60%以上的学生在CLAS前后10min内处于平静状态。而78%的学生在25分钟内处于积极的学习情绪，多模态情绪识别模型对学生的情绪识别效果良好，经过教学实践，实验班的学生成绩比对照班提高12.29%。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – A new study on artificial intelligence is now available. According to news reporting out of Guangdong, People’s Republ ic of China, by NewsRx editors, research stated, “The integration of artificial intelligence and education is a general trend, and it has become necessary to ut ilize artificial intelligence for teaching.” The news reporters obtained a quote from the research from School of Law: “This study takes the application of artificial intelligence technology in teaching st rategy as the starting point, constructs an intelligent classroom model for reco gnizing students’ faces and emotions, and better understands their learning stat e. The method first carries out emotion recognition based on a support vector ma chine, then realizes the fusion of the decision layer through a posteriori proba bility, completes the construction of a multimodal emotion recognition model, an d finally applies the PAD scale to quantify the emotion and analyze the emotion and state of the sample students in various stages of the classroom. The artific ial intelligence teaching strategy that integrates multimodal emotion recognitio n is constructed and its application effectiveness is examined. More than 60% of the students were in a calm state in the 10 minutes before and after the clas s, and 78% of the students were in a positive learning mood in the 25 minutes of the class, so the multimodal emotion recognition model has a good effect of recognizing students’ emotions. After the teaching practice is carrie d out, the student’s performance in the experimental class is 12.29% higher than that in the control class.”
NETL
NSTL