Institute of Marxism and Research, Jiangxi Police College, Nanchang Jiangxi 330000, China.
Occup Ther Int. 2022 Apr 14;2022:3650308. doi: 10.1155/2022/3650308. eCollection 2022.
This paper presents an in-depth study and analysis of students' role perceptions and their tendencies in classroom education using a visual inspection approach. A multi example learning student engagement assessment method based on a one-dimensional convolutional neural network is proposed. Based on the conceptual composition of student engagement, head posture, eye gaze, and eye-opening and closing states and the most used facial movement units are used as visual features. For feature extraction, the proposed view of relative change features, based on the video features extracted from the Open Face toolset, the standard deviation of the distance between adjacent multiple frames relative to the center point of the three visual features is used as the relative change features of the video. This results in the phenomenon that students are highly motivated in the early stage and significantly increase the rate of absenteeism in the later stage. With the development of information technology injecting new vitality into educational innovation, many researchers have introduced computer vision and image processing technology into students' online learning activities, and understand students' current learning situation by analyzing students' learning status. There are relatively few studies in this area in classroom teaching. Considering the low relative position correlation of the features in the examples, the examples are analyzed using a one-dimensional convolutional neural network to obtain the example-level student engagement, and a multi-example pooling layer is used to infer the student engagement in the video from the example-level student engagement. Finally, the experimental method is used to apply the student classroom attention evaluation detection system to actual classroom teaching activities, and the effectiveness and accuracy of the design of the student classroom attention evaluation detection system are investigated in depth through specific applications and example analysis, and the accuracy of the method of this paper is further verified by communicating feedback with teachers and students in the form of interviews.
本文采用可视化检查方法，深入研究和分析了学生在课堂教育中的角色认知和倾向。提出了一种基于一维卷积神经网络的多示例学习学生参与评估方法。基于学生参与的概念构成、头部姿势、目光注视、睁眼和闭眼状态以及最常用的面部运动单元作为视觉特征。对于特征提取，所提出的相对变化特征视图基于从 Open Face 工具集中提取的视频特征，将相邻多个帧相对于三个视觉特征中心点的距离的标准差用作视频的相对变化特征。这导致学生在早期阶段的积极性很高，而在后期阶段的缺勤率显著增加。随着信息技术的发展为教育创新注入新的活力，许多研究人员将计算机视觉和图像处理技术引入到学生的在线学习活动中，通过分析学生的学习状态来了解学生的当前学习情况。在课堂教学中，这方面的研究相对较少。考虑到示例中的特征相对位置相关性较低，使用一维卷积神经网络对示例进行分析，以获得示例级别的学生参与度，并使用多示例池化层从示例级别的学生参与度推断视频中的学生参与度。最后，实验方法将学生课堂注意力评估检测系统应用于实际课堂教学活动中，通过具体应用和实例分析深入研究学生课堂注意力评估检测系统设计的有效性和准确性，并通过与教师和学生的访谈形式进行沟通反馈，进一步验证了本文方法的准确性。
