基于卷积神经网络的远程学习参与度检测  

Convolutional Neural Network-based distance learning engagement detection

作　　者：刘莹[1] LIU Ying(Xi’an Fanyi University,Xi’an 710100,China)

机构地区：[1]西安翻译学院,西安710100

出　　处：《信息技术》2024年第12期130-135,共6页Information Technology

基　　金：陕西省哲学社会科学重大理论与现实问题研究项目(2022HZ0860)。

摘　　要：为使用面部表情来检测在线学习者在其教育活动中的参与度,研究了三种不同的基本卷积神经网络模型和一种新提出的卷积神经网络模型,包括全卷积网络(All-CNN)、网络中的网络(NiN-CNN)和非常深的卷积网络(VD-CNN),根据三个基本模型的优势特征提出新的模型,线性卷积层被多层感知器替换,使用小的(3×3)卷积滤波器增加网络的深度,并将一些最大池化层替换为带有增加步幅的卷积层。将四个模型应用于E-环境中的情感状态数据集(DAiSEE),分析其在学习者参与度检测中的性能,结果显示提出的模型优于其他模型。In order to test the applicability of using facial expressions to detect the participation level of online learners in their educational activities,three different convolutional neural network models and one proposed convolutional neural network model are studied,including All-CNN,NiN-CNN,and VD-CNN.The new model is raised based on the advantages of three basic models,and the proposed model replaces linear convolutional layers with multi-layer perceptrons and uses small(3×3)convolutional filters to increase the depth of the network,and replaces some max pooling layers with convolutional layers with increased stride.The four models are applied to the Dataset for Affective States in E-Learning Environments(DAiSEE),and their performance in detecting learner participation is analyzed.The results show that the proposed model performs better than the other models.

关 键 词：深度学习 卷积神经网络 在线学习环境 参与度检测 面部表情 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]