ZHOU Jian-guo,TANG Dong-ming,PENG Zheng,et al.Students' Expression Analysis in the Classroom based on Gradient Boosting Decision Tree and Convolution Neural Network[J].Journal of Chengdu University of Information Technology,2017,(05):508-512.[doi:10.16836/j.cnki.jcuit.2017.05.008]
基于卷积神经网络的课堂表情分析软件研究与实现
- Title:
- Students' Expression Analysis in the Classroom based on Gradient Boosting Decision Tree and Convolution Neural Network
- 文章编号:
- 2096-1618(2017)05-0508-05
- 关键词:
- 卷积神经网络; 梯度提升决策树(GBDT); 特征提取; 模型融合
- Keywords:
- convolution neural network; gradient boosting decision tree; feature extraction; model fusion
- 分类号:
- TP391
- 文献标志码:
- A
- 摘要:
- 课堂上听众的面部表情是听众的心理状态的一个表征,通过分析听众的面部表情数据可以用于评估和改善教学效果。提出利用卷积神经网络分析学生课堂面部表情,进而辅助分析和研究学生们在课堂的专注程度和帮助教师改善教学过程。引入梯度提升方法与卷积神经网络相结合的方式来描述学生表情的图片特征,通过训练神经网络并将其作为图片特征萃取器,使用梯度提升决策树将特征映射至更高维度空间,并融合二者特征进行分类。最后在实际的手机应用中通过使用提出的模型来进行课堂表情数据分析,能够有效地分析课堂上学生的听课情况并帮助教师提升教学效果。
- Abstract:
- The facial expression of the students in the classroom is a representation of the mental state of the students, and the facial expression data of the audience can be used to assess the teaching effect. This paper proposes the use of CNN(convolutional neural network)to analyze students` facial expressions, and then study students facial expression so as to helping teachers improving the teaching process. In this paper, we combine GBDT(gradient boost decision tree)and CNN to describe the characteristics of the pictures. By training the neural network and using it as the image feature extractor, we use the GBDT to map the feature to higher dimension space and then according to the characteristics of the two categories to classified. Finally, in the practical application, it can effectively analyze the lectures of the students in the classroom and help the teachers to improve the teaching effect.
参考文献/References:
[1] 张翠平,苏光大.人脸识别技术综述[J].中国图像图形学报:A辑,2000(11):885-894.
[2] 梁路宏,艾海舟,徐光祐,等.人脸检测研究综述[J].计算机学报,2002,25(5):449-458.
[3] 李华胜,杨桦,袁保宗.人脸识别系统中的特征提取[J].北方交通大学学报,2001,25(2):18-21.
[4] 王聃,贾云伟,林福严.人脸识别系统中的特征提取[J].微计算机信息,2005,21(07X):53-55.
[5] Bouvrie J.Notes on convolutional neural networks[J].2006.
[6] Friedman J H.Greedy function approximation:a gradient boosting machine[J].Annals of statistics,2001:1189-1232.
[7] Elith J,Leathwick J R,Hastie T.A working guide to boosted regression trees[J].Journal of Animal Ecology,2008,77(4):802-813.
[8] He K,Zhang X,Ren S,et al.Deep residual learning for image recognition[C].Proceedings of the IEEE conference on computer vision and pattern recognition.2016:770-778.
[9] Szegedy C,Liu W,Jia Y,et al.Going deeperwith convolutions[C].Proceedings of the IEEE conference on computer vision and pattern recognition.2015:1-9.
[10] Krizhevsky A,Sutskever I,Hinton G E.Imagenet classification with deep convolutional neural networks[C].Advances in neural information processing systems.2012:1097-1105.
[11] 李航.统计学习方法[M].北京:清华大学出版社,2012.
[12] 苏耶亚塔·兰尼.用以提升教学效果的情感分析系统[J].计算科学评论,2017,6(1):34-41.
[13] 卢家楣.课堂教学的情感目标分类[J].心理科学,2006,29(6):1291-1295.
[14] Mishra,Brojo Kishore,Sahoo.Abhaya Kumar Source Evaluation of Faculty Performance in Education System Using Classification Technique in Opinion Mining Based on GPU Computational Intelligence in Data Mining.2016,(2):109-119.
相似文献/References:
[1]曹家华,吴 震,王 燚,等.基于CNN-BPR的S-Box功耗随机化侧信道攻击[J].成都信息工程大学学报,2022,37(01):16.[doi:10.16836/j.cnki.jcuit.2022.01.003]
CAO Jiahua,WU Zhen,WANG Yi,et al.Side Channel Attack of S-box Power Randomization based on CNN-BPR[J].Journal of Chengdu University of Information Technology,2022,37(05):16.[doi:10.16836/j.cnki.jcuit.2022.01.003]
[2]李孝涌,陈科艺,李熙晨.卷积神经网络在ENSO预报中的应用[J].成都信息工程大学学报,2022,37(01):81.[doi:10.16836/j.cnki.jcuit.2022.01.014]
LI Xiaoyong,CHEN Keyi,LI Xichen.Application of Convolutional Neural Network in ENSO Prediction[J].Journal of Chengdu University of Information Technology,2022,37(05):81.[doi:10.16836/j.cnki.jcuit.2022.01.014]
备注/Memo
收稿日期:2017-09-06 基金项目:国家自然科学基金资助项目(61003101-131-4)