基于轻量化网络的课堂学生学习状态判别
Learning State Discrimination of Classroom Students Based on Lightweight Network
DOI: 10.12677/CSA.2021.114121, PDF,    科研立项经费支持
作者: 刘秋会, 王 林, 梁明秀：贵州民族大学数据科学与信息工程学院，贵州 贵阳
关键词: 深度学习；课堂学生学习状态判别；Mobilenetv2；Swish；Deep Learning； Classroom Student Learning State Detection； Mobilenetv2； Swish
摘要: 课堂学习状态判别是了解学生课堂学习情况及教师授课情况的关键步骤，轻量化网络能够提高学习状态的判别精度，轻量化网络是在神经网络算法的基础上进行优化的网络，在本文中，我们采用改进的轻量化网络Mobilnetv2对教室课堂学生学习状态进行判别，实验结果表明，通过提出的方法得到的课堂学生学习状态判别最高达到了99.00%的精度。
Abstract: Classroom learning status discrimination is a key step to understand students’ classroom learning status and teachers’ teaching status. Lightweight networks can improve the accuracy of learning status. Lightweight networks are optimized networks based on neural network algorithms. In this article, the improved lightweight network Mobilnetv2 is used to discriminate the learning status of classroom students. The experimental results show that the accuracy of class student learning status discrimination obtained by the proposed method is up to 99.00%.
文章引用：刘秋会, 王林, 梁明秀. 基于轻量化网络的课堂学生学习状态判别[J]. 计算机科学与应用, 2021, 11(4): 1173-1185. https://doi.org/10.12677/CSA.2021.114121

参考文献

[1] 左国才, 吴小平, 苏秀芝, 等. 基于CNN人脸识别模型的大学生课堂行为分析研究[J]. 智能计算机与应用, 2019, 9(6): 107-110.
[2] 李芙蓉. 基于MTCNN的多特征融合学生疲劳检测[J]. 信息技术, 2020, 44(6): 108-113, 120.
[3] 唐康, 先强, 李明勇. 基于人脸检测的大学课堂关注度研究[J]. 重庆师范大学学报(自然科学版), 2019, 36(5): 123.
[4] Lecun, Y., Bottou, L., Bengio, Y., et al. (1998) Gradient-Based Learning Applied to Document Recog-nition. Proceedings of the IEEE, 86, 2278-2324.
://doi.org/10.1109/5.726791
[5] León, M.D., Moreno-Báez, A., Magallanes-Quintanar, R., et al. (2011) Assessment in Subsets of MNIST Handwritten Digits and Their Effect in the Recognition Rate. Journal of Pattern Recognition Research, 2, 244-252.
://doi.org/10.13176/11.348
[6] Krizhevsky, A., Sutskever, I. and Hinton, G. (2012) ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012, Lake Tahoe, 3-6 December 2012, 1097-1105.
[7] 蒋昂波, 王维维. ReLU激活函数优化研究[J]. 传感器与微系统, 2018, 37(2): 50-52.
[8] Szegedy, C., Liu, W., Jia, Y., et al. (2016) Going Deeper with Convolutions. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, 7-12 June 2015, 1-9.
://doi.org/10.1109/CVPR.2015.7298594
[9] Simonyan, K. and Zisserman, A. (2014) Very Deep Convolutional Networks for Large-Scale Image Recognition.
[10] He, K., Zhang, X., Ren, S., et al. (2016) Deep Resid-ual Learning for Image Recognition. IEEE Conference on Computer Vision & Pattern Recognition, Las Vegas, 27-30 June 2016, 770-778.
://doi.org/10.1109/CVPR.2016.90
[11] Bordes, A., Bottou, L. and Gallinari, P. (2009) SGD-QN: Careful Quasi-Newton Stochastic Gradient Descent. Journal of Machine Learning Research, 10, 1737-1754.
[12] Xie, S., Girshick, R., Dollár, P., et al. (2017) Aggregated Residual Transformations for Deep Neural Networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 5987-5995.
://doi.org/10.1109/CVPR.2017.634
[13] Hu, J., Shen, L. and Sun, G. (2018) Squeeze-and-Excitation Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-22 June 2018, 7132-7141.
://doi.org/10.1109/CVPR.2018.00745
[14] Howard, A.G., Zhu, M., Chen, B., et al. (2017) MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.
[15] Sandler, M., Howard, A., Zhu, M., et al. (2018) MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-22 June 2018, 4510-4520.
://doi.org/10.1109/CVPR.2018.00474