A Neural Network-Based Teaching Style Analysis Model

Human motion detection and behavior analysis have become research hotspots in the field of artificial intelligence. This paper proposes a teaching style analysis model based on neural networks to solve the problem that the teaching evaluation of colleges and universities is not objective and not comprehensive and the students select their courses blindly. The model uses OpenPose to extract the coordinates of the key points and the human-body skeleton diagram, and then uses the DenseNet to classify the actions. The action activity evaluation model is then used to evaluate the teachers' activity level during the lectures. And the emotion analysis model of Microsoft is used to analyze the emotions of the teachers during lectures. We use the self-made dataset to test and analyze the model, and the results fully prove the validity of the model.

[1]  Nicole P. Pitterson,et al.  Investigating current approaches to assessing teaching evaluation in engineering departments , 2016, 2016 IEEE Frontiers in Education Conference (FIE).

[2]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Nanning Zheng,et al.  Concurrent Action Detection with Structural Prediction , 2013, 2013 IEEE International Conference on Computer Vision.

[4]  Zhang Jun,et al.  Teaching Evaluation Model Research Based on Integration of Information Technology , 2015, 2015 8th International Conference on Intelligent Computation Technology and Automation (ICICTA).

[5]  Thierry Dutoit,et al.  Action recognition based on 2D skeletons extracted from RGB videos , 2019, MATEC Web of Conferences.

[6]  Pingping Gu,et al.  Cluster Analysis on the Teaching Evaluation Data from College Students , 2018, 2018 13th International Conference on Computer Science & Education (ICCSE).

[7]  Xiaoyu Wu,et al.  Static Human Gesture grading based on Kinect , 2012, 2012 5th International Congress on Image and Signal Processing.

[8]  P. Ekman.  Universals and cultural differences in facial expressions of emotion. , 1972 .

[9]  Yaser Sheikh,et al.  OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.