A Neural Network-Based Teaching Style Analysis Model
Sheng Li, Zanhan Ding, Honglv Chen · 2019
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.