Improved Convolutional Neural Networks for Course Teaching Quality Assessment

Abstract

The cultivation of innovative talents is closely related to the quality of course teaching, and there is a correlation between facial expressions and the effectiveness of classroom teaching. In this paper, a separate long-term recursive convolutional network (SLRCN) microexpression recognition algorithm is proposed using deep learning technology for building a course teaching effectiveness evaluation model. Firstly, facial image sequences are extracted from microexpression data sets, and the transfer learning method is introduced to extract spatial features of facial expression frames through pretrained convolutional neural network model to reduce the risk of overfitting in network training. The extracted features of video sequences were input into long short-team memory (LSTM) to process temporal features. Experimental results show that SLRCN algorithm has the best performance in training set and test set. It has the best performance in ROC curve. This effectively distinguishes between seven different expressions in the database. The model proposed in this paper can obtain the changes of students' facial expressions in class and evaluate students' learning status, thus promoting the improvement of teaching quality. It provides a new method of course teaching quality evaluation.