DRN-LSTM: A Deep Residual Network Based On Long Short-term Memory Network For Students Behaviour Recognition In Education

Abstract

In classroom teaching, artificial intelligence technology can help automate student behavior analysis and enable teachers to master learning efficiently and intuitively provide data support for subsequent optimization of teaching design and implementation of teaching intervention, this paper proposes a residual network based on long short-term memory network. Long short-term memory network (LSTM) is introduced on the basis of deep residual network, in which LSTM can effectively capture the temporal information of students’ behaviors. The Dropout layer is introduced into the residual block to improve the accuracy and convergence speed of student behavior recognition. Finally, four behaviors closely related to learning engagement state are selected for recognition: sitting, side-turning, lowering head and raising hand. The accuracy of the detection and recognition method in the verification set reaches 96.56%. The recognition accuracy of common behaviors such as playing mobile phone and writing in class is greatly improved compared with the original model.

Keywords

• deep residual network
• lstm
• dropout
• education
• student behaviour recognition