Recognition of students’ behavior states in classroom based on improved MobileNetV2 algorithm

Abstract

Analyzing and learning students' behavior states in classroom plays a positive role in understanding and improving the teaching effectiveness. Meanwhile, the application of lightweight network to pattern recognition has become a trend with the development of mobile networks. In order to improve the recognition accuracy of the lightweight network model MobileNetV2 and reduce the computational cost and delay caused by extracting rich features, an improved lightweight network model based on MobileNetV2 is proposed, in which an improved reverse residual module (C-Inverted residual block) is applied to replace the traditional module. In the improved reverse residual module, channel split operation is added to reduce MAC, and channel shuffle operations are used to promote information exchange and channel fusion. Experiments were carried out on Pascal VOC 2007 detection data set to test the general performance of the proposed improved model. Under the operation limits of 140 MFLOPS, 40 MFLOPS and 20 MFLOPS, mean average precision (mAP) of the improved MobileNetV2 algorithm increased by 1.2%, 2.2% and 4.3% compared with MobileNetV2. While the recognition accuracy of the proposed network model on self-made dataset of student classroom behavior states is 4.6% and 3.7% higher than that of MobileNetV1 and MobileNetV2 respectively, and the average recognition rate of students' classroom behavior states can be up to 92.7%. The results of this research combined with mobile networks would be expected to be used to evaluate teaching and learning effects and promote teaching quality improvement.