Student Learning Behavior Recognition Incorporating Data Augmentation with Learning Feature Representation in Smart Classrooms

Abstract

A robust and scientifically grounded teaching evaluation system holds significant importancein modern education, serving as a crucial metric that reflects the quality of classroominstruction. However, current methodologies within smart classroom environments have distinctlimitations. These include accommodating a substantial student population, grappling with objectdetection challenges due to obstructions, and encountering accuracy issues in recognition stemmingfrom varying observation angles. To address these limitations, this paper proposes an innovativedata augmentation approach designed to detect distinct student behaviors by leveraging focusedbehavioral attributes. The primary objective is to alleviate the pedagogical workload. The processbegins with assembling a concise dataset tailored for discerning student learning behaviors, followedby the application of data augmentation techniques to significantly expand its size. Additionally, thearchitectural prowess of the Extended-efficient Layer Aggregation Networks (E-ELAN) is harnessedto effectively extract a diverse array of learning behavior features. Of particular note is the integrationof the Channel-wise Attention Module (CBAM) focal mechanism into the feature detection network.This integration plays a pivotal role, enhancing the network’s ability to detect key cues relevant tostudent learning behaviors and thereby heightening feature identification precision. The culminationof this methodological journey involves the classification of the extracted features through adual-pronged conduit: the Feature Pyramid Network (FPN) and the Path Aggregation Network(PAN). Empirical evidence vividly demonstrates the potency of the proposed methodology, yieldinga mean average precision (mAP) of 96.7%. This achievement surpasses comparable methodologiesby a substantial margin of at least 11.9%, conclusively highlighting the method’s superior recognitioncapabilities. This research has an important impact on the field of teaching evaluation system, whichhelps to reduce the burden of educators on the one hand, and makes teaching evaluation moreobjective and accurate on the other hand.