Towards Analyzing Student Engagement: A Deep Learning System for Classroom Behavior Recognition
Keywords:
Deep learning, Student classroom behavior, Recognition systemAbstract
This study proposes a deep-learning-based student classroom behavior recognition system aimed at accurately detecting and analyzing student classroom behaviors through intelligent means. The system adopts a modular design covering five modules: data acquisition, preprocessing, model training, behavior recognition, and visual interaction. Centered on the YOLOv8 algorithm, model performance is optimized by adjusting parameters such as iteration count and learning rate. A dataset of 3200 training images and 800 test images is split at an 8:2 ratio. Techniques including Mosaic data augmentation, adaptive anchor calculation, and SPP/PAN feature fusion are employed to enhance the model’s multi-scale object detection capability. The loss function comprises bounding-box loss, class loss, and confidence loss to ensure detection accuracy.
References
Gao W and Gorinevsky D 2020 Probabilistic modeling for optimization of resource mix with variable generation and storage IEEE Trans. Power Syst. 35 4036–45
Guo, Y. (2025). The Optimal Trajectory Control Using Deterministic Artifi cial Intelligence for Robotic Manipulator. Industrial Technology Research, 2(3).
Guo, Y. (2025, May). IMUs Based Real-Time Data Completion for Motion Recognition With LSTM. In Forum on Research and Innovation Management (Vol. 3, No. 6).
Guo, Y., & Tao, D. (2025). Modeling and Simulation Analysis of Robot Environmental Interaction. Artificial Intelligence Technology Research, 2(8).
Wei, Xiangang, et al. "AI driven intelligent health management systems in telemedicine: An applied research study." Journal of Computer Science and Frontier Technologies 1.2 (2025): 78-86.
Zhang, Yujun, et al. "MamNet: A Novel Hybrid Model for Time-Series Forecasting and Frequency Pattern Analysis in Network Traffic." arXiv preprint arXiv:2507.00304 (2025).
Peng, Qucheng, Ce Zheng, and Chen Chen. "A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024.
Peng, Qucheng, et al. "RAIN: regularization on input and network for black-box domain adaptation." Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence. 2023.
Chen, J., Zhang, X., Wu, Y., Ghosh, S., Natarajan, P., Chang, S. F., & Allebach, J. (2022). One-stage object referring with gaze estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 5021-5030).
Zhang, Jingbo, et al. "AI-Driven Sales Forecasting in the Gaming Industry: Machine Learning-Based Advertising Market Trend Analysis and Key Feature Mining." (2025).
Zhang, Yuhan. "CrossPlatformStack: Enabling High Availability and Safe Deployment for Products Across Meta Services." (2025).
Hu, Xiao. "AdPercept: Visual Saliency and Attention Modeling in Ad 3D Design." (2025).
Li, X., Lin, Y., & Zhang, Y. (2025). A Privacy-Preserving Framework for Advertising Personalization Incorporating Federated Learning and Differential Privacy. arXiv preprint arXiv:2507.12098.
Tu, Tongwei. "AutoNetTest: A Platform-Aware Framework for Intelligent 5G Network Test Automation and Issue Diagnosis." (2025).
Zhu, Bingxin. "ReliBridge: Scalable LLM-Based Backbone for Small Business Platform Stability." (2025).
Hu, Xiao. "Learning to Animate: Few-Shot Neural Editors for 3D SMEs." (2025).
Tan, C., Gao, F., Song, C., Xu, M., Li, Y., & Ma, H. (2024). Proposed Damage Detection and Isolation from Limited Experimental Data Based on a Deep Transfer Learning and an Ensemble Learning Classifier.
Xie, Minhui, and Shujian Chen. "Maestro: Multi-Agent Enhanced System for Task Recognition and Optimization in Manufacturing Lines." Authorea Preprints (2025).
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Linying Yan
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
