Detecting Levels of Learning Concentration Through Student Behavior in the Classroom Using Convolutional Neural Networks (CNN)
DOI:
https://doi.org/10.62951/ijamc.v2i1.74Keywords:
CNN, Computer Vision, Concentration, Learning, MobileNetV2Abstract
This study discusses a student concentration detection system using Convolutional Neural Network (CNN) with the MobileNetV2 architecture. The dataset was adapted from Classroom Student Behaviors and mapped into four concentration categories: highly focused, focused, less focused, and unfocused. The system was tested with a 720p webcam and produced real-time detection data. The evaluation results show an overall accuracy of 75.85%, with the highest precision achieved in the focused class (0.9859) and the highest recall in the highly focused (0.9739) and unfocused (0.9811) classes. The confusion matrix indicates that the focused class was detected most consistently, while highly focused and unfocused classes were often misclassified as focused, resulting in lower precision. In real-time testing, the system operated at an average of 7 FPS and worked optimally when students faced the camera directly with sufficient lighting, but its performance decreased significantly at face angles greater than 45°. User evaluation shows that 75% of students rated the detection results as accurate/very accurate with an average satisfaction score of 3.6 out of 5, and 75% felt assisted in recognizing their concentration level. From the teachers’ perspective, most stated that the results were consistent with classroom observations, and all expressed willingness to reuse the system.
References
Abadi, M., et al. (2016). TensorFlow: A system for large-scale machine learning. In Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (OSDI) (pp. 265–283). USENIX Association.
Alperin, A., et al. (2023). Convergent validity of the Behavior Observation of Students in Schools (BOSS) form. Psychology in the Schools, 60(10), 2031–2045.
Alruwais, N., & Zakariah, M. (2025). Detecting student engagement with convolution neural network and facial expression recognition. Technical Sciences Journal, 42(2), 943–961. https://doi.org/10.18280/ts.420229
Ansari, M. F., Kasprowski, P., & Obetkal, M. (2021). Gaze tracking using an unmodified web camera and convolutional neural network. Applied Sciences, 11(19), 9068. https://doi.org/10.3390/app11199068
Arifin, S., Aisjah, A. S., Fatima, A. N., & Mahmudah, H. (2020). Design and development of a system for monitoring student attention and concentration using CNN model and face landmark detection. In Proceedings of the 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) (pp. 170–175). IEEE. https://doi.org/10.1109/ISRITI51436.2020.9315513
Avon-Washington County Schools. (2015). Systematic behavior observation form. Avon Central School District.
Dewan, M. L., Sharma, R., & Kumar, M. (2019). Engagement detection in online learning: A review. Smart Learning Environments, 6(1), 1–21. https://doi.org/10.1186/s40561-019-0094-0
Dimyati, & Mudjiono. (2009). Belajar dan pembelajaran. Rineka Cipta.
Gonzalez, R. C., & Woods, R. E. (2008). Digital image processing (3rd ed.). Pearson Prentice Hall.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
Gupta, A., D’Mello, S., & Baker, R. (2017). Data set for affective states in e-learning environments (DAiSEE). In Proceedings of the 8th International Conference on Affective Computing and Intelligent Interaction (pp. 236–242). IEEE.
Hintze, J. M., Volpe, R. J., & Shapiro, E. S. (2002). Best practices in the systematic direct observation of student behavior. In A. Thomas & J. Grimes (Eds.), Best practices in school psychology IV (pp. 999–1020). National Association of School Psychologists.
Jia, Q., & He, J. (2024). Student behavior recognition in classroom based on deep learning. Applied Sciences, 14(17), 7981. https://doi.org/10.3390/app14177981
Kluyver, T., et al. (2016). Jupyter notebooks—A publishing format for reproducible computational workflows. In F. Loizides & B. Schmidt (Eds.), Positioning and power in academic publishing: Players, agents and agendas (pp. 87–90). IOS Press.
Li, X., Song, D., & Lu, B.-L. (2016). Emotion recognition based on EEG using hybrid deep learning model. In 2016 International Joint Conference on Neural Networks (IJCNN) (pp. 1013–1018). IEEE.
Qi, J., Zhang, H., Liu, X., Yang, W., & Zhang, M. (2024). Application of face detection for learning engagement in the classroom. Electronics, 13, 149. https://doi.org/10.3390/electronics13010149
Qi, Y., Zhuang, L., Chen, H., Han, X., & Liang, A. (2023). Evaluation of students’ learning engagement in online classes based on multimodal vision perspective. Electronics, 13(1), Article 149. https://doi.org/10.3390/electronics13010149
Rasiban, J., & Praja Raymond Maruli, S. (2022). Penerapan data mining untuk memprediksi penerimaan peserta didik baru. Journal of Military Science and Technology, 3, 22–29. https://doi.org/10.54930/1859-1043.j.mst.83.2022.22-29
Slameto. (2010). Belajar dan faktor-faktor yang mempengaruhinya. Rineka Cipta.
Szeliski, R. (2022). Computer vision: Algorithms and applications (2nd ed.). Springer.
Wang, Z., Wang, M., Zeng, C., & Li, L. (2024). Multi-scale deformable transformers for student learning behavior detection in smart classroom (arXiv:2410.07834). arXiv. https://arxiv.org/abs/2410.07834
Whitehill, J., Serpell, Z., Lin, Y.-C., Foster, A., & Movellan, J. R. (2014). The faces of engagement: Automatic recognition of student engagement from facial expressions. IEEE Transactions on Affective Computing, 5(1), 86–98. https://doi.org/10.1109/TAFFC.2014.2316244
Winkel, W. S. (2009). Psikologi pengajaran. Gramedia.
Zheng, W.-L., & Lu, B.-L. (2015). Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks. IEEE Transactions on Autonomous Mental Development, 7(3), 162–175.
Zhou, H., Jiang, F., Si, J., Xiong, L., & Lu, H. (2023). StuArt: Individualized classroom observation of students with automatic behavior recognition and tracking (arXiv:2111.03127v3). arXiv. https://arxiv.org/abs/2111.03127
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Applied Mathematics and Computing
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
