Student Behavior Detection Using YOLOv10 for Classroom Engagement Analysis

Resa Pramudita; Mochamad Rizal Fauzan; Ilyasa Nafan Faza; Jaja Kustija; Ibnu Hartopo; Muhammad Adli Rizqulloh

doi:10.22146/jnteti.v15i2.24611

Resa Pramudita Industrial Automation and Robotics Engineering Education Study Program, Faculty of Engineering Education and Industry, Universitas Pendidikan Indonesia, Bandung, Jawa Barat 40154, Indonesia
Mochamad Rizal Fauzan Department of Electrical Engineering, College of Electrical Engineering and Computer Science, National Taipei University of Technology, Taipei 10608, Taiwan (R.O.C.)
Ilyasa Nafan Faza Industrial Automation and Robotics Engineering Education Study Program, Faculty of Engineering Education and Industry, Universitas Pendidikan Indonesia, Bandung, Jawa Barat 40154, Indonesia
Jaja Kustija Electrical Engineering Education Study Program, Faculty of Engineering Education and Industry, Universitas Pendidikan Indonesia, Bandung, Jawa Barat 40154, Indonesia
Ibnu Hartopo Industrial Automation and Robotics Engineering Education Study Program, Faculty of Engineering Education and Industry, Universitas Pendidikan Indonesia, Bandung, Jawa Barat 40154, Indonesia
Muhammad Adli Rizqulloh Department of Computer Engineering, College of Computing and Mathematics, King Fahd University of Petroleum & Minerals Dhahran, Dhahran 31261, Saudi Arabia

DOI: https://doi.org/10.22146/jnteti.v15i2.24611

Keywords: Student Engagement, YOLOv10, Classroom Behavior Detection, Deep Learning, Real-Time Analytics, Educational Technology

Abstract

Student engagement is a critical determinant of learning effectiveness, yet manual observation in classroom environments remains labor-intensive, subjective, and difficult to scale. This study examined a student behavior detection framework built on You Only Look Once (YOLO) version 10 or YOLOv10, the latest generation of real-time object detection models. A dataset of 2,600 annotated classroom images covering eight behavioral categories was collected under diverse conditions, including variations in lighting, camera perspectives, and occlusion. Five YOLOv10 variants (n, s, m, l, x) were trained and evaluated using precision, recall, F1 score, and mean average precision (mAP). The best-performing configuration achieved an overall mAP@0.5 of 0.821 and mAP@0.5:0.95 of 0.640, with strong performance on upright (AP = 0.967), bow head (AP = 0.958), and sleep (AP = 0.943), while more subtle behaviors such as writing (AP = 0.519) and hand-raising (AP = 0.650) proved challenging. Importantly, the system maintained real-time inference speeds ranging from 40 to 88 FPS depending on the YOLOv10 variant, when evaluated on an RTX 2060 GPU, thereby demonstrating its robustness for deployment in classroom settings. To ensure usability, the optimized YOLOv10 model was integrated into a Streamlit-based interactive dashboard, enabling educators to monitor engagement levels and respond with timely interventions. By combining state-of-the-art YOLOv10 architecture with real-time behavioral analytics, this work establishes a scalable foundation for intelligent classroom monitoring and contributes to advancing technology-enhanced education.

References

L. Li et al., “ET-YOLOv5s: Toward deep identification of students’ in-class behaviors,” IEEE Access, vol. 10, pp. 44200–44211, Apr. 2022, doi: 10.1109/ACCESS.2022.3169586.

D. Zhou et al., “MFDS-STGCN: Predicting the behaviors of college students with fine-grained spatial-temporal activities data,” IEEE Trans. Emerg. Top. Comput., vol. 12, no. 1, pp. 254–265, Jan.-Mar. 2024, doi: 10.1109/TETC.2023.3344131.

Y. Shi, F. Sun, H. Zuo, and F. Peng, “Analysis of learning behavior characteristics and prediction of learning effect for improving college students’ information literacy based on machine learning,” IEEE Access, vol. 11, pp. 50447–50461, May 2023, doi: 10.1109/ACCESS.2023.3278370.

S.A. Amoudi et al., “Click-based representation learning framework of student navigational behavior in MOOCs,” IEEE Access, vol. 12, pp. 121480–121494, Aug. 2024, doi: 10.1109/ACCESS.2024.3450514.

N. Ruiz et al., “ATL-BP: A student engagement dataset and model for affect transfer learning for behavior prediction,” IEEE Trans. Biom. Behav. Identity Sci., vol. 5, no. 3, pp. 411–424, Jul. 2023, doi: 10.1109/TBIOM.2022.3210479.

S. Kim et al., “Characteristic behaviors of elementary students in a low attention state during online learning identified using electroencephalography,” IEEE Trans. Learn. Technol., vol. 17, pp. 619–628, Jun. 2024, doi: 10.1109/TLT.2023.3289498.

X.M. Zhao et al., “Classroom student behavior recognition using an intelligent sensing framework,” IEEE Access, vol. 13, pp. 49767–49776, Mar. 2025, doi: 10.1109/ACCESS.2025.3550921.

H. Liu, R. Hu, H. Dong, and Z. Liu, “SFC-YOLOv8: Enhanced strip steel surface defect detection using spatial-frequency domain-optimized YOLOv8,” IEEE Trans. Instrum. Meas., vol. 74, pp. 1–11, Mar. 2025, doi: 10.1109/TIM.2025.3548193.

S. Tao et al., “MIS-YOLOv8: An improved algorithm for detecting small objects in UAV aerial photography based on YOLOv8,” IEEE Trans. Instrum. Meas., vol. 74, pp. 1–12, Mar. 2025, doi: 10.1109/TIM.2025.3551917.

K. Xu et al., “RMT-YOLOv9s: An infrared small target detection method based on UAV remote sensing images,” IEEE Geosci. Remote Sens. Lett., vol. 21, pp. 1–5, Oct. 2024, doi: 10.1109/LGRS.2024.3484748.

X. Yu et al., “FEL-YoloV8: A new algorithm for accurate monitoring soybean seedling emergence rates and growth uniformity,” IEEE Trans. Geosci. Remote Sens., vol. 63, pp. 1–17, Jun. 2025, doi: 10.1109/TGRS.2025.3578800.

M. Hussain and R. Khanam, “In-depth review of YOLOv1 to YOLOv10 variants for enhanced photovoltaic defect detection,” Solar, vol. 4, no. 3, pp. 351–386, Sep. 2024, doi: 10.3390/solar4030016.

H. Sun et al., “SOD-YOLOv10: Small object detection in remote sensing images based on YOLOv10,” IEEE Geosci. Remote Sens. Lett., vol. 22, pp. 1–5, Jan. 2025, doi: 10.1109/LGRS.2025.3534786.

H. Fu et al., “MSOAR-YOLOv10: Multi-scale occluded apple detection for enhanced harvest robotics,” Horticulturae, vol. 10, no. 12, pp. 1–24, Dec. 2024, doi: 10.3390/horticulturae10121246.

D. Wang et al., “Real-time detection and identification of fish skin health in the underwater environment based on improved YOLOv10 model,” Aquac. Rep., vol. 42, pp. 1–11, Jul. 2025, doi: 10.1016/J.AQREP.2025.102723.

W. Tu et al., “YOLOv10-UDFishNet: Detection of diseased Takifugu rubripes juveniles in turbid underwater environments,” Aquac. Int., vol. 33, pp. 1–27, Jan. 2025, doi: 10.1007/s10499-024-01798-5.

M. Mao, A. Lee, and M. Hong, “Efficient fabric classification and object detection using YOLOv10,” Electronics, vol. 13, no. 19, pp. 1–23, Oct. 2024, doi: 10.3390/electronics13193840.

C. Zhang et al., “A novel YOLOv10-DECA model for real-time detection of concrete cracks,” Buildings, vol. 14, no. 10, pp. 1–24, Oct. 2024, doi: 10.3390/buildings14103230.

Q. Du, S. Zhang, and S. Yang, “BLP-YOLOv10: Efficient safety helmet detection for low-light mining,” J. Real-Time Image Process., vol. 22, pp. 1–11, Nov. 2024, doi: 10.1007/s11554-024-01587-6.

R. Chai et al., “Automated detection of early-stage osteonecrosis of the femoral head in adult using YOLOv10: Multi-institutional validation,” Eur. J. Radiol., vol. 184, pp. 1–9, Mar. 2025, doi: 10.1016/J.EJRAD.2025.111983.

L. Zheng, T. Hu, and J. Zhu, “Underwater sonar target detection based on improved ScEMA-YOLOv8,” IEEE Geosci. Remote Sens. Lett., vol. 21, pp. 1–5, May 2024, doi: 10.1109/LGRS.2024.3397848.

J. Wang et al., “DPH-YOLOv8: Improved YOLOv8 based on double prediction heads for the UAV image object detection,” IEEE Trans. Geosci. Remote Sens., vol. 62, pp. 1–15, Oct. 2024, doi: 10.1109/TGRS.2024.3487191.

Y. Xing et al., “MAM-YOLOv9: A multiattention mechanism network for methane emission facility detection in high-resolution satellite remote sensing images,” IEEE Trans. Geosci. Remote Sens., vol. 63, pp. 1–16, Feb. 2025, doi: 10.1109/TGRS.2025.3545034.

A.S. Geetha, M.A.R. Alif, M. Hussain, and P. Allen, “Comparative analysis of YOLOv8 and YOLOv10 in vehicle detection: Performance metrics and model efficacy,” Vehicles, vol. 6, no. 3, pp. 1364–1382, Sep. 2024, doi: 10.3390/vehicles6030065.

W. Kong et al., “A shadow-robust pavement damage detection framework based on RACycle-GAN and DDE-YOLOv8 IEEE Trans. Intell. Transp. Syst., vol. 26, no. 8, pp. 11342–11355, Aug. 2025, doi: 10.1109/TITS.2025.3556941.

Y. Long, Y. Yang, J. Hu, and X. Huang, “Operating mechanism detection in aluminum electrolysis workshops via YOLOv8-MIE,” IEEE Trans. Instrum. Meas., vol. 74, pp. 1–15, Jan. 2025, doi: 10.1109/TIM.2024.3522436.

L. Zhang et al., “Intelligent psyllid monitoring based on DiTs-YOLOv10-SOD,” IEEE Trans. AgriFood Electron., vol. 3, no. 1, pp. 286–294, Mar./Apr. 2025, doi: 10.1109/tafe.2025.3551072.