StayOnTrack: Student Attention Scoring Using Facial and Behavioral Cue Analysis

This paper suggested the attention monitoring system named as StayOnTrack that monitors student attention in real-time for improving student engagement in online learning environments using artificial intelligence. The framework uses Computer Vision and Machine Learning methods to make inferences from the behavioral clues of the eye movements, gaze direction, facial landmarks, and head pose based on the input from a webcam. The use of Eye Aspect Ratio (EAR), gaze detection and head pose estimation provided a good measure of attentive, distracted and drowsy states. Experimental results demonstrated good real-time performance for attention classification under low computational demands and also efficient and practical performance for virtual classrooms using the Random Forest classifier. There are also alert systems and dashboard analytics for teachers and parents to track engagement trends in the system. Also, no raw video data are saved, using a privacy-focused approach, only behavioral metrics. In conclusion, StayOnTrack shows that AI-driven behaviour analysis can be a useful tool for enhancing attentiveness monitoring in virtual classrooms.

[1]     M. A. Khan, A. Raza, and M. Ahmad, “Student Attentiveness Monitoring: A Surveillance System for Virtual Classes,” International Journal of Scientific Research in Engineering and Management (IJSREM), vol. 7, no. 5, pp. 122–129, 2023. [2]   K. Praveen, R. Anitha, and S. Ghosh, “Machine Learning Applied to Student Attentiveness Detection Using Emotional and Non-Emotional Measures,” in Lecture Notes in Networks and Systems, Springer, 2023, pp. 645–654. [3]     A. Setiawan and R. Nurul, “An Adaptive System for Predicting Student Attentiveness in Online Classrooms,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 29, no. 1, pp. 91–100, 2023. [4]     Z. Lin, H. Zhao, and J. Chen, “Real-Time Attention Monitoring System for Classroom: A Deep Learning Approach for Student Behavior Recognition,” Big Data and Cognitive Computing, vol. 7, no. 1, pp. 31–39, 2023. [5]    H. Patel and R. Sharma, “An Automated Online Proctoring System Using Attentive-Net to Assess Student Mischievous Behavior,” in Advances in Artificial Intelligence and Data Engineering, Springer, 2023, pp. 819–829. [6]     A. Alqahtani and J. Smith, “Deep Learning for Cognitive Attention Recognition in E-Learning Environments,” International Journal of Advanced Computer Science and Applications (IJACSA), vol. 14, no. 2, pp. 78–85, 2023. [7]    A. Kumar and P. Das, “Attention Detection Using Facial Features and Eye Tracking in Virtual Classrooms,” Journal of Artificial Intelligence Research, vol. 82, no. 4, pp. 555–566, 2023. [8]        V. Reddy and K. Raj, “Enhancing Virtual Learning with Real-Time Attention Detection Using Deep Learning and Computer Vision,” IEEE Access, vol. 12, pp. 4332–4345, 2024. [9]        G. Bradski, “The OpenCV Library,” Dr. Dobb’s Journal of Software Tools, vol. 25, no. 11, pp. 120–126, 2000. [10]      F. Schroff, D. Kalenichenko, and J. Philbin, “FaceNet: A Unified Embedding for Face Recognition and Clustering,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015, pp. 815–823.