Student Action Recognition for Improving Teacher Feedback During Tele-Education

Dimitriadou, Eleni; Lanitis, Andreas

doi:10.1109/tlt.2023.3301094

Cited by 4 publications

(1 citation statement)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial intelligence (AI) offers numerous benefits and opportunities to understand the engagement level of students and teachers and transforms the way students learn, teachers teach, and educational institutions operate [4,8,9]. It can be useful in applications from personalised learning to adaptive learning platforms [10]. This kind of analysis could contribute to developing more effective teaching strategies and personalised learning experiences and improve student outcomes by leveraging the capabilities of AI in combination with human action recognition (HAR) techniques.…”

Section: Introductionmentioning

confidence: 99%

STAR-3D: A Holistic Approach for Human Activity Recognition in the Classroom Environment

Sharma,

Gupta,

Kumar

et al. 2024

Information

View full text Add to dashboard Cite

The video camera is essential for reliable activity monitoring, and a robust analysis helps in efficient interpretation. The systematic assessment of classroom activity through videos can help understand engagement levels from the perspective of both students and teachers. This practice can also help in robot-assistive classroom monitoring in the context of human–robot interaction. Therefore, we propose a novel algorithm for student–teacher activity recognition using 3D CNN (STAR-3D). The experiment is carried out using India’s indigenously developed supercomputer PARAM Shivay by the Centre for Development of Advanced Computing (C-DAC), Pune, India, under the National Supercomputing Mission (NSM), with a peak performance of 837 TeraFlops. The EduNet dataset (registered under the trademark of the DRSTATM dataset), a self-developed video dataset for classroom activities with 20 action classes, is used to train the model. Due to the unavailability of similar datasets containing both students’ and teachers’ actions, training, testing, and validation are only carried out on the EduNet dataset with 83.5% accuracy. To the best of our knowledge, this is the first attempt to develop an end-to-end algorithm that recognises both the students’ and teachers’ activities in the classroom environment, and it mainly focuses on school levels (K-12). In addition, a comparison with other approaches in the same domain shows our work’s novelty. This novel algorithm will also influence the researcher in exploring research on the “Convergence of High-Performance Computing and Artificial Intelligence”. We also present future research directions to integrate the STAR-3D algorithm with robots for classroom monitoring.

show abstract

Section: Introductionmentioning

confidence: 99%

STAR-3D: A Holistic Approach for Human Activity Recognition in the Classroom Environment

Sharma,

Gupta,

Kumar

et al. 2024

Information

View full text Add to dashboard Cite

show abstract

An integrated framework for developing and evaluating a lecture style assessment methodology

Dimitriadou,

Lanitis

2024

Multimed Tools Appl

View full text Add to dashboard Cite

Research on Monitoring Teaching Activities Based on Image Recognition in Educational Management Informatization Construction of Colleges and Universities

Liu,

Ran

2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

Teaching activity monitoring is an important part of the development of educational management informationization in colleges and universities. In this paper, we initially integrate the FDRL model with the self-attention mechanism to create the IMEDRL model, a tool for identifying the micro-expression categories of students during teaching activities. Then, the YOLOv5 model is added with the CA attention mechanism, and the loss function is replaced from CIOU to SIOU to get the IM-YOLOv5 model, which is used to detect the behavioral categories of students in teaching activities. Finally, a teaching activity monitoring system was designed based on these two models and used in actual teaching activity monitoring to explore the application effect of the models in the system. The IMEDRL model achieved an average recognition rate of 95.2% and 91.4% on the two public datasets, CK+ and Oulu-CASIA, respectively. The training and testing convergence on the teaching activity video dataset was superior, and the recognition accuracy rate reached 87.48%, demonstrating the model’s strong practical value. IM-YOLOv5 compared to YOLOv5, the FPS is basically the same, the number of parameters only increases by 8.72%, and the mAP0.5 and mAP0.5:0.95 improve by 0.99% and 1.65%, respectively. Among the 16 indicators of the 8 behaviors, 14 of the 8 behaviors of IM-YOLOv5 are higher than those of YOLOv5, confirming the feasibility of this study to improve YOLOv5. The monitoring system of teaching activities designed in this paper has a strong practicality, which is conducive to promoting informationization in education management in colleges and universities.

show abstract

Student Action Recognition for Improving Teacher Feedback During Tele-Education

Cited by 4 publications

References 69 publications

STAR-3D: A Holistic Approach for Human Activity Recognition in the Classroom Environment

STAR-3D: A Holistic Approach for Human Activity Recognition in the Classroom Environment

An integrated framework for developing and evaluating a lecture style assessment methodology

Research on Monitoring Teaching Activities Based on Image Recognition in Educational Management Informatization Construction of Colleges and Universities

Contact Info

Product

Resources

About