• SRI HARIKA MANI DODDABOINA
• RAKESH KANCHARLA
• SRIVALLI PINNINTI
• SURYA VENKATA BHAVANI KOUJULA
• LAKSHMI BHAVANI DONGA

In an era of quickly growing educational frameworks and digital change, student activity recognition has become a vital area. Activity identification systems are a vast subject of research and development, presently with a focus on advanced machine learning, deep learning algorithms, and reducing the costs of monitoring. The research largely focuses on the applications of activity recognition systems and surveys. This complete article covers student activity recognition, covering its methodology, uses, and consequences in the area of education. The applications are categorized according to the methodology utilized for identifying human activity, namely as based on visual, non-visual, and multimodal sensor technologies. This presents an overview of different applications and explores the merits and limits of each strategy. Additionally, we present public datasets that are created for the assessment of such identification algorithms. Further The study finishes with a comparison of the available strategies that, when applied to real-world settings, enable the development of research topics for future approaches.

Student Activity Recognition (SVR), Human Activity Classification (HAC), Deep Learning Algorithms, Machine Learning Algorithms.

"Video-Based Student Activity Recognition Using Deep Learning : A Comprehensive Review", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.c429-c434, March-2024, Available :http://www.jetir.org/papers/JETIR2403254.pdf

"Video-Based Student Activity Recognition Using Deep Learning : A Comprehensive Review", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppc429-c434, March-2024, Available at : http://www.jetir.org/papers/JETIR2403254.pdf