AUTHOR=Guangde Zhao 

TITLE=Physical education and emergency response system using deep learning: A step toward sustainable development of physical education environment

JOURNAL=Frontiers in Environmental Science

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/environmental-science/articles/10.3389/fenvs.2022.974291

DOI=10.3389/fenvs.2022.974291

ISSN=2296-665X

ABSTRACT=The physical education (PE) systems' key goal is to educate individuals and the large community of participating students to accomplish self-fulfilment. Deep learning uses integrated expertise to help students master challenging conditions in unfamiliar contexts. When they work together as a team in physical education training, injuries are to be expected. As an emergency response to mitigating students' future risks by the availability of first aid, safety steps are promptly taken. Therefore, this article suggests a Physical Education and Emergency Response System using Deep Learning (PSERS-DL) to handle such situations effectively. In real-time, the PE environment can be tracked using a global positioning system-enabled surveillance system to immediately provide the wounded student with protective measures. The acquired visuals are immediately Analyzed using a deep learning model, Convolutional Neural Network (CNN). The 27 layers proposed CNN model has been evaluated compared with other deep learning models. The simulation results show that the proposed PSERS-DL can assure the emergency response with the highest accuracy of 97.61%. The Experimental results show that the proposed PSERS-DL model enhances an accuracy ratio of 95.6%, a performance ratio of 97.6%, Movement detection analysis Ratio of 96.3%, Learning rate 95.2%, Efficiency Ratio of 98.1%, Security Ratio 93.5%, Delay time ratio 33.2% and Behaviour Analysis Ratio of 90.7% to other existing approaches.