<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>This study provides an in-depth research on the dynamic allocation of resources in higher education teaching and learning, especially in the application of edge intelligence architecture. In the study, the characteristics of edge intelligence and its application in smart mobile devices (SMDs) are first analyzed, highlighting the role of mobile edge computing (MEC) in reducing latency and improving the quality of user experience. Then, the study adopts a data acquisition method based on deep neural network (DNN) model to optimize the edge training model. The experimental results show that the efficiency of edge computing can be significantly improved by optimizing the allocation of computing resources and reducing the data transmission delay. Specifically, the total training delay and energy consumption of the edge server are reduced under different global iteration numbers in the experiment. In addition, the study also explores the integration of 5G networks and AR/VR technology in education. It proposes a teaching optimization model based on edge intelligence, improving interaction quality and learning efficiency in AR/VR safety education classrooms. The study shows that the teaching model performs well in reducing latency and increasing transmission rate, which is especially suitable for dual-teacher classroom scenarios and provides a new perspective for future higher education teaching.</p>
</abstract>

This study provides an in-depth research on the dynamic allocation of resources in higher education teaching and learning, especially in the application of edge intelligence architecture. In the study, the characteristics of edge intelligence and its application in smart mobile devices (SMDs) are first analyzed, highlighting the role of mobile edge computing (MEC) in reducing latency and improving the quality of user experience. Then, the study adopts a data acquisition method based on deep neural network (DNN) model to optimize the edge training model. The experimental results show that the efficiency of edge computing can be significantly improved by optimizing the allocation of computing resources and reducing the data transmission delay. Specifically, the total training delay and energy consumption of the edge server are reduced under different global iteration numbers in the experiment. In addition, the study also explores the integration of 5G networks and AR/VR technology in education. It proposes a teaching optimization model based on edge intelligence, improving interaction quality and learning efficiency in AR/VR safety education classrooms. The study shows that the teaching model performs well in reducing latency and increasing transmission rate, which is especially suitable for dual-teacher classroom scenarios and provides a new perspective for future higher education teaching.

Optimization of Higher Education Teaching Methodology System Based on Edge Intelligence

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

This study provides an in-depth research on the dynamic allocation of resources in higher education teaching and learning, especially in the application of...

Optimization of Higher Education Teaching Methodology System Based on Edge Intelligence

Publié en ligne: 26 févr. 2024

Pages: -

Reçu: 15 janv. 2024

Accepté: 20 janv. 2024

DOI: https://doi.org/10.2478/amns-2024-0619

Mots clés
Mobile edge computing, Deep neural network, Dynamic allocation of resources, Educational teaching methods

© 2023 Jingjing Guo et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Optimization of Higher Education Teaching Methodology System Based on Edge Intelligence

Publié en ligne: 26 févr. 2024

Pages: -

Reçu: 15 janv. 2024

Accepté: 20 janv. 2024

DOI: https://doi.org/10.2478/amns-2024-0619

Mots clésMobile edge computing, Deep neural network, Dynamic allocation of resources, Educational teaching methods

© 2023 Jingjing Guo et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Mots clés
Mobile edge computing, Deep neural network, Dynamic allocation of resources, Educational teaching methods