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

<p>As an innovative design, microgrid teaching has great application prospects in teaching practical skills in sports. In this paper, we constructed a knowledge graph based on sport-themed microgrid teaching and updated the knowledge graph with a bottom-up model. In the inference model of the knowledge graph, a gated loop unit is used to make modifications on GNN and unfold a fixed number T of recursions, while time backpropagation is used to compute the gradient to evaluate the students’ sports intensity under the theme-based microgrid teaching. The SSA algorithm improved the ontology rule inference of the core parameters by including sport intensity in the core parameter constraints for the generation of physical education microgram instruction. The RMSE mean of the recommendation algorithm in the optimized optimal sports instruction search was 0.43257 with a standard deviation of 0.05531 and a 95% confidence interval of [0.44149,0.42364]. The use of SSA was able to obtain lower RMSE values under the same model of sports and physical activity similarity calculation. By obtaining the optimal sports instruction program, the sports thematic microgrid teaching model was scientifically guided.</p>
</abstract>

As an innovative design, microgrid teaching has great application prospects in teaching practical skills in sports. In this paper, we constructed a knowledge graph based on sport-themed microgrid teaching and updated the knowledge graph with a bottom-up model. In the inference model of the knowledge graph, a gated loop unit is used to make modifications on GNN and unfold a fixed number T of recursions, while time backpropagation is used to compute the gradient to evaluate the students’ sports intensity under the theme-based microgrid teaching. The SSA algorithm improved the ontology rule inference of the core parameters by including sport intensity in the core parameter constraints for the generation of physical education microgram instruction. The RMSE mean of the recommendation algorithm in the optimized optimal sports instruction search was 0.43257 with a standard deviation of 0.05531 and a 95% confidence interval of [0.44149,0.42364]. The use of SSA was able to obtain lower RMSE values under the same model of sports and physical activity similarity calculation. By obtaining the optimal sports instruction program, the sports thematic microgrid teaching model was scientifically guided.

A Thematic Microgrid Teaching Model for Physical Education Based on SSA Optimization Algorithm

Applied Mathematics and Nonlinear Sciences

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

As an innovative design, microgrid teaching has great application prospects in teaching practical skills in sports. In this paper, we constructed a knowledge...

A Thematic Microgrid Teaching Model for Physical Education Based on SSA Optimization Algorithm

Published Online: Dec 16, 2023

Page range: -

Received: Mar 21, 2023

Accepted: Jun 26, 2023

DOI: https://doi.org/10.2478/amns.2023.2.01503

Keywords
Knowledge graph, GNN, SSA algorithm, Ontology rule reasoning, Sport intensity assessment

© 2023 Wei Chen et al., published by Sciendo

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

A Thematic Microgrid Teaching Model for Physical Education Based on SSA Optimization Algorithm

Published Online: Dec 16, 2023

Page range: -

Received: Mar 21, 2023

Accepted: Jun 26, 2023

DOI: https://doi.org/10.2478/amns.2023.2.01503

KeywordsKnowledge graph, GNN, SSA algorithm, Ontology rule reasoning, Sport intensity assessment

© 2023 Wei Chen et al., published by Sciendo

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

Keywords
Knowledge graph, GNN, SSA algorithm, Ontology rule reasoning, Sport intensity assessment