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

<p>Teaching online physical education courses under the epidemic normalization plays a positive role in students’ physical fitness. In this paper, taking 308 college students of X Sports College as a research case, personalized recommendation of physical education online teaching courses is carried out through a user collaborative filtering recommendation algorithm based on fuzzy clustering and user interests. The model of sports skill action development is constructed based on the mountain peak model and hourglass model, and the exercise intensity of the initial exercise is modified according to the results of home exercise intensity adjustment to obtain a personalized home exercise program suitable for individuals. Finally, the effectiveness of the home exercise optimization program was verified through the analysis of teaching constraints and exercise effects. The results show that under the epidemic normality, the difference between the demonstration movements and the test results in the 1st, 2nd and 3rd optimized teaching phases is between ±5.86, which is closer to the value of each index of the demonstration movements, indicating that the optimization and adjustment scheme of the home exercise of the physical education network teaching course has good effects. This paper has reference value for universities to conduct online teaching and training of university physical education courses in the context of major public health emergencies.</p>
</abstract>

Teaching online physical education courses under the epidemic normalization plays a positive role in students’ physical fitness. In this paper, taking 308 college students of X Sports College as a research case, personalized recommendation of physical education online teaching courses is carried out through a user collaborative filtering recommendation algorithm based on fuzzy clustering and user interests. The model of sports skill action development is constructed based on the mountain peak model and hourglass model, and the exercise intensity of the initial exercise is modified according to the results of home exercise intensity adjustment to obtain a personalized home exercise program suitable for individuals. Finally, the effectiveness of the home exercise optimization program was verified through the analysis of teaching constraints and exercise effects. The results show that under the epidemic normality, the difference between the demonstration movements and the test results in the 1st, 2nd and 3rd optimized teaching phases is between ±5.86, which is closer to the value of each index of the demonstration movements, indicating that the optimization and adjustment scheme of the home exercise of the physical education network teaching course has good effects. This paper has reference value for universities to conduct online teaching and training of university physical education courses in the context of major public health emergencies.

An analysis of the effects of a physical education web-based instructional program on college students exercising at home during COVID-19

Applied Mathematics and Nonlinear Sciences

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

Teaching online physical education courses under the epidemic normalization plays a positive role in students’ physical fitness. In this paper, taking 308...

An analysis of the effects of a physical education web-based instructional program on college students exercising at home during COVID-19

Publié en ligne: 23 déc. 2023

Pages: -

Reçu: 10 mars 2023

Accepté: 03 juil. 2023

DOI: https://doi.org/10.2478/amns.2023.2.01600

Mots clés
Epidemic normalization, Fuzzy clustering, Collaborative filtering, Recommendation algorithms, Hourglass models

© 2023 Chunyan Li et al., published by Sciendo

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

An analysis of the effects of a physical education web-based instructional program on college students exercising at home during COVID-19

Publié en ligne: 23 déc. 2023

Pages: -

Reçu: 10 mars 2023

Accepté: 03 juil. 2023

DOI: https://doi.org/10.2478/amns.2023.2.01600

Mots clésEpidemic normalization, Fuzzy clustering, Collaborative filtering, Recommendation algorithms, Hourglass models

© 2023 Chunyan Li et al., published by Sciendo

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

Mots clés
Epidemic normalization, Fuzzy clustering, Collaborative filtering, Recommendation algorithms, Hourglass models