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

<p>Nowadays, people’s demand for healthy exercise is growing rapidly, appropriate exercise can effectively improve physical function, and good exercise effect cannot be separated from the assessment of exercise intensity. In this paper, through the construction of a knowledge graph and parameterized inference model, the elastic network algorithm is introduced to assess the exercise intensity, and the three indexes of myocardial force, heart rate and blood supply are chosen as references through the test experiments to compare the exercise intensity level and the prediction results of the parameter model, to validate the validity and accuracy of parameter model assessment method, and then to compare the assessment effect of BP neural network and the parameter model of the present paper on the exercise prescription. Finally, it was concluded that the critical values of exercise intensity classifications obtained from the experimental tests of the three indexes of myocardial force, heart rate and cardiac blood supply were 4.002, 25.742 and −0.301, respectively, and the assessment results obtained from the parametric model were 3.722, 23.793 and −0.276, which were close to each other. A comparison of different levels of exercise intensity testing and assessment results can be obtained. The accuracy of the three test groups is 96%, 93% and 89%, indicating that the accuracy of the parametric model assessment is higher. The best values of the BP neural network and the parametric model in the paper in terms of the accuracy of the assessment of exercise prescription are 95% and 96%, respectively, in terms of the combined parametric model convergence better error loss.</p>
</abstract>

Nowadays, people’s demand for healthy exercise is growing rapidly, appropriate exercise can effectively improve physical function, and good exercise effect cannot be separated from the assessment of exercise intensity. In this paper, through the construction of a knowledge graph and parameterized inference model, the elastic network algorithm is introduced to assess the exercise intensity, and the three indexes of myocardial force, heart rate and blood supply are chosen as references through the test experiments to compare the exercise intensity level and the prediction results of the parameter model, to validate the validity and accuracy of parameter model assessment method, and then to compare the assessment effect of BP neural network and the parameter model of the present paper on the exercise prescription. Finally, it was concluded that the critical values of exercise intensity classifications obtained from the experimental tests of the three indexes of myocardial force, heart rate and cardiac blood supply were 4.002, 25.742 and −0.301, respectively, and the assessment results obtained from the parametric model were 3.722, 23.793 and −0.276, which were close to each other. A comparison of different levels of exercise intensity testing and assessment results can be obtained. The accuracy of the three test groups is 96%, 93% and 89%, indicating that the accuracy of the parametric model assessment is higher. The best values of the BP neural network and the parametric model in the paper in terms of the accuracy of the assessment of exercise prescription are 95% and 96%, respectively, in terms of the combined parametric model convergence better error loss.

Research on a parametric model-based algorithm for sports intensity assessment

Applied Mathematics and Nonlinear Sciences

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

{"article-title":"Research on a parametric model-based algorithm for sports intensity assessment"}

Nowadays, people’s demand for healthy exercise is growing rapidly, appropriate exercise can effectively improve physical function, and good exercise effect...

Research on a parametric model-based algorithm for sports intensity assessment

Online veröffentlicht: 31. Jan. 2024

Seitenbereich: -

Eingereicht: 15. Dez. 2023

Akzeptiert: 21. Dez. 2023

DOI: https://doi.org/10.2478/amns-2024-0114

Schlüsselwörter
Parametric model, GGNN, Elastic network algorithm, Exercise intensity assessment, Sports intensity

© 2024 Yongliang Fang, published by Sciendo

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

Research on a parametric model-based algorithm for sports intensity assessment

Online veröffentlicht: 31. Jan. 2024

Seitenbereich: -

Eingereicht: 15. Dez. 2023

Akzeptiert: 21. Dez. 2023

DOI: https://doi.org/10.2478/amns-2024-0114

SchlüsselwörterParametric model, GGNN, Elastic network algorithm, Exercise intensity assessment, Sports intensity

© 2024 Yongliang Fang, published by Sciendo

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

Schlüsselwörter
Parametric model, GGNN, Elastic network algorithm, Exercise intensity assessment, Sports intensity