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

<p>The continuous development and improvement of information technology and the arrival of the knowledge economy have injected new vitality into the development of the sports industry. In the context of artificial intelligence, this paper constructs a graph convolutional neural network model. It applies it to the field of sports teaching, creating an adjacency matrix based on image information to optimize the information processing speed of the neural network model. The standardized way is used to recognize and guide the various sports movements performed by students in the classroom. Through effectiveness analysis and FMS experiments, it was found that the graph convolutional neural network has a high recognition rate, and the matching rate for each section of the movement is above 70%. The mean values of angle features of students with very different body sizes remained at the same level with minimal differences under the same shooting angle. From the perspective of students’ sports performance, in the fourth week of the middle and late experimental period, the results of the experimental group and the control group students were 82.39±2.10 and 73.64±3.62, respectively, which was a difference of nearly 10 points. The results of the control group students had already lagged behind the experimental group students substantially from the perspective of the score, and the difference was significant at P=0.000&lt;0.05. The convolutional neural network can effectively improve sports movement standardization, which in turn enhances the performance of students in physical education and promotes the information development of the sports industry.</p>
</abstract>

The continuous development and improvement of information technology and the arrival of the knowledge economy have injected new vitality into the development of the sports industry. In the context of artificial intelligence, this paper constructs a graph convolutional neural network model. It applies it to the field of sports teaching, creating an adjacency matrix based on image information to optimize the information processing speed of the neural network model. The standardized way is used to recognize and guide the various sports movements performed by students in the classroom. Through effectiveness analysis and FMS experiments, it was found that the graph convolutional neural network has a high recognition rate, and the matching rate for each section of the movement is above 70%. The mean values of angle features of students with very different body sizes remained at the same level with minimal differences under the same shooting angle. From the perspective of students’ sports performance, in the fourth week of the middle and late experimental period, the results of the experimental group and the control group students were 82.39±2.10 and 73.64±3.62, respectively, which was a difference of nearly 10 points. The results of the control group students had already lagged behind the experimental group students substantially from the perspective of the score, and the difference was significant at P=0.000<0.05. The convolutional neural network can effectively improve sports movement standardization, which in turn enhances the performance of students in physical education and promotes the information development of the sports industry.

Artificial Intelligence Technology Helps Inform the Sports Industry

Applied Mathematics and Nonlinear Sciences

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

{"article-title":"Artificial Intelligence Technology Helps Inform the Sports Industry"}

The continuous development and improvement of information technology and the arrival of the knowledge economy have injected new vitality into the development...

Artificial Intelligence Technology Helps Inform the Sports Industry

Publicado en línea: 15 may 2024

Páginas: -

Recibido: 29 ene 2024

Aceptado: 01 abr 2024

DOI: https://doi.org/10.2478/amns-2024-1105

Palabras clave
Graph convolutional neural network, Neighbor matrix, FMS, Artificial intelligence, Sports industry

© 2024 Lin Shen et al., published by Sciendo

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

Artificial Intelligence Technology Helps Inform the Sports Industry

Publicado en línea: 15 may 2024

Páginas: -

Recibido: 29 ene 2024

Aceptado: 01 abr 2024

DOI: https://doi.org/10.2478/amns-2024-1105

Palabras claveGraph convolutional neural network, Neighbor matrix, FMS, Artificial intelligence, Sports industry

© 2024 Lin Shen et al., published by Sciendo

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

Palabras clave
Graph convolutional neural network, Neighbor matrix, FMS, Artificial intelligence, Sports industry