<abstract xmlns="http://www.w3.org/1999/xhtml">
<p>The purpose of designing a sports training fitness index monitoring system is to grasp better the physical performance data of athletes in the training process to ensure training safety. In this paper, the principle of multilayer perceptron is explained based on the perceptron model, the optimal loss function of multilayer perceptron is solved by using the activation function and forward propagation algorithm, the sensor data collection module is constructed, and the physical fitness index monitoring system for sports training is built by this method. To verify the feasibility of the detection system in this paper, experimental analysis was conducted from three aspects: the distribution of physical fitness index monitoring information density, physical fitness index data and monitoring data accuracy. The index monitoring density distribution was between 0.11 and 2.09 from the monitoring information density. Regarding physical performance indicators, the average values of maximum oxygen uptake, heart rate, relative energy metabolism level, and exercise intensity were 41.02, 121.58, and 11.84, respectively. From the accuracy of indicator monitoring data, the accuracy of the system in this paper was 93.63%, which was 21.57 and 11.03 percentage points higher than that of GAN and MCNN algorithms, respectively. The physical fitness index monitoring system constructed based on the perceptron model can effectively realize the monitoring of physical fitness indexes, help trainers master the training rhythm, and improve the safety of sports training. </p>
</abstract>

The purpose of designing a sports training fitness index monitoring system is to grasp better the physical performance data of athletes in the training process to ensure training safety. In this paper, the principle of multilayer perceptron is explained based on the perceptron model, the optimal loss function of multilayer perceptron is solved by using the activation function and forward propagation algorithm, the sensor data collection module is constructed, and the physical fitness index monitoring system for sports training is built by this method. To verify the feasibility of the detection system in this paper, experimental analysis was conducted from three aspects: the distribution of physical fitness index monitoring information density, physical fitness index data and monitoring data accuracy. The index monitoring density distribution was between 0.11 and 2.09 from the monitoring information density. Regarding physical performance indicators, the average values of maximum oxygen uptake, heart rate, relative energy metabolism level, and exercise intensity were 41.02, 121.58, and 11.84, respectively. From the accuracy of indicator monitoring data, the accuracy of the system in this paper was 93.63%, which was 21.57 and 11.03 percentage points higher than that of GAN and MCNN algorithms, respectively. The physical fitness index monitoring system constructed based on the perceptron model can effectively realize the monitoring of physical fitness indexes, help trainers master the training rhythm, and improve the safety of sports training.

Design of a perceptron model-based physical fitness index monitoring system for sports training 

Applied Mathematics and Nonlinear Sciences

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