System Design and Simulation for Square Dance Movement Monitoring Based on Machine Learning

Area of Science:

• Sports Science
• Computer Science
• Data Science

Background:

• Square dancing is a popular national fitness activity in China, reflecting public health and societal well-being.
• Advancements in Internet of Things (IoT) and machine learning enable intelligent motion detection for health and exercise monitoring.

Purpose of the Study:

• To develop a sports monitoring data system for square dancing using IoT and machine learning.
• To improve data quality for machine learning algorithms in a fitness context.

Main Methods:

• Review of IoT communication protocols (MQTT) and network frameworks (Netty).
• Integration of IoT and machine learning technologies.
• Development of a data preprocessing scheme tailored for IoT characteristics.
• Application of k-Nearest Neighbors (KNN) and regression models for data imputation.
• Training machine learning models to obtain final data filling values.

Main Results:

• A novel scheme for data preprocessing in IoT environments is proposed.
• Machine learning models successfully generated high-quality data for the sports monitoring system.
• The integration facilitates effective motion detection and analysis for square dancing.

Conclusions:

• The developed system effectively combines IoT and machine learning for square dance sports monitoring.
• This approach supports national fitness programs by providing reliable exercise data.
• The study demonstrates the potential of IoT and ML in enhancing public health initiatives.