Intelligent monitoring and analysis of physical education based on IoT and deep learning in the context of big data-Reference-Cited by-同舟云学术

Intelligent monitoring and analysis of physical education based on IoT and deep learning in the context of big data

Published:2023-06-06 Issue: Volume: Page:
ISSN:
Container-title:
language:
Short-container-title:

Author:

Liang Bingyuan¹,Wu Liujin²^ORCID

Affiliation:

1. Guangxi Normal University

2. Guilin Medical University

Abstract

Abstract This paper proposes a system for detecting errors in physical education training that utilizes the Internet of Things and deep learning technology, with the aim of reducing error rates and improving detection effectiveness. The hardware component of the system employs an IoT sensing network that includes an infrared sensor, a three-axis acceleration sensor, a heart rate band, a pulse sensor, and a body temperature monitoring probe to collect real-time physical function parameters from physical trainers. In the software component of the system, a lightweight network is formed by combining the improved MobileNetV3 with SSD, and Bi-FPN is then incorporated to fuse features and achieve accurate detection of errors in sports teaching and training. The experimental results show that the system has good performance and good detection performance for sports teaching and training error actions. The mean average precision (mAP) on the self-made dataset is 94.3%, which is 4.1% higher than the original network. It can accurately detect the training errors of sports personnel in various regions.

Publisher

Research Square Platform LLC

Reference34 articles.

1. Spyridis Yannis,Villarini Barbara,Argyriou Vasileios. Intraclass Clustering-Based CNN Approach for Detection of Malignant Melanoma[J];Bandy Adrian D

2. Eva Bartaguiz,Freya Gassmann, Conceptual Structure and Current Trends in Artificial Intelligence, Machine Learning, and Deep Learning Research in Sports: A Bibliometric Review[J];Carlo D;Int J Environ Res Public Health,2023

3. Cho K, Xi C, Classifying (2013) and Visualizing Motion Capture Sequences using Deep Neural Networks[C]// IEEE,

4. Human Hepatocellular Carcinoma Classification from H&E Stained Histopathology Images with 3D Convolutional Neural Networks and Focal Loss Function[J];Cinar Umut,Cetin Atalay Rengul,Cetin Yasemin Yardimci;J Imaging,2023

5. Chen X Zhang Chunhong,Fang Jingjing,Zheng Yu,Li Dan. A Study on Application of Infrared Sensor Method in Moisture Permeability Test of Food Packaging Materials[J]. Journal of Physics: Conference Series,2021,2044(1)