Design of an epidemic prevention and control bracelet system integrated with convolutional neural networks: Promote real-time physiological feedback and adaptive training in remote physical education

  • Yan Weng Physical Education Institute, Jiujiang University, Jiujiang 332005, Jiangxi, China
  • Zhijun Chen Physical Education Institute, Jiujiang University, Jiujiang 332005, Jiangxi, China
  • Shengbo Weng No.2 Midle School of Mi Luo, Miluo 414400, Hunan, China
  • Zuqin Yin No.1 Midle School of Jiu Jiang, Jiujiang 332005, Jiangxi, China
Keywords: convolutional neural network; epidemic prevention and control; physical education; physiological indicators; adaptive training
Article ID: 547

Abstract

This study aims to design an epidemic prevention and control bracelet system that integrates convolutional neural network (CNN). This system can collect and process the user’s physiological index data in real time, especially in the remote physical education scene, and provide learners with immediate physiological index feedback and personalized adaptive training suggestions through accurate human action recognition (HAR) technology. One-dimensional acceleration signal is converted into two-dimensional image, and CNN’s powerful feature extraction and classification ability is used to effectively solve the problem that manual feature extraction is complex and nonlinear features are difficult to capture. By considering the joint action trajectory in the time window, a dynamic Recurrence Plot (RP) is constructed to capture the dynamic changes among joints. To input recursive graph data into CNN, it needs to be converted into image form. In the task of HAR, CNN can automatically learn useful features from images without manually designing features. It can not only effectively extract features from images, but also be directly used in classification tasks. Experimental results show that compared with other algorithms, the proposed RP + CNN model has the best performance in action recognition, with an accuracy of 96.89% and a F1 value of 86.76%. RP captures the dynamic patterns and periodic behaviors in time series by visualizing the repeated appearance of system states over time. The RP + CNN model is used to extract and classify human action features, which significantly improves the accuracy and efficiency of HAR. This innovative method not only simplifies the complex process of traditional manual feature extraction, but also enhances the system’s ability to identify nonlinear and complex action patterns, which provides strong technical support for remote physical education.

References

1. Bin S. Construction and simulation analysis of epidemic propagation model based on covid-19 characteristics. International Journal of Environmental Research and Public Health, 2022, 20(1): 132.

2. Luo X, Zhao H, Chen Y. Research on User Experience of Sports Smart Bracelet Based on Fuzzy Comprehensive Appraisal and SSA-BP Neural Network. Computational Intelligence and Neuroscience, 2022, 2022(1): 5597662.

3. Yang C, Chang Y T. Data Collection And Performance Evaluation Of Running Training Sport Using Different Neural Network Techniques. Journal of Mechanics in Medicine and Biology, 2023, 23(04): 2340053.

4. Liang J, He Q. Application of artificial intelligence wearable devices based on neural network algorithm in mass sports activity evaluation. Soft Computing, 2023, 27(14): 10177-10188.

5. Ma B, Nie S, Ji M, et al. Research and Analysis of Sports Training Real-Time Monitoring System Based on Mobile Artificial Intelligence Terminal. Wireless Communications and Mobile Computing, 2020, 2020(1): 8879616.

6. Chidambaram S, Maheswaran Y, Patel K, et al. Using artificial intelligence-enhanced sensing and wearable technology in sports medicine and performance optimisation. Sensors, 2022, 22(18): 6920.

7. Dai X, Li S. [Retracted] Application Analysis of Wearable Technology and Equipment Based on Artificial Intelligence in Volleyball. Mathematical Problems in Engineering, 2021, 2021(1): 5572389.

8. Yang Z. Using wearable technology to optimize sports performance and prevent injuries. Molecular & Cellular Biomechanics, 2024, 21(1): 305-305.

9. Sevil M, Rashid M, Maloney Z, et al. Determining physical activity characteristics from wristband data for use in automated insulin delivery systems. IEEE sensors journal, 2020, 20(21): 12859-12870.

10. Wu Q, Tang P, Yang M. Data processing platform design and algorithm research of wearable sports physiological parameters detection based on medical internet of things. Measurement, 2020, 165: 108172.

11. Sel K, Mohammadi A, Pettigrew R I, et al. Physics-informed neural networks for modeling physiological time series for cuffless blood pressure estimation. npj Digital Medicine, 2023, 6(1): 110.

12. Yong Z. Intelligent system simulation and data accuracy of physical fitness training for sports majors based on real-time status update of wearable Internet of Things. Soft Computing, 2023, 27(14): 10145-10154.

13. Tan L, Ran N. Applying artificial intelligence technology to analyze the athletes’ training under sports training monitoring system. International Journal of Humanoid Robotics, 2023, 20(06): 2250017.

14. Davidson P, Trinh H, Vekki S, et al. Surrogate modelling for oxygen uptake prediction using LSTM neural network. Sensors, 2023, 23(4): 2249.

15. Sun W, Guo Z, Yang Z, et al. A review of recent advances in vital signals monitoring of sports and health via flexible wearable sensors. Sensors, 2022, 22(20): 7784.

16. Nazaret A, Tonekaboni S, Darnell G, et al. Modeling personalized heart rate response to exercise and environmental factors with wearables data. NPJ Digital Medicine, 2023, 6(1): 207.

17. Yang L, Amin O, Shihada B. Intelligent wearable systems: Opportunities and challenges in health and sports. ACM Computing Surveys, 2024, 56(7): 1-42.

18. Cosoli G, Antognoli L, Scalise L. Wearable Electrocardiography for Physical Activity Monitoring: Definition of Validation Protocol and Automatic Classification. Biosensors, 2023, 13(2): 154.

19. Saad M, Ahmad M B, Asif M, et al. Blockchain and IIoT Enabled Solution for Social Distancing and Isolation Management to Prevent Pandemics. Computers, Materials & Continua, 2023, 76(1).

20. Han W, Cai H, Lu J, et al. Application of body area network wearable smart bracelet in epidemic isolation scenario. Journal of Translational Internal Medicine, 2024, 12(3): 321-324.

21. Xu Z, Yu B, Wang F. Artificial intelligence/machine learning solutions for mobile and wearable devices. Digital Health: Mobile and Wearable Devices for Participatory Health Applications, 2020, 55.

22. Cui C. Intelligent analysis of exercise health big data based on deep convolutional neural network. Computational Intelligence and Neuroscience, 2022, 2022(1): 5020150.

23. Edriss S, Romagnoli C, Caprioli L, et al. The Role of Emergent Technologies in the Dynamic and Kinematic Assessment of Human Movement in Sport and Clinical Applications. Applied Sciences, 2024, 14(3): 1012.

24. Balkhi P, Moallem M. A multipurpose wearable sensor-based system for weight training. Automation, 2022, 3(1): 132-152.

25. Askari M R, Abdel-Latif M, Rashid M, et al. Detection and classification of unannounced physical activities and acute psychological stress events for interventions in diabetes treatment. Algorithms, 2022, 15(10): 352.

26. Bangaru S S, Wang C, Aghazadeh F. Automated and continuous fatigue monitoring in construction workers using forearm EMG and IMU wearable sensors and recurrent neural network. Sensors, 2022, 22(24): 9729.

27. de Pedro-Carracedo J, Clemente J, Fuentes-Jimenez D, et al. Photoplethysmographic Signal-Diffusive Dynamics as a Mental-Stress Physiological Indicator Using Convolutional Neural Networks. Applied Sciences, 2023, 13(15): 8902.

28. Xu S. Retracted article: BP neural network–based detection of soil and water structure in mountainous areas and the mechanism of wearing fatigue in running sports. Arabian Journal of Geosciences, 2021, 14(11): 920.

Published
2024-11-20
How to Cite
Weng, Y., Chen, Z., Weng, S., & Yin, Z. (2024). Design of an epidemic prevention and control bracelet system integrated with convolutional neural networks: Promote real-time physiological feedback and adaptive training in remote physical education. Molecular & Cellular Biomechanics, 21(3), 547. https://doi.org/10.62617/mcb547
Section
Article