Combining variational autoencoders with generative adversarial networks to adaptively adjust the electromagnetic compatibility of biomechanical data analysis platforms

  • Hongyan Sun School of Electrical Engineering, Nanjing Normal University Taizhou College, Taizhou 225300, China
  • Mingxiang Zhu School of Electrical Engineering, Nanjing Normal University Taizhou College, Taizhou 225300, China
  • Xingbo Wang School of Electrical Engineering, Nanjing Normal University Taizhou College, Taizhou 225300, China
Keywords: variational autoencoders (VAEs); generative adversarial networks (GANs); electromagnetic compatibility (EMC); biomechanical data analysis; wearable devices; synthetic data generation
Article ID: 1332

Abstract

This study investigates the integration of variational autoencoders (VAEs) and generative adversarial networks (GANs) to enhance the electromagnetic compatibility (EMC) of biomechanical data analysis platforms. Leveraging a comprehensive dataset from multiple wearable devices, we capture diverse biomechanical parameters, including muscle activity, joint angles, and kinematic data. The preprocessing phase involves normalization and feature extraction, followed by encoding the biomechanical data into a latent space using VAEs. The GAN component generates synthetic data that are indistinguishable from real data, which are then utilized to adjust the EMC parameters of the analysis platform. Our results reveal significant improvements in model performance, as indicated by reduced mean squared error (MSE) and enhanced structural similarity index (SSIM) across multiple training epochs. Furthermore, the EMC adjustment process effectively minimizes electromagnetic interference, as evidenced by a substantial decrease in electromagnetic interference error function values. The high similarity between real and synthetic data validates the quality of the generated data. This integrated VAE-GAN framework presents a promising methodology for augmenting the accuracy and reliability of biomechanical data analysis in various applications.

References

1. Kingma DP, Welling M. An Introduction to Variational Autoencoders. Foundations and Trends® in Machine Learning. 2019; 12(4): 307–392.

2. Doersch C. Tutorial on Variational Autoencoders. ArXiv. 2016.

3. Liang D, Krishnan RG, Hoffman MD, Jebara T. Variational Autoencoders for Collaborative Filtering. In: Proceedings of the 2018 World Wide Web Conference; 10 April 2018; Lyon, France.

4. Papadopoulos D, Karalis VD. Variational Autoencoders for Data Augmentation in Clinical Studies. Applied Sciences. 2023; 13(15): 8793. doi: 10.3390/app13158793

5. Kalafut NC, Huang X, Wang D. Joint Variational Autoencoders For Multimodal Imputation And Embedding. Nature Machine Intelligence. 2023; 5(6): 631–642. doi: 10.1038/s42256-023-00663-z

6. Solera-Rico A, Vila CS, Gómez-López M, et al. β-Variational autoencoders and transformers for reduced-order modelling of fluid flows. Nature Communications. 2024; 15(1). doi: 10.1038/s41467-024-45578-4

7. Bredell G, Flouris K, Chaitanya K, et al. Explicitly Minimizing the Blur Error of Variational Autoencoders. ArXiv. 2023. doi: 10.48550/ARXIV.2304.05939

8. Khemakhem I, Kingma D, Monti R, Hyvarinen A. Variational Autoencoders and Nonlinear ICA: A Unifying Framework. International Conference on Artificial Intelligence and Statistics. 2019; 2207–2217.

9. Zhao T, Zhao R, Eskenazi M. Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics; 30 July–4 August 2017; Vancouver, Canada.

10. Karras T, Laine S, Aila T. A Style-Based Generator Architecture for Generative Adversarial Networks. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019; 4396–4405. doi: 10.1109/cvpr.2019.00453

11. Radford A, Metz L, Chintala S. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. CoRR. 2015.

12. Miyato T, Kataoka T, Koyama M, Yoshida Y.(2018). Spectral Normalization for Generative Adversarial Networks. ArXiv. 2018.

13. Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks. Communications of the ACM. 2020; 63(11): 139–144. doi: 10.1145/3422622

14. Mao X, Li Q, Xie H, et al. Least Squares Generative Adversarial Networks. 2017 IEEE International Conference on Computer Vision (ICCV). 2017; 2813–2821. doi: 10.1109/iccv.2017.304

15. Martín A, Chintala M, Bottou L. Wasserstein Generative Adversarial Networks. International Conference on Machine Learning. 2017; 214–223.

16. Wang X, Yu K, Wu S, et al. ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks. In: Computer Vision—ECCV Workshops. Springer; 2018. pp. 63–79.

17. Zhang H, Goodfellow I, Metaxas D, Odena A. Self-Attention Generative Adversarial Networks. ArXiv. 2018.

18. Karras T, Aittala M, Hellsten J, et al. Training Generative Adversarial Networks with Limited Data. ArXiv. 2020.

19. Gao H, Guo J, Zhang Y, Guo C. Analysis of the Rectification Case of Electromagnetic Compatibility Conducted Emission of a Vehicle Projection Lamp. In: Proceedings of the 2023 IEEE 7th International Symposium on Electromagnetic Compatibility (ISEMC); 20–23 October 2023; Hangzhou, China. pp. 1–4.

20. Andersson J, Olsson H, Theocharis A. Analysis of electromagnetic compatibility in photovoltaic installations validated by site measurements. 2021 IEEE Madrid PowerTech. 2021; 1–6. doi: 10.1109/powertech46648.2021.9494791

21. Ye J, Li X, Liang F, Li Y. Electromagnetic compatibility analysis of GBAS VDB by magnetic levitation arc. In: Proceedings of the Seventh International Conference on Electromechanical Control Technology and Transportation (ICECTT 2022); 27–29 May 2022; Guangzhou, China.

22. Urbanczyk CA, Bonfiglio A, McGregor AH, Bull AMJ. Comparing optical and electromagnetic tracking systems to facilitate compatibility in sports kinematics data. International Biomechanics. 2021; 8(1): 75–84. doi: 10.1080/23335432.2021.2003719

23. Wang J, Zhao Y, Yang C, et al. The Electromagnetic Compatibility Analysis Between FAST and the 2G-IMT System Around its RQZ. IEEE Transactions on Electromagnetic Compatibility. 2023; 65(6): 1960–1971.

24. Wang Y. Mechanical finite element analysis and electromagnetic compatibility optimization of nickel-plated carbon fiber composite high-frequency box shell material. In: Proceedings of the 2024 IEEE Transportation Electrification Conference and Expo, Asia-Pacific (ITEC Asia-Pacific); 10–13 October 2024; Xi’an, China. pp. 257–260.

25. Yadav S, Tiwari R, Marandi AK. An Analytical Study of the Impact of Data Flow on Electromagnetic Compatibility. In: Proceedings of the 2024 2nd International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA); 15–16 March 2024; Namakkal, India. pp. 1–7.

26. Bejalwar SA. Study on Bibliometric Analysis of “IEEE Transactions on Electromagnetic Compatibility”: 2010–2015. In: Innovations in Science and Technology. BP International; 2021. pp. 36–45.

27. Venkata RD. Spectral Analysis of Electromagnetic Compatibility. European Journal of Engineering and Technology Research. 2021; 6(7): 38–41. doi: 10.24018/ej-eng.2021.6.7.2596

Published
2025-03-24
How to Cite
Sun, H., Zhu, M., & Wang, X. (2025). Combining variational autoencoders with generative adversarial networks to adaptively adjust the electromagnetic compatibility of biomechanical data analysis platforms. Molecular & Cellular Biomechanics, 22(5), 1332. https://doi.org/10.62617/mcb1332
Section
Article