IDEAS home Printed from https://ideas.repec.org/a/eee/phsmap/v670y2025ics0378437125002729.html
   My bibliography  Save this article

Optimal transport guided GAN with unpaired data for inertial signal enhancement

Author

Listed:
  • Wang, Yifeng
  • Zhao, Yi
  • Han, Xinyu

Abstract

Low-cost inertial sensors suffer from inherent noise, yet enhancing their signals remains challenging due to the absence of paired high-quality references, which hinders end-to-end supervised training for deep learning models. Therefore, we propose leveraging optimal transport theory to exploit implicit supervision through unpaired data correlations. By establishing the Feature Optimal Transport Theorem, we derive the existence conditions for optimal transport mappings between signal features of different qualities. We also quantify the upper bound of optimal transport error, revealing the impact of feature distribution differences and the compactness radius of feature space on the optimal transport error bound. Guided by this theoretical basis, we design an OTES-GAN, which reduces static noise metrics by over 95%, decreases dynamic displacement prediction error by 83.54%, and improves semantic recognition accuracy by 17.32%, outperforming all comparative methods by a significant margin, offering a new theoretical framework and practical paradigm for unpaired signal translation.

Suggested Citation

  • Wang, Yifeng & Zhao, Yi & Han, Xinyu, 2025. "Optimal transport guided GAN with unpaired data for inertial signal enhancement," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 670(C).
    • Handle: RePEc:eee:phsmap:v:670:y:2025:i:c:s0378437125002729
    DOI: 10.1016/j.physa.2025.130620
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0378437125002729
    Download Restriction: Full text for ScienceDirect subscribers only. Journal offers the option of making the article available online on Science direct for a fee of $3,000
    File URL: https://libkey.io/10.1016/j.physa.2025.130620?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    References listed on IDEAS

    as
    1. Lin, Yi & Zhang, Jianwei & Yang, Bo & Liu, Hong & Zhao, Liping, 2019. "An optimal routing strategy for transport networks with minimal transmission cost and high network capacity," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 521(C), pages 551-561.
    2. Bongiorno, Christian & Lamrani, Lamia, 2025. "Quantifying the information lost in optimal covariance matrix cleaning," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 657(C).
    3. Shiqiang Liu & Junchang Zhang & Yuzhong Zhang & Rong Zhu, 2020. "A wearable motion capture device able to detect dynamic motion of human limbs," Nature Communications, Nature, vol. 11(1), pages 1-12, December.
    4. Yang Liu & Guangwu Chen & Zongshou Wei & Juhua Yang & Dongfeng Xing, 2020. "Denoising Method of MEMS Gyroscope Based on Interval Empirical Mode Decomposition," Mathematical Problems in Engineering, Hindawi, vol. 2020, pages 1-12, December.
    5. Cai, Lingru & Zhang, Zhanchang & Yang, Junjie & Yu, Yidan & Zhou, Teng & Qin, Jing, 2019. "A noise-immune Kalman filter for short-term traffic flow forecasting," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 536(C).
    6. Shao, Feng & Shao, Hu & Wang, Dongle & Lam, William H.K. & Cao, Shuhan, 2023. "A generative model for vehicular travel time distribution prediction considering spatial and temporal correlations," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 621(C).
    7. Liddy, Joshua J. & Ducharme, Scott W. & van Emmerik, Richard E.A. & Haddad, Jeffrey M., 2019. "Temporal correlations in human locomotion: Recommendations for sampling rate and foot strike detection," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 532(C).
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Ma, Changxi & Zhang, Bowen & Li, Shukai & Lu, Youpeng, 2024. "Urban rail transit passenger flow prediction with ResCNN-GRU based on self-attention mechanism," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 638(C).
    2. Shao, Feng & Shao, Hu & Wang, Dongle & Lam, William H.K., 2024. "A multi-task spatio-temporal generative adversarial network for prediction of travel time reliability in peak hour periods," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 638(C).
    3. Karthikeyan Kalyanasundaram Balasubramanian & Andrea Merello & Giorgio Zini & Nathan Charles Foster & Andrea Cavallo & Cristina Becchio & Marco Crepaldi, 2023. "Neural network-based Bluetooth synchronization of multiple wearable devices," Nature Communications, Nature, vol. 14(1), pages 1-10, December.
    4. Ma, Jinlong & Kong, Lingkang & Li, Hui-Jia, 2023. "An effective edge-adding strategy for enhancing network traffic capacity," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 609(C).
    5. Fei Wang & Yinxi Liang & Zhizhe Lin & Jinglin Zhou & Teng Zhou, 2024. "SSA-ELM: A Hybrid Learning Model for Short-Term Traffic Flow Forecasting," Mathematics, MDPI, vol. 12(12), pages 1-17, June.
    6. Xiong, Kaixiao & Fan, Chengliang & He, Deqiang & Chen, Hongyu & Zhao, Xinyi & Feng, Xihui & Zhang, Zutao & Wu, Xiaoping, 2025. "A wearable driver gesture recognition system enabled AI application in virtual reality interaction for smart traffic," Energy, Elsevier, vol. 327(C).
    7. Chen, Junlan & Pu, Ziyuan & Guo, Xiucheng & Cao, Jieyu & Zhang, Fang, 2023. "Multiperiod metro timetable optimization based on the complex network and dynamic travel demand," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 611(C).
    8. Song, Yuxin & Duan, Huiming & Cheng, Yunlong, 2024. "A novel fractional-order grey Euler prediction model and its application in short-term traffic flow," Chaos, Solitons & Fractals, Elsevier, vol. 189(P2).
    9. Fang, Weiwei & Zhuo, Wenhao & Yan, Jingwen & Song, Youyi & Jiang, Dazhi & Zhou, Teng, 2022. "Attention meets long short-term memory: A deep learning network for traffic flow forecasting," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 587(C).
    10. Shihao Zhao & Shuli Xing & Guojun Mao, 2022. "An Attention and Wavelet Based Spatial-Temporal Graph Neural Network for Traffic Flow and Speed Prediction," Mathematics, MDPI, vol. 10(19), pages 1-15, September.
    11. Chen, Xinqiang & Chen, Huixing & Yang, Yongsheng & Wu, Huafeng & Zhang, Wenhui & Zhao, Jiansen & Xiong, Yong, 2021. "Traffic flow prediction by an ensemble framework with data denoising and deep learning model," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 565(C).
    12. Wang, Yunsheng & Xu, Xinghan & Hu, Lei & Liu, Jianwei & Yan, Xiaohui & Ren, Weijie, 2024. "Continuous imputation of missing values in time series via Wasserstein generative adversarial imputation networks and variational auto-encoders model," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 647(C).
    13. Wu Bo & Xu Gong & Fei Chen & Haisheng Ren & Junhao Chen & Delu Li & Fengying Gou, 2025. "Sustainable Data Construction and CLS-DW Stacking for Traffic Flow Prediction in High-Altitude Plateau Regions," Sustainability, MDPI, vol. 17(16), pages 1-27, August.
    14. Liu, Yang & Song, Yaolun & Zhang, Yan & Liao, Zhifang, 2022. "WT-2DCNN: A convolutional neural network traffic flow prediction model based on wavelet reconstruction," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 603(C).
    15. Tian, Jing & Song, Xianmin & Tao, Pengfei & Liang, Jiahui, 2022. "Pattern-adaptive generative adversarial network with sparse data for traffic state estimation," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 608(P1).
    16. Shen, Yi & Song, Guohao & Xu, Huangliang & Xie, Yuancheng, 2020. "Model of node traffic recovery behavior and cascading congestion analysis in networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 545(C).
    17. Ze Dong & Yipeng Zhou & Xiongguan Bao, 2024. "A Short-Term Vessel Traffic Flow Prediction Based on a DBO-LSTM Model," Sustainability, MDPI, vol. 16(13), pages 1-21, June.
    18. repec:plo:pone00:0218908 is not listed on IDEAS
    19. Zhang, Mengyao & Huang, Tao & Guo, Zhaoxia & He, Zhenggang, 2022. "Complex-network-based traffic network analysis and dynamics: A comprehensive review," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 607(C).
    20. Zhanzhong Wang & Ruijuan Chu & Minghang Zhang & Xiaochao Wang & Siliang Luan, 2020. "An Improved Hybrid Highway Traffic Flow Prediction Model Based on Machine Learning," Sustainability, MDPI, vol. 12(20), pages 1-22, October.
    21. Chih-Yao Chang & Kuo-Ping Lin, 2020. "Developing Support Vector Machine with New Fuzzy Selection for the Infringement of a Patent Rights Problem," Mathematics, MDPI, vol. 8(8), pages 1-16, August.

    More about this item

    Keywords

    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:phsmap:v:670:y:2025:i:c:s0378437125002729. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.journals.elsevier.com/physica-a-statistical-mechpplications/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.