Abstract Noise is inevitable in the collection of traffic data, which may cause accuracy and stability issues in smart mobility applications. In the literature, most of the existing studies on traffic data denoising assume that noises follow specific distributions (e.g., Gaussian) or structures (e.g., sparsity). However, various noises may coexist in the traffic data and their distributions or structures are usually unknown in the real world. This leads to the corrupted noise and brings a huge challenge to the traffic data recovery due to the irregular characteristics of such noise. In this research, we develop a doubly physics-regularized denoising diffusion model to address this issue. The proposed denoising diffusion model gradually adds noise to the data and then learns to recover the true value from noises. Each layer of the model can be perceived as a filter that removes noises with different scales, which helps to disentangle the coupling of noises. To make up for the insufficient information of noise distributions or structures, we incorporate prior traffic domain knowledge of the fundamental diagram into the denoising diffusion model using . Under suitable assumptions, we prove that our model can output an unbiased estimation of the true value. We validate our model using two real datasets collected in Japan and China. Results demonstrate that our model outperforms other denoising methods, such as filter-based methods, compressed sensing, robust principal component analysis, and machine learning methods.

    Highlights A doubly physics-regularized denoising diffusion model is built for data denoising. Traffic domain knowledge is incorporated into the denoising diffusion model. Unbiased estimation can be provably obtained under suitable assumptions. The proposed model is validated using two real datasets in Japan and China.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Recovering traffic data from the corrupted noise: A doubly physics-regularized denoising diffusion model


    Beteiligte:
    Zheng, Zhenjie (Autor:in) / Wang, Zhengli (Autor:in) / Hu, Zijian (Autor:in) / Wan, Zihan (Autor:in) / Ma, Wei (Autor:in)


    Erscheinungsdatum :

    2024-02-01




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Traffic Flow Modeling With Gradual Physics Regularized Learning

    Yuan, Yun / Wang, Qinzheng / Yang, Xianfeng Terry | IEEE | 2022


    Traffic Data Recovery From Corrupted and Incomplete Observations via Spatial-Temporal TRPCA

    Feng, Xinxin / Zhang, Haitao / Wang, Can et al. | IEEE | 2022


    Algorithms for impulse noise removal from corrupted color images

    Kober, V. / Mozerov, M. / Ovseyevich, I. A. | British Library Online Contents | 2007


    Control Oriented Freeway Traffic Modelling by Physics-Regularized Machine Learning

    Binjaku, K. / Mece, E.K. / Pasquale, C. et al. | IEEE | 2023