Skip to main content
Log in

Adaptive weighted median filtering for time-varying graph signals

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Graph filter is one of the cornerstones of graph signal processing that can extract desired features from graph signal and filter out noise signal. In the majority of existing research, graph signal operators are designed to be linear and are applicable solely to time-invariant graph signals. Recently, some studies have extended graph signal processing to time-vertex graph signals. Combining the correlation between graph topology and time can obtain better results. This paper proposes an adaptive weighted median filter for pulsed noise in time-varying graph signals. It uses joint correlation to denoise time-varying graph signals and can adjust filtering window and node weights according to whether node information is destroyed by noise. The proposed filter has the advantages of high efficiency and high localization. Information only needs to be exchanged with one-hop neighbors, and it can be implemented in a distributed manner. Three real sensor network data sets are used for denoising experiments here, and the comprehensive experimental results show that the proposed filters perform better in most cases.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2

Similar content being viewed by others

Data availability

No datasets were generated or analysed during the current study.

References

  1. Mei, J., Moura, J.M.F.: Signal processing on graphs: causal modeling of unstructured data. IEEE Trans. Signal Process. 65(8), 2077–2092 (2017). https://doi.org/10.1109/TSP.2016.2634543

    Article  MathSciNet  MATH  Google Scholar 

  2. Guo, J., Moses, S., Wang, Z.: Graph learning from signals with smoothness superimposed by regressors. IEEE Signal Process. Lett. 30, 942–946 (2023). https://doi.org/10.1109/LSP.2023.3298280

    Article  MATH  Google Scholar 

  3. Wang, W., Doğançay, K.: Distributed nonlinear polynomial adaptive graph filter based on diffusion conjugate gradient strategy. IEEE Trans. Circuits Syst. II Express Briefs 71(2), 947–951 (2024)

    MATH  Google Scholar 

  4. Leus, G., Marques, A.G., Moura, J.M.F., Ortega, A., Shuman, D.I.: Graph signal processing: history, development, impact, and outlook. IEEE Signal Process. Mag. 40(4), 49–60 (2023)

    Article  MATH  Google Scholar 

  5. Stankovic, L., Mandic, D.P.: Understanding the basis of graph convolutional neural networks via an intuitive matched filtering approach [lecture notes]. IEEE Signal Process. Mag. 40(2), 155–165 (2023). https://doi.org/10.1109/MSP.2022.3207304

    Article  MATH  Google Scholar 

  6. Shuai, W., Ni, H., Wu, J., Lin, Z., Yan, W., Wang, W.: A shrinkage adaptive filtering algorithm with graph filter models. Signal Image Video Process. 18(1), 703–712 (2024). https://doi.org/10.1007/s11760-024-03186-1

    Article  MATH  Google Scholar 

  7. Sun, Q., Liu, Y., Li, S.: Weighted directed graph-based automatic seizure detection with effective brain connectivity for EEG signals. Signal Image Video Process. 18(1), 899–909 (2024). https://doi.org/10.1007/s11760-023-02816-4

    Article  MATH  Google Scholar 

  8. Yu, L., Xie, J., Zheng, X.: The relationship between graph fourier transform (gft) and discrete cosine transform (dct) for 1d signal and 2d image. Signal Image Video Process. 17(2), 445–451 (2023). https://doi.org/10.1007/s11760-022-02249-5

    Article  MATH  Google Scholar 

  9. Feng, J., Chen, F., Chen, H.: Data reconstruction coverage based on graph signal processing for wireless sensor networks. IEEE Wirel. Commun. Lett. 11(1), 48–52 (2022). https://doi.org/10.1109/LWC.2021.3120276

    Article  MathSciNet  MATH  Google Scholar 

  10. Ozturk, C., Ozaktas, H.M., Gezici, S., Koç, A.: Optimal fractional fourier filtering for graph signals. IEEE Trans. Signal Process. 69, 2902–2912 (2021). https://doi.org/10.1109/TSP.2021.3079804

    Article  MathSciNet  MATH  Google Scholar 

  11. Domingos, J., Moura, J.M.F.: Graph fourier transform: a stable approximation. IEEE Trans. Signal Process. 68, 4422–4437 (2020). https://doi.org/10.1109/TSP.2020.3009645

    Article  MathSciNet  MATH  Google Scholar 

  12. Wang, W., Dogancay, K.: Widely linear adaptive filtering based on clifford geometric algebra: a unified framework [hypercomplex signal and image processing]. IEEE Signal Process. Mag. 41(2), 86–101 (2024)

  13. Engelberg, S.: Implementing moving average filters using recursion. IEEE Signal Process. Mag. 40(7), 78–80 (2023). https://doi.org/10.1109/MSP.2023.3294721

    Article  MATH  Google Scholar 

  14. Shiung, D., Huang, J.-J.: Tricks for cascading running-sum filters with their variations for high-performance filtering. IEEE Signal Process. Mag. 40(3), 59–63 (2023). https://doi.org/10.1109/MSP.2023.3247903

    Article  MATH  Google Scholar 

  15. Shiung, D., Huang, J.-J., Yang, Y.-Y.: Tricks for designing a cascade of infinite impulse response filters with an almost linear phase response. IEEE Signal Process. Mag. 40(7), 64–73 (2023). https://doi.org/10.1109/MSP.2023.3290772

    Article  MATH  Google Scholar 

  16. Shi, X., Feng, H., Zhai, M., Yang, T., Hu, B.: Infinite impulse response graph filters in wireless sensor networks. IEEE Signal Process. Lett. 22(8), 1113–1117 (2015). https://doi.org/10.1109/LSP.2014.2387204

    Article  MATH  Google Scholar 

  17. Wang, W., Doğançay, K.: Selective partial-update widely linear geometric-algebra NLMS. IEEE Trans. Circuits Syst. II: Express Briefs 71, 4381–4385 (2024)

    MATH  Google Scholar 

  18. Isufi, E., Loukas, A., Simonetto, A., Leus, G.: Autoregressive moving average graph filtering. IEEE Trans. Signal Process. 65(2), 274–288 (2017). https://doi.org/10.1109/TSP.2016.2614793

    Article  MathSciNet  MATH  Google Scholar 

  19. Loukas, A., Simonetto, A., Leus, G.: Distributed autoregressive moving average graph filters. IEEE Signal Process. Lett. 22(11), 1931–1935 (2015). https://doi.org/10.1109/LSP.2015.2448655

    Article  MATH  Google Scholar 

  20. Yin, L., Yang, R., Gabbouj, M., Neuvo, Y.: Weighted median filters: a tutorial. IEEE Trans. Circuits Syst. II: Analog Dig. Signal Process. 43(3), 157–192 (1996). https://doi.org/10.1109/82.486465

    Article  MATH  Google Scholar 

  21. Ruiz, L., Gama, F., Marques, A.G., Ribeiro, A.: Invariance-preserving localized activation functions for graph neural networks. IEEE Trans. Signal Process. 68, 127–141 (2020). https://doi.org/10.1109/TSP.2019.2955832

    Article  MathSciNet  MATH  Google Scholar 

  22. Segarra, S., Marques, A.G., Arce, G.R., Ribeiro, A.: Center-weighted median graph filters. In: 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 336–340 (2016). https://doi.org/10.1109/GlobalSIP.2016.7905859

  23. Segarra, S., Marques, A.G., Arce, G.R., Ribeiro, A.: Design of weighted median graph filters. In: 2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), pp. 1–5 (2017). https://doi.org/10.1109/CAMSAP.2017.8313120

  24. Tay, D.B., Jiang, J.: Time-varying graph signal denoising via median filters. IEEE Trans. Circuits Syst. II Express Briefs 68(3), 1053–1057 (2021). https://doi.org/10.1109/TCSII.2020.3017800

    Article  MATH  Google Scholar 

  25. Tay, D.B.: Sensor network data denoising via recursive graph median filters. Signal Process. (2021). https://doi.org/10.1016/j.sigpro.2021.108302

    Article  MATH  Google Scholar 

  26. Tay, D.B.: Median autoregressive graph filters. IEEE Signal Process. Lett. 30, 833–837 (2023). https://doi.org/10.1109/LSP.2023.3292741

    Article  MATH  Google Scholar 

  27. Romero, D., Ioannidis, V.N., Giannakis, G.B.: Kernel-based reconstruction of space-time functions on dynamic graphs. IEEE J. Select. Topics Signal Process. 11(6), 856–869 (2017). https://doi.org/10.1109/JSTSP.2017.2726976

    Article  MATH  Google Scholar 

  28. Qiu, K., Mao, X., Shen, X., Wang, X., Li, T., Gu, Y.: Time-varying graph signal reconstruction. IEEE J. Select. Topics Signal Process. 11(6), 870–883 (2017). https://doi.org/10.1109/JSTSP.2017.2726969

    Article  MATH  Google Scholar 

  29. Grassi, F., Loukas, A., Perraudin, N., Ricaud, B.: A time-vertex signal processing framework: scalable processing and meaningful representations for time-series on graphs. IEEE Trans. Signal Process. 66(3), 817–829 (2018). https://doi.org/10.1109/TSP.2017.2775589

    Article  MathSciNet  MATH  Google Scholar 

  30. Isufi, E., Loukas, A., Perraudin, N., Leus, G.: Forecasting time series with varma recursions on graphs. IEEE Trans. Signal Process. 67(18), 4870–4885 (2019). https://doi.org/10.1109/TSP.2019.2929930

    Article  MathSciNet  MATH  Google Scholar 

  31. Ioannidis, V.N., Shen, Y., Giannakis, G.B.: Semi-blind inference of topologies and dynamical processes over dynamic graphs. IEEE Trans. Signal Process. 67(9), 2263–2274 (2019). https://doi.org/10.1109/TSP.2019.2903025

    Article  MathSciNet  MATH  Google Scholar 

  32. Sea-Level Pressure, 1948-2010. (2016.05). http://research.jisao.washington.edu/data_sets/reanalysis

  33. 850hPa Air Temperature, 1948-2000. (2016.05). http://research.jisao.washington.edu/data_sets/reanalysis

  34. Sea Surface Temperature (SST) V2. (2015.12). http://www.esrl.noaa.gov/psd/data/gridded/data.noaa.oisst.v2.html

Download references

Acknowledgements

This work was partially supported by National Natural Science Foundation of China (grant: 62101215), the Natural Science Foundation of Jiangsu Province (grant: BK20210450), the Fundamental Research Funds for the Central Universities (grant: JUSRP121021) and the National Key R&D Program of China (2022YFD2100401).

Author information

Authors and Affiliations

Authors

Contributions

Shaodian Liu: methodology, writing, reviewing and editing, validation, Hongyu Ni: Conceptualization, writing, supervision, Yuan Zhong: methodology, Wenxu Yan: reviewing and editing, Wenyuan Wang: reviewing and editing, validation.

Corresponding authors

Correspondence to Wenxu Yan or Wenyuan Wang.

Ethics declarations

Conflict of interest

The authors declare that they have no Conflict of interest as defined by Springer or other interests that might be perceived to influence the results and discussion reported in this paper.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, S., Ni, H., Zhong, Y. et al. Adaptive weighted median filtering for time-varying graph signals. SIViP 19, 88 (2025). https://doi.org/10.1007/s11760-024-03610-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11760-024-03610-6

Keywords

Navigation