Skip to main content
SpringerLink
Log in

An Efficiency-Based Improvement of a Reconstruction Algorithm Reconstructs Signal from Its Scattering Transform

  • Published:
International Journal of Wireless Information Networks Aims and scope Submit manuscript

Abstract

Scattering transform has many advantages and has been widely used in various fields since proposed. An algorithm using machine learning was proposed by some developers of Kymatio to reconstruct the signal based on the Scattering transform of the signal on the internet (Reconstruct a synthetic signal from its scattering transform (DB/OL) https://www.kymat.io/gallery_1d/reconstruct_torch.html#sphx-glr-gallery-1d-reconstruct-torch-py and Andreux et al. https://arxiv.org/1812.11214, 2019). In this paper, I improve this reconstruction algorithm to an efficiency-based algorithm. However, the coefficient in the original formula for the input signal is defined and followed by original gradient descent algorithm with the learning rate multiplied by an accelerator or braker for every iteration. Once the error is spotted out then the system is discarded. By introducing an efficiency parameter, the calculation time and the eliminated error are linked, so that coefficient can be determined to improve the efficiency and eliminated most errors in a short time. Also, the experimenter can adjust the importance parameter in the efficiency parameter to determine the importance of speed and accuracy, which provides the experimenter with more choices.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Fig.1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Data Availability

None.

References

  1. The Mathwork, Inc., Wavelet Scattering. https://ww2.mathworks.cn/help/wavelet/ug/wavelet-scattering.html. Accessed 28 Feb 2021

  2. Mallat, S. "Group Invariant Scattering." Communications in Pure and Applied Mathematics.. Vol. 65, Number 10, 2012, pp. 1331–1398.

    Article  MathSciNet  MATH  Google Scholar 

  3. Bruna, J., and Mallat S. "Invariant Scattering Convolution Networks."IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 35, Number 8, 2013, pp. 1872–1886.

    Article  Google Scholar 

  4. Andén, J., and Mallat S. "Deep Scattering Spectrum." IEEE Transactions on Signal Processing. Vol. 62, Number 16, 2014, pp. 4114–4128.

    Article  MathSciNet  MATH  Google Scholar 

  5. Mallat, S. "Understanding deep convolutional networks." Philosophical Transactions of the Royal Society A. Volume 374: 20150203, 2016, pp. 1–16. https://doi.org/10.1098/rsta.2015.0203.

    MathSciNet  Google Scholar 

  6. Lostanlen, V. Scattering.m. A MATLAB toolbox for wavelet scattering. https://github.com/lostanlen/scattering.m. Accessed 28 Feb 2021

  7. Andén J., Lostanlen V. and Mallat S. “Joint Time–Frequency Scattering.” IEEE Transactions on Signal Processing. Vol. 67, Number 14, July 15, 2019, pp.3704–3718.

    Article  MathSciNet  MATH  Google Scholar 

  8. Gupta, R., Khari, M., Gupta, V., Wu, E. V., Herrera-Viedma, E., & Crespo, R. G. (2020). Fast Single Image Haze Removal Method for Inhomogeneous Environment Using Variable Scattering Coefficient. Computer Modeling in Engineering & Sciences, 123(3), 1175-1192. https://doi.org/10.32604/cmes.2020.010092’.

    Article  Google Scholar 

  9. Lopez, D., & Manogaran, G. (2018). Health data analytics using scalable logistic regression with stochastic gradient descent. International Journal of Advanced Intelligence Paradigms, 10(1/2), 118. https://doi.org/10.1504/ijaip.2018.10010530.

    Article  Google Scholar 

  10. The Kymatio Developers, Reconstruct a synthetic signal from its scattering transform. https://www.kymat.io/gallery_1d/reconstruct_torch.html#sphx-glr-gallery-1d-reconstruct-torch-py. Accessed 28 Feb 2021

  11. Andreux M., Angles T., Exarchakis G., Leonarduzzi R., Rochette G., Thiry L., Zarka J., Mallat S., Andén J., Belilovsky E., Bruna J., Lostanlen V., Hirn M. J., Oyallon E., Zhang S., Cella C., Eickenberg M. (2019). Kymatio: Scattering Transforms in Python. arXiv preprint https://arxiv.org/1812.11214.

  12. The Kymatio Developers, User Guide. https://www.kymat.io/userguide.html. Accessed 28 Feb 2021

  13. Waldspurger I., “Exponential decay of scattering coefficients,” in Proc. Sampling Theory Appl. Conf., 2017, pp. 143–146.

  14. Kengo Tateishi. The Mathematics of Machine Learning in the vernacular. Beijing, China, Posts and Telecom Press, 2020, pp. 15-58

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Beijing University of Posts and Telecommunications, Beijing, People’s Republic of China

    Kaiheng Zhang

Authors
  1. Kaiheng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kaiheng Zhang.

Ethics declarations

Conflict of interest

No conflict of interest.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, K. An Efficiency-Based Improvement of a Reconstruction Algorithm Reconstructs Signal from Its Scattering Transform. Int J Wireless Inf Networks 30, 111–118 (2023). https://doi.org/10.1007/s10776-021-00526-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10776-021-00526-7

Keywords

Search

Navigation