Volume 4 Number 5 (Sep. 2014)
Home > Archive > 2014 > Volume 4 Number 5 (Sep. 2014) >
IJAPM 2014 Vol.4(5): 313-323 ISSN: 2010-362X
DOI: 10.7763/IJAPM.2014.V4.304

Curvelet Based Multiresolution Analysis of Graph Neural Networks

Bharat Bhosale
Abstract—Multiresolution techniques are deeply related to image/signal processing, biological and computer vision, scientific computing, optical data analysis. Improving quality of noisy signals/images has been an active area of research in many years. Although wavelets have been widely used in signal processing, they have limitations with orientation selectivity and hence, they fail to represent changing geometric features along edges effectively. Curvelet transform on the contrary exhibits good reconstruction of the edge data by incorporating a directional component to the conventional wavelet transform and can be robustly used in the analysis of complex neural networks; which in turn are represented by graphs, called Graph Neural Networks.
This paper explores the application of curvelet transform in the analysis of such complex networks. Especially, a technique of Fast Discrete Curvelet Transform de-noising with the Independent Component Analysis (ICA) for the separation of noisy signals is discussed. Two different approaches viz. separating noisy mixed signals using fast ICA algorithm and then applying Curvelet thresholding to de-noise the resulting signal, and the other one that uses Curvelet thresholding to de-noise the mixed signals and then the fast ICA algorithm to separate the de-noised signals are presented for the purpose. The Signal-to-Noise Ratio and Root Mean Square Error are used as metrics to evaluate the quality of the separated signals.

Index Terms—Curvelet transform, graph neural networks, curvelet thresholding, denoising.

Bharat Bhosale is with S. H. Kelkar College of Arts, Commerce and Science, University of Mumbai, Devgad 416613 (M.S.), India (email: bn.bhosale@rediffmail.com).

Cite: Bharat Bhosale, "Curvelet Based Multiresolution Analysis of Graph Neural Networks," International Journal of Applied Physics and Mathematics vol. 4, no. 5, pp. 313-323, 2014.

General Information

ISSN: 2010-362X (Online)
Abbreviated Title: Int. J. Appl. Phys. Math.
Frequency: Quarterly
DOI: 10.17706/IJAPM
Editor-in-Chief: Prof. Haydar Akca 
Abstracting/ Indexing:  Index Copernicus, IET INSPEC, Chemical Abstracts Services (CAS), Nanowerk Database, Google Scholar, EBSCO, etc.
E-mail: ijapm@iap.org
  • May 14, 2019 News!

    IJAPM Vol 7, No 4-Vol 8, No 3 have been indexed by EI (Inspec)   [Click]

  • Sep 16, 2021 News!

    IJAPM Vol 11, No 4 has been published with online version   [Click]

  • Jun 10, 2021 News!

    Vol 11, No 3 has been published with online version   [Click]

  • Mar 15, 2021 News!

    Vol 11, No 2 has been published with online version   [Click]

  • Dec 24, 2020 News!

    Vol 11, No 1 has been published with online version   [Click]

  • Read more>>