A De-noising Scheme Based on the Null Hypothesis of Intrinsic Mode Functions

Mahdi H. Al-Badrawi, Bessam Z. Al-Jewad, Wayne Smith, Nicholas J. Kirsch

IEEE Signal Processing Letters · 2016 · 13 citations · 20 references

Concepts

Abstract

Empirical mode decomposition is a nonparametric adaptive tool that decomposes signals into a set of zero-mean modes called intrinsic mode functions (IMFs) that can be used to denoise a signal by selecting the relevant (noise-free) modes. In this paper, the statistical properties of IMFs, produced by a range of signal distributions, are examined. Insight from the statistical analysis is used in a null hypothesis test that validates a best fit model distribution of the IMFs. This test is then used in a de-noising scheme, which is evaluated using different test signals corrupted with white and colored noise. Simulations under different scenarios demonstrate the efficacy of the proposed method as compared to other EMD-based de-noising techniques.

References

20