A De-Noising Method for Non-Stationary Signal

Yan Hai Shang

doi:10.4028/www.scientific.net/AMM.148-149.309

Paper Titles

Hydrogen Storage Kinetics of Mg₂₀Ni_10-xM_x (M=Cu, Co; x=0-4) Alloys Prepared by Melt Spinning
p.291

Sorting Mechanism and Airflow Simulation of Garbage Pneumatic Separator
p.297

Modal Analysis of a New Solid Micro-Gyroscope with Bulk Giant Magnetostrictive Material (GMM) Resonator
p.301

Study on the Artificial Breeding Techniques in Ternstroemia gymnnanthera, an Important Industrial Tanning Plant
p.305

A De-Noising Method for Non-Stationary Signal
p.309

The Kinetic Analysis of Carbide Lime Reaction Based on Multi-Heating Rate Method
p.313

Linear Parameter-Varying Modeling of Electric Vehicle Air Conditioning System
p.318

Characteristics Analysis of Photonic Crystal Fiber with Hexagonal and Octagonal Structure
p.326

Analysis of C80B Wagon’s Load-Stress Transfer Relation
p.331

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 148-149A De-Noising Method for Non-Stationary Signal

A De-Noising Method for Non-Stationary Signal

Abstract:

The paper proposed a de-noising method for non-stationary signals received by a small-size antenna array. By taking into consideration of the correlation of signals received by antennae which compose the antenna array, we could improve greatly the discovery probability of signal coefficients in time-frequency domain through taking advantage of the method of integration for signal detection. Meanwhile, under the assumption of Gaussian noise environment, the probability density functions of noise and signal after integration were also presented. In order to extract the coefficients for signal and reduce the Type I error further, an algorithm based False Discovery Rate (FDR) was put forward. Finally, a comparison between the detection performances before and after integration was made: under same rate of Type I error, the detection performance of signal after integration is improved significantly. And the effectiveness of the method was showed by experimental results as well.

You might also be interested in these eBooks

Mechanical Engineering, Materials and Energy

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 148-149)

Pages:

309-312

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.148-149.309

Citation:

Cite this paper

Online since:

December 2011

Authors:

Yan Hai Shang

Keywords:

De-Noising, Detection, Integration, Multiple Hypothesis, Non-Stationary, Type I Error, Wavelet Packet (WP)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Siliang, Wu: Study on Data Processing Technique for Vector Miss Distance Measurement System and Its Practice(Post-doctoral Research Report, Beiing Institute of Technology, China 1998).

Google Scholar

[2] D. Donoho and I. Johnstone, Ideal spatial adaptation via wavelet shrinkage, Biometrika, vol. 81, p.425–455, December (1994).

DOI: 10.1093/biomet/81.3.425

Google Scholar

[3] D. Donoho and I. Johnstone, Adpating to unknown smoothness via wavelet shrinkage, J. American Statist. Assoc., vol. 90, pp, 1200-1224, (1995).

DOI: 10.1080/01621459.1995.10476626

Google Scholar

[4] Y. Benjamini, and Y. Hochberg, Controlling the false discovery rate: a practical and powerful approach to multiple testing, J. R. Statist. Soc. B, vol. 57, pp.289-300, (1995).

DOI: 10.1111/j.2517-6161.1995.tb02031.x

Google Scholar

[5] D. B. Percival and A. T. Walden, Wavelet Methods for Time Series Analysis. London: Cambridge University Press, (2000).

Google Scholar