Detection of Weak Signals Based on RBF Neural Network Filtering

Jian Jun Li

doi:10.4028/www.scientific.net/AMR.211-212.846

Paper Titles

A Method for Design of Oblique Intersection Beams in Roof Structures
p.827

Study on a New-Style Air-Condition System Driven by Combination of Exhaust Heat of Engine and Solar Energy
p.832

The Impact of Green Purchasing on Enterprise Performance: Empirical Study of China Textile and Garment Industry
p.837

Study on Rebuilding of X53 Milling Machine for Numerical Control
p.842

Detection of Weak Signals Based on RBF Neural Network Filtering
p.846

Interoperable STEP-NC Enabled Process Planning for Intelligent Machining
p.850

Model Based Design and Implementation of Hierarchical and Distributed Control for Robotic Flexible Manufacturing System Cells Using Petri Nets
p.856

Design and Implementation of Debugging Structure in Full-Custom CPU
p.861

Graphic Representation on Algebra Concepts of University Students Based on Clustering Approach
p.866

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 211-212Detection of Weak Signals Based on RBF Neural...

Detection of Weak Signals Based on RBF Neural Network Filtering

Abstract:

The algorithm is presented in this paper based on the character about RBF adaptive neural network filtering needn’t previous information of input single and noise and has better ability of nonlinear mapping and self-study. The adaptive noise cancellation system is designed. The system can improve LMS algorithm slow convergence speed and extraction of narrow band signal faults and has small amount of calculation and real-time good characteristic. The effect is better at Using this system in the field of life characteristic signal detection identification. Results show that the system has the high feasibility and validity.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 211-212)

Pages:

846-849

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.211-212.846

Citation:

Cite this paper

Online since:

February 2011

Authors:

Jian Jun Li

Keywords:

Adaptive Filter, Neural Network (NN), Noise Cancellation, RBF

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] W Maass, E D Sontag. Neural systems as nonlinear filters[J]. Neural Computation 2000, 12(8): 1743-1772.

DOI: 10.1162/089976600300015123

Google Scholar

[2] Simon Haykin. Neural network theory [M]. Beijing: CHINA MACHINE PRESS, (2004).

Google Scholar

[3] S I Amari, H park, K Fukvmizu, Adaptive method for realizing natural gradient learning for multi-layer perceptrons[J]. Neural Computation 2000, 12: 1399-1409.

DOI: 10.1162/089976600300015420

Google Scholar

[4] Chen K M, Huang Y, J. Microwave life-detection systerns for searching human subjects under earthquake rubble Or behind barrier[J]. IEEE Transactions on Biomedical Engineering, 2000, 27(1): 105-114.

DOI: 10.1109/10.817625

Google Scholar

[5] Xiao-Long zhu, Xian-Da zhang, Adaptive RLS algorithm for blind source separation using a natural gradient[J] ieee signal processing letters. 2002, 9(12): 432-435.

DOI: 10.1109/lsp.2002.806047

Google Scholar

[6] Wang JQ, Dong XZ, Wang HB, et a1. Experimental study on noncontact detection of breathing and heartbeat based on millimeter wave [J]. J Fourth Mil Med Univ, 2001；22(2): 180—182.

Google Scholar