A non-linear noise canceller based on additive-multiplicative fuzzy neural networks

Author

Zhai, Dong-hai ; Li, Li ; Jin, Fan

Author_Institution

Sch. of Comput. & Commun. Eng., Southwest Jiaotong Univ., Sichuan, China

Volume

1

fYear

2003

fDate

14-17 Dec. 2003

Firstpage

168

Abstract

A non-linear noise canceller based on the additive-multiplicative fuzzy neural network (AMFNN) is proposed in this paper. The novel noise canceller has the advantages of neural networks, such as parallel-distributed information processing, fault-tolerance and robustness. In this paper, AMFNN is used to approximate noise, and the noise approximated is cancelled from the measuring signal to obtain useful signal. Here, the AMFNN model, the learning algorithm and the universal approximation are discussed. The simulation results show that this method has a strong noise canceling capability.

Keywords

approximation theory; fault tolerance; fuzzy neural nets; learning (artificial intelligence); signal denoising; stability; additive-multiplicative fuzzy neural networks; fault-tolerance; learning algorithm; noise approximation; nonlinear noise canceller; nonlinear signal processing; parallel-distributed information processing; robustness; Adaptive filters; Colored noise; Computer networks; Filtering; Fuzzy neural networks; Information processing; Neural networks; Noise cancellation; Noise measurement; Signal processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks and Signal Processing, 2003. Proceedings of the 2003 International Conference on

Conference_Location

Nanjing

Print_ISBN

0-7803-7702-8

Type

conf

DOI

10.1109/ICNNSP.2003.1279238

Filename

1279238