Performance of RBF neural networks for array processing in impulsive noise environment

Authors:
Wenqiang Guo;Tianshuang Qiu;Hong Tang;Wenrong Zhang
Affiliations:
Dalian University of Technology, Dalian 116024, PR China and Xinjiang University of Finance and Economics, Urumchi 830012, PR China;Dalian University of Technology, Dalian 116024, PR China;Dalian University of Technology, Dalian 116024, PR China;Dalian University of Technology, Dalian 116024, PR China
Venue:
Digital Signal Processing
Year:
2008

Citing 9
Cited 0

Signal processing with alpha-stable distributions and applications

Signal processing with alpha-stable distributions and applications
Robust spatial filtering of coherent sources for wireless communications

Signal Processing
Robust auto-focusing wideband DOA estimation

Signal Processing
Robust adaptive beamforming in alpha-stable noise environments

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 05
DOA estimation based on the database retrieval technique with nonuniform quantization and clustering

Digital Signal Processing
Underwater sources location in non-Gaussian impulsive noise environments

Digital Signal Processing
The robust covariation-based MUSIC (ROC-MUSIC) algorithm forbearing estimation in impulsive noise environments

IEEE Transactions on Signal Processing
A subspace-based direction finding algorithm using fractional lowerorder statistics

IEEE Transactions on Signal Processing
Measurements and models of radio frequency impulsive noise for indoor wireless communications

IEEE Journal on Selected Areas in Communications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper addresses the array processing problems (mainly focuses on direction of arrival estimation and beamforming) of mobile communication system using linear antenna arrays in high impulsive noise environment. One possible way to simulate the impulsive noise is to introduce alpha-stable distribution as the noise model. In order to reduce the computational complexity, the problems of DOA and beamforming are approached as a nonlinear mapping which can be modeled using a suitable radial-basis function neural network (RBFNN) trained with input-output pairs. This paper discusses the application of a three-layer RBFNN to perform the DOA estimation and beamforming in presence of impulsive noise. The performance of the network is compared to that of the algorithms based fractional lower-order statistics. Simulations show that the RBFNN is appropriate to approach the DOA estimation and beamforming. At the same time, the RBFNN substantially reduces the computation complexity.