Unscented kalman filter-trained MRAN equalizer for nonlinear channels

Authors:
Ye Zhang;Jianhua Wu;Guojin Wan;Yiqiang Wu
Affiliations:
Electronic and information school of Nanchang University, Nanchang, China;Electronic and information school of Nanchang University, Nanchang, China;Electronic and information school of Nanchang University, Nanchang, China;Electronic and information school of Nanchang University, Nanchang, China
Venue:
ICONIP'06 Proceedings of the 13th international conference on Neural Information Processing - Volume Part II
Year:
2006

Citing 3
Cited 0

Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Channel equalization using radial basis function network

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 03
Adaptive nonlinear system identification using minimal radial basis function neural networks

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 06

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, the application of minimal resource allocation network (MRAN) trained with Unscented Kalman Filter (UKF) to the nonlinear channel equalization problems was discussed. Using novel criterion and prune strategy, the algorithm uses online learning, and has the ability to grow and prune the hidden neurons to realize a minimal network structure. Simulation results show that the equalizer is well suited for nonlinear channel equalization problems and the proposed equalizer required short training data to attain good performance.