DocumentCode :
2111744
Title :
A new complex recurrent neural network equalizer for data communication
Author :
Hongrui Jiang ; Kyung Sup Kwak
Author_Institution :
Dept.of Electron. Eng., Inha Univ., Inchon
Volume :
4
fYear :
2002
fDate :
2002
Firstpage :
1271
Abstract :
A new modified version called decision feedback complex recurrent neural network equalizer (DFCRNNE) is proposed with the study of complex recurrent neural network adaptive equalizer (CRNNE). Based on DFCRNNE, a modified real time recurrent learning (CRTRL) algorithm is developed. Simulation results show that DFCRNNE has better performance than the CRNNE based on traditional CRTRL algorithm in complex nonlinear channels with severe intersymbol interference (ISI) and nonlinear distortion.
Keywords :
data communication; decision feedback equalisers; intersymbol interference; recurrent neural nets; complex recurrent neural-network equalizer; data communication; intersymbol interference; modified real time recurrent learning algorithm; nonlinear channels; nonlinear distortion;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Industrial Electronics, 2002. ISIE 2002. Proceedings of the 2002 IEEE International Symposium on
Print_ISBN :
0-7803-7369-3
Type :
conf
DOI :
10.1109/ISIE.2002.1025972
Filename :
1025972
Link To Document :
بازگشت