DocumentCode :
2607758
Title :
A neural predictor for blind equalization of digital communication systems
Author :
Cavalcante, Charles C. ; F, Jugurta R Montalvão ; Dorizzi, Bernadette ; Mota, Joao Cesar M
Author_Institution :
Univ. Fed. do Ceara, Fortaleza, Brazil
fYear :
2000
fDate :
2000
Firstpage :
347
Lastpage :
351
Abstract :
In digital channel equalization, self-learning techniques are used in the cases where a training period is not available. Considering the transmitted sequence as composed of independent random variables, the equalization task can be done by means of prediction. In this work we propose to use artificial neural networks (ANN), instead of a linear prediction device, in order to obtain a better performance. Prediction concepts are revisited and a new self-organized algorithm is proposed to update the first layer in the nonlinear predictor whose aim is to avoid local minimum points in the applied cost function. The second layer is updated by using a classical supervised algorithm. Simulation results are presented which illustrate the performance of this technique
Keywords :
blind equalisers; digital communication; neural nets; prediction theory; telecommunication computing; unsupervised learning; applied cost function; artificial neural networks; blind equalization; classical supervised algorithm; digital communication systems; independent random variables; neural predictor; nonlinear predictor; performance; prediction; self-learning techniques; self-organized algorithm; simulation; transmitted sequence; Artificial neural networks; Blind equalizers; Cost function; Delay estimation; Digital TV; Digital communication; Filters; Neural networks; Noise figure; Random variables;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Adaptive Systems for Signal Processing, Communications, and Control Symposium 2000. AS-SPCC. The IEEE 2000
Conference_Location :
Lake Louise, Alta.
Print_ISBN :
0-7803-5800-7
Type :
conf
DOI :
10.1109/ASSPCC.2000.882498
Filename :
882498
Link To Document :
بازگشت