Title :
Blind equalization of a channel using continuous wavelet networks
Author :
Mirabdollah, Mohammad Hossein ; Shafiee, Masoud
Author_Institution :
Nat. Iranian Gas Co., Tehran, Iran
Abstract :
A new blind equalization method based on continuous wavelet network is presented to address the problem of nonlinear or non-minimum phase channel equalizations. Due to special features of continuous wavelet network, a simple criterion is outlined by which the blind training of the network, under some conditions, becomes feasible. In addition, it is discussed why the training process might be trapped in local minima, and how to achieve the global minima.
Keywords :
blind equalisers; learning (artificial intelligence); telecommunication channels; telecommunication computing; wavelet transforms; blind equalization; continuous wavelet network; local minima; neural network training process; nonlinear phase channel equalization; nonminimum phase channel equalization; Blind equalizers; Continuous wavelet transforms; Convergence; Decision feedback equalizers; Electronic mail; Intersymbol interference; Iterative algorithms; Neural networks; Phase estimation; Transfer functions; Blind equalization; Wavelet network;
Conference_Titel :
Control and Decision Conference, 2009. CCDC '09. Chinese
Conference_Location :
Guilin
Print_ISBN :
978-1-4244-2722-2
Electronic_ISBN :
978-1-4244-2723-9
DOI :
10.1109/CCDC.2009.5191601
