Title :
MLP/BP-based MIMO DFEs for distorted 16-QAM signal recovery in severe ISI channels with ACI disturbances
Author :
Hsu, Terng-Ren ; Hsu, Terng-Yin ; Wu, Lin-Jin ; Ou, Zong-Cheng
Author_Institution :
Dept. of Microelectron. Eng., Chung Hua Univ., Hsinchu, Taiwan
Abstract :
In this work, we base on multi-layered perceptron neural networks with backpropagation algorithm (MLP/BP) to construct multi-input multi-output (MIMO) decision feedback equalizers (DFEs). The proposal is used to recover distorted 16-point quadrature amplitude modulation (16-QAM) signal. From the simulations, we note that the proposed approach can recover severe distorted signals as well as suppress intersymbol interference (ISI), adjacent channel interference (ACI) and background additive white Gaussian noise (AWGN). As compared with a set of LMS DFEs, the proposed scheme can provide better BER and PER performance.
Keywords :
AWGN; MIMO communication; adjacent channel interference; backpropagation; decision feedback equalisers; error statistics; least mean squares methods; multilayer perceptrons; quadrature amplitude modulation; telecommunication computing; AWGN; BER performance; ISI channels; MIMO systems; QAM signal; adjacent channel interference; background additive white Gaussian noise; backpropagation algorithm; intersymbol interference; multi-input multi-output decision feedback equalizers; multi-layered perceptron neural networks; quadrature amplitude modulation signal; AWGN; Backpropagation algorithms; Decision feedback equalizers; Distortion; Intersymbol interference; MIMO; Multi-layer neural network; Multilayer perceptrons; Neural networks; Proposals;
Conference_Titel :
Microsystems, Packaging, Assembly and Circuits Technology Conference, 2009. IMPACT 2009. 4th International
Conference_Location :
Taipei
Print_ISBN :
978-1-4244-4341-3
Electronic_ISBN :
978-1-4244-4342-0
DOI :
10.1109/IMPACT.2009.5382290
