IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 5
Equalization Using the Bilinear Recursive Polynomial Perceptron with Decision Feedback
Como, Italy
July 24-July 27
ISBN: 0-7695-0619-4
In order to improve the performance and simplify the structure of the equalizer using bilinear recursive polynomial perceptron (BRPE), a new equalizer, which is an equalizer using bilinear recursive polynomial perceptron with decision feedback (BRPDFE), is proposed. The proposed BRPDFE is compared with the BRPE in terms of mean square error (MSE). In addition, the performance is compared with the conventional decision feedback equalizer (DFE), the multilayer perceptron decision feedback equalizer (MLPDFE) and the BRPE in terms of bit-error rate (BER) in two o data transmission systems. One is a digital communication system in which the dominant distortion factor is inter-symbol interference (ISI). In addition, the other is a digital storage system in which the primary interference element is nonlinear distortion. The results from analysis and simulation show that the proposed BRPDFE is superior to the other equalizers. Moreover, the BRPDFE has the simpler structure than the other equalizers.
Citation:
Sooyong Choi, Daesik Hong, "Equalization Using the Bilinear Recursive Polynomial Perceptron with Decision Feedback," ijcnn, vol. 5, pp.5366, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 5, 2000