Blind channel equalization based on Complex-valued neural network and probability density fitting

Chouaib Farhati (1) , Souhaila Fki (1) , Abdeldjalil Aissa El Bey (2, 3) , Fatma Abdelkefi (1)

1 SUP'COM [TUNIS] - Ecole supérieure des communications de Tunis
2 IMT Atlantique - MEE - Département Mathematical and Electrical Engineering
3 Lab-STICC_COSYDE - Equipe Communication System Design

In this paper, we study blind equalization techniques to reduce the intersymbol interference (ISI) and we are particularly interested in equalizers based on probability density fitting (PDF). The PDF criterion was used with conventional linear equalizers. So we try in this paper to use this criterion in a nonlinear context using a neural network architecture. The network weights are updated by minimizing, at first, the stochastic quadratic distance, then the Multimodulus quadratic distance between the equalized PDF and some target distribution. Our approach shows a better performance in terms of mean square error (MSE) and symbol error rate (SER).

Keywords: blind equalization; Neural network; probability density fitting

Domains: Signal and Image processing

Chouaib Farhati, Souhaila Fki, Abdeldjalil Aissa El Bey, Fatma Abdelkefi. Blind channel equalization based on Complex-valued neural network and probability density fitting. IEEE International Wireless Communications and Mobile Computing Conference (IWCMC), May 2022, Dubrovnik, Croatia. ⟨10.1109/IWCMC55113.2022.9824100⟩. ⟨hal-03633511⟩