Reduced complexity in-phase/quadrature-phase turbo equalisation using radial basis functions

A novel reduced complexity radial basis function (RBF) neural network based equaliser, referred to as the in-phase/quadrature-phase RBF equaliser (I/Q-RBF-EQ), is proposed. The I/Q-RBF-EQ is employed in the context of turbo equalisation (TEQ) assisted by iterative channel estimation. The performance of the I/Q-RBF-TEQ is characterized in a noise limited environment over an equally weighted, symbol-spaced three-path Rayleigh fading channel. The I/Q-RBF-TEQ achieved the same performance as the conventional turbo equaliser, while achieving a complexity reduction by a factor of 1.5 and 109.6 for 4-QAM and 16-QAM, respectively