BER performance improvement of an FNN based equaliser using fuzzy tuned sigmoidal activation function

Adaptive equalisers are characterised in general by their structures, the learning algorithms and the use of training sequences. This paper presents a novel technique of improving the performance of conventional multilayer perceptron (MLP) based decision feedback equaliser (DFE) of reduced structural complexity by adapting the slope of the sigmoidal activation function using fuzzy logic control technique. The adaptation of the slope parameter increases the degrees of freedom in the weight space of the conventional feedforward neural network (CFNN) configuration. Application of this technique reduces the structural complexity of a conventional FNN equaliser, provides faster learning and significant performance gain.