Development of Hybrid ANN Structures for Performance Enhancement of Adaptive Channel Equalisers

Adaptive equalisation in digital communication systems is a process of compensating the disruptive effects caused mainly by inter symbol interference in a band-limited channel and plays a vital role for enabling higher data rate in modern digital communication system. Designing efficient nonlinear equalisers having low structural complexity with faster learning algorithms is also an area of major research interest in the present scenario. Several hybrid Artificial Neural Network structures on the backbone of feedforward neural network and recurrent neural network have been proposed and suitable modification of existing learning algorithms for the new configurations are developed. Further in order to prove the efficacy of the proposed hybrid ANN structures, exhaustive simulation study of adaptive equalisation of communication channels have been analysed.