Training Strategy of Fuzzy-Firefly Based ANN in Non-Linear Channel Equalization

Channel equalization is remaining a challenge for the researcher. Especially non-linear channel as well extremely dispersive channel, an effective equalizer required. It common knowledge that equalizers based on neural networks (NN) outperform adaptive filter-based linear equalizers. To train NN equalizers, gradient-descent-based approaches like back-propagation algorithm are often utilized, although they have drawbacks such trapping of local minima, slower convergence, and compassion to log in. In this work, we presented novel training strategy using fuzzy firefly (FFA) equalization. By proper network topology parameters, suggested system offers stronger exploitation exploration skills, ability solve minima issue. The performance can be analyzed by estimating two parameters i.e. MSE BER. exhibit technique’s resilience in performance, burst error situation was used, outcomes showed more managing situations than previous methods. proposed method through simulation, Furthermore, it proved validates wide range SNR, also outperforms existing NN-based