Neuro Fuzzy System Based Adaptive Equaliser in Mobile Cellular Channels
SSNL Venkateswara Rao1, Gottapu Sasibhushana rao2
1SSNL Venkateswara Rao, Department of Electronics and Communications Engineering, GITAM University, Visakhapatnam, India.
2Dr G Sasibhushana Rao, Department of Electronics and Communications Engineering, Andhra University, Visakhapatnam, India.
Manuscript received on 15 May 2019 | Revised Manuscript received on 22 May 2019 | Manuscript Published on 02 June 2019 | PP: 510-514 | Volume-8 Issue-7S2 May 2019 | Retrieval Number: G10860587S219/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Mobile Cellular Channels are subjected to multi-path reflections by virtue of the environment they are operating. Owing to this, the transmitted symbols are subjected to different types of fading. This is more evident in urban scenario. The time-dispersive nature of the channel causes Inter symbol Interference (ISI). The Frequency re-use concept is adopted in mobile communications to raise the system capacity. This technique causes co channel interference (CCI). Spectral seepage in the system owing to filters, cause Adjacent channel interference. Hence the mobile channels are viewed as time varying. This ultimately results in more bit errors in the communication system. To keep the BER within the specified limits in time varying channels, receiver employs adaptive equalizer. These are based on different algorithms.. Most of these algorithms are proved to be much complex and not implementable in dealing with non linear and time varying channels. Of late, Neuro Fuzzy systems (NFS) are used to model adaptive equaliser. Fuzzy systems work on if then rules with membership functions (MF) to minimise output error. It is seen that the consolidation of fuzzy logic and neural network can deal efficiently with uncertainties associated with nonlinear time varying channels. In this paper, we present NFS based adaptive equaliser. Channel and Equaliser outputs are observed for the given input binary sequence. BER versus SINR curves are plotted and analysed.
Keywords: Adaptive Equaliser, ISI, the Wireless Channel, BER, the Membership Function.
Scope of the Article: Communications