Premium
MC–CDMA receiver design using recurrent neural networks for eliminating multiple access interference and nonlinear distortion
Author(s) -
C.V. Ravi Kumar,
Bagadi Kala Praveen
Publication year - 2017
Publication title -
international journal of communication systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.344
H-Index - 49
eISSN - 1099-1131
pISSN - 1074-5351
DOI - 10.1002/dac.3328
Subject(s) - code division multiple access , computer science , nonlinear distortion , artificial neural network , spectral efficiency , interference (communication) , electronic engineering , wireless network , minimum mean square error , spread spectrum , wireless , channel (broadcasting) , amplifier , telecommunications , bandwidth (computing) , artificial intelligence , mathematics , engineering , statistics , estimator
Summary Multicarrier code division multiple access (MC–CDMA) is a promising wireless communication technology with high spectral efficiency and system performance. However, all multiple access techniques including MC–CDMA were most likely to have multiple access interference (MAI). So this paper mainly aims at designing a suitable receiver for MC–CDMA system to mitigate such MAI. The classical receivers like maximal ratio combining, minimum mean square error, and iterative block–decision feedback equalization fail to cancel MAI when the MC–CDMA is subjected to severe nonlinear distortions, which may occur due to saturated power amplifiers or arbitrary channel conditions. Being highly nonlinear structures, the neural network receivers such as multilayer perceptron and recurrent neural network could be better alternative for such a case. The feasibility, efficiency, and effectiveness of the proposed neural network receiver are studied thoroughly for MC–CDMA system under different nonlinear conditions.