Abstract
Orthogonal frequency division multiplexer
(OFDM) is a recent modulation scheme used to transmit
signals across power line communication (PLC) channel due
to its robustness against some known PLC problems.
However, this scheme is greatly affected by the impulsive
noise (IN) and often causes corruption with the transmitted
bits. Different impulsive noise error correcting methods have
been introduced and used to remove impulsive noise in
OFDM systems. However, these techniques suffer some
limitations and require much signal to noise ratio (SNR)
power to operate. In this paper, an approach of designing an
effective impulsive-noise error-correcting technique was
introduced using three-known artificial neural network
techniques (Levenberg-Marquardt, Scaled conjugate
gradient, and Bayesian regularization). Findings suggest that
both Bayesian regularization and Levenberg-Marquardt
ANN techniques can be used to effectively remove the
impulsive noise present in an OFDM channel and using the
least SNR power.