No abstract

Neural network based Interference cancellers occupy a prominent place in the class of multi user detectors for CDMA.The present work focuses on the effect of pre-processing of the data fed to the neural networks in those receivers. The effect on bit error rate due to pre-processing is presented, with respect to a variation of signal to noise ratios and the number of parallel interference canceller stages. The work considered, R a y l e i g h multipath fading channel as the medium and DPSK as baseband modulation.

Orthogonal frequency division multiplexing has high data rate capacity and lowest ISI, among the different present technologies and hence considered as the modulation technique for next generation wireless communication. Channel estimation is one of the crucial challenges in designing high performance receivers based on OFDM. In this paper, different operation mode for Levenberg Maquardt algorithm powered back propagation feed forward neural networks are examined for channel estimation of OFDM receivers. A novel, semi blind, optimized channel estimation technique is presented based on the outcomes of different experiments. The tests were conducted in the background of varying channel characteristics, subcarriers, pilot positioning etc. The performance of the different techniques were analyzed based on bit error rate, which is also used for the comparison between the different techniques. The simulations of the tests are included for illustrating the results.

No abstract

Abstract-Reduction of multiple access interference is occupying great importance in wireless communication using code division multiple access (CDMA). Different interference cancellation schemes were developed and neural network based canceller is one of them. This paper introduces the effect of training parameters on achieving optimum performance on a multi stage parallel interference canceller (PIC) based on neural network.Index Terms-BER, CDMA, LM algorithm, neural network.