On the use of neural network-based determination of weighted despreading sequences for a DS/CDMA system


Ciftlikli C., Develi I.

ENGINEERING INTELLIGENT SYSTEMS FOR ELECTRICAL ENGINEERING AND COMMUNICATIONS, cilt.11, sa.3, ss.157-161, 2003 (SCI-Expanded) identifier identifier

Özet

The stepping chip weighting waveforms used in a coherent receiver are designed with the purpose of multiple access interference rejection by emphasizing the transitions in the received spreading signal of interest [1]. This paper presents a useful method based on neural networks to help the determination of the despreading sequences weighted by the stepping chip weighting waveforms for a direct sequence/code division multiple access system. Numerical examples for additive white Gaussian noise channels show that the parameter values of the chip weighting waveforms obtained by the proposed method are satisfactory and does not cause any degradation on the bit error rate performance of the system.