Wavelet Preprocessed Neural Network Based Receiver for Low SNR Communication System

Conference: European Wireless 2015 - 21th European Wireless Conference
05/20/2015 - 05/22/2015 at Budapest, Hungary

Proceedings: European Wireless 2015

Pages: 6Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Authors:
Alzaq, Husam; Ustundag, B. Berk (Computer Engineering Department, Istanbul Technical University, Maslak, 34469, Istanbul)

Abstract:
In this paper, we address the problem of digital modulation classification in Additive White Gaussian Noise (AWGN) for Pattern Based cognitive Communication System (PBCCS). In order to classify digital modulation signal reliably, we propose a cognitive receiver that is based on Wavelet filterbanks and Artificial Neural Network(ANN). We verify this system by using 3-bit, 4-bit and 5-bit glossary spaces. The performance of the proposed system is investigated through the simulations. The simulation results show that using wavelet transform and neural network, a signal-to-noise-ratio of ??8, 0 and 4 dB is achieved at BER of 10-5.