Automatic digital modulation recognition using artificial neural network and genetic algorithm

doi:10.1016/j.sigpro.2003.10.019

2004-02-01

179

PRE

M. L. Dennis Wong

Asoke K. Nandi

DOI：10.1016/j.sigpro.2003.10.019

原文链接

原文求助

摘要

En 中文

Automatic recognition of digital modulation signals has seen increasing demand nowadays. The use of artificial neural networks for this purpose has been popular since the late 1990s. Here, we include a variety of modulation types for recognition, e.g. QAM16, V29, V32, QAM64 through the addition of a newly proposed statistical feature set. Two training algorithms for multi-layer perceptron (MLP) recogniser, namely Backpropagation with Momentum and Adaptive Learning Rate is investigated, while resilient backpropagation (RPROP) is proposed for this problem, are employed in this work. In particular, the RPROP algorithm is applied for the first time in this area. In conjunction with these algorithms, we use a separate data set as validation set during training cycle to improve generalisation. Genetic algorithm (GA) based feature selection is used to select the best feature subset from the combined statistical and spectral feature set. RPROP MLP recogniser achieves about 99% recognition performance on most SNR values with only six features selected using GA. (C) 2003 Elsevier B.V. All rights reserved.

Keyword:

modulation recognition

artificial neural networks

genetic algorithm

feature subset selection