Intelligent digital modulation type identifier

Authors:
Ataollh Ebrahimzadeh;Seyed Alireza Seyedin
Affiliations:
Department of Electrical and Computer Engineering, Noshirvani Institute of Technology, Ferdowsi University of Mashad, Iran;Department of Electrical and Computer Engineering, Ferdowsi University of Mashad, Iran
Venue:
NN'06 Proceedings of the 7th WSEAS International Conference on Neural Networks
Year:
2006

Citing 4
Cited 0

Genetic algorithms + data structures = evolution programs (3rd ed.)

Genetic algorithms + data structures = evolution programs (3rd ed.)
Digital modulation classification using constellation shape

Signal Processing
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

Automatic modulation type identification is needed in many applications. Most of modulation type identification methods can only recognize a few kinds of signals. They usually require high levels of signal to noise ratio (SNR) to achieve an acceptable performance. This paper proposes a new intelligent digital modulation type identifier. This identifier uses a multilayer perceptron neural network with resilient back propagation learning algorithm as the classifier and higher order moments and cumulants (up to eighth) as the features. A validation method is used during training cycle to improve the generalization of the classifier. Genetic algorithm is utilized to finding the numbers of hidden layer nodes and selection of input features. The experiment results show that IDMTI is able to discriminate the different kinds of digital modulations with high accuracy even at very low SNR values.