Blind Modulation Recognition of Communication Signals Based on Support Vector Machines
Subject Areas : electrical and computer engineeringسعید شعرباف تبریزی 1 , مرتضی خادمی 2 , محمد مولوی کاخکی 3
1 -
2 -
3 -
Keywords:
Abstract :
Automatic modulation type classifier is a system which recognizes the modulation type of received signal automatically from some possible, pre-assumed types. Automatic modulation classification has applications such as spectrum surveillance, signal confirmation, interference identification, software radio, etc. This paper, proposes a new method for recognition of 9 famous digital and analog modulations, which no need for prior knowledge of the signal to be recognized. This system is used to separate AM, FM, DSB and SSB in Analog modulations and 2ASK, 2PSK, 2FSK, 4PAM and 16QAM in digital modulations. Support Vector Machines (SVM) is used to classify these modulations and Genetic Algorithm is used to optimize Classifier Structure. Simulation results show that proposed algorithms have a good performance in comparison with other algorithms. Computational simplicity, High training speed and High classification rate, are the advantages of proposed algorithms.
