An Effective Method for Classification of Digital Communication Signals

This paper presents an intelligent method for identification of modulation type in digital communication signals at different signal to noise ratios (SNRs). The method isbased on the idea of optimization of the adaptive neuro-fuzzy inference system (ANFIS) and includes three major modules:the feature extraction module, the classifier module and theoptimization module. In the feature extraction module, a novel combination of the higher order moments (up to eighth), higherorder cumulants (up to eighth) and spectral characteristics are proposed as the efficient features. The adaptive neuro-fuzzyinference system (ANFIS) is investigated as a classifier. In the training phase of ANFIS, the vector of radius has very important roles in terms of recognition accuracy. Therefore, in the optimization module, cuckoo optimization algorithm (COA) is proposed for optimization of the classifier. Experimental results clearly indicate that the proposed hybrid intelligent method has a high classification accuracy to discriminate between different types of digital signals even at very low SNRs.

Keywords:

Pattern recognition , ANFIS , cuckoo optimization algorithm (COA) , spectral characteristics