Classification of communications signals using an advanced technique

Because of rapid growing of radio communication technology of late years, importance of automatic classification of digital signal type is rising increasingly. This paper presents an advanced technique that identifies a variety of digital signal types. This method is a hybrid heuristic formed by a radial basis function neural networks (as a classifier) and particle swarm optimization technique. A suitable combination of higher order statistics up to eighth are proposed as the prominent characteristics of the considered signals. In conjunction with neural network we have used a cross-validation technique to improve the generalization ability. Experimental results indicate that the proposed technique has high percentage of correct classification to discriminate different types of digital signal even at low SNRs.