A New Signal Type Classifier for Fading Environments

Abstract

Automatic classification of digital signal types is extremely important in communication intelligence. In this paper we present a highly efficient digital signal type classifier for fading environments. In the proposed method, an equalizer is used to reduce the channel effects. Selected combination of the fourth, the sixth and the eighth order of moments and cumulants of the received signal are introduced as the features for representation of digital signal. A novel multiclass classifier based on support vector machines determines types of the received signals. Simulation results show that the proposed method has a high success rate for recognition of different digital signal types even at low signal to noise ratio (SNR).