Second-order Statistical Approach for Digital modulation Scheme Classification in Cognitive Radio using Support Vector Machine and k-Nearest Neighbor Classifier

Abstract

Cognitive radio systems require detection of differ ent signals for communication. In this study, an ap proach for multiclass signal classification based on second-or der statistical feature is proposed. The proposed s ystem is designed to recognize three different digital modul ation schemes such as PAM, 32QAM and 64QAM. The signal classification is achieved by extracting the 2nd or der cumulants of the real and imaginary part of the complex envelope. These second-order statistical features a re given to multiclass Support Vector Machine (SVM) and KNearest Neighbor (KNN) classifier for classificatio n. The modulated signals are passed through an Additive White Gaussian Noise (AWGN) channel before feature extraction. The performance evaluation of the syste m is carried using 400 generated signals. Experimental r esults show that the proposed method produces an accurate classification rate in the range 65%-89% for SVM classifier and 65-68% for KNN classifier.