Research of Communication Signal Modulation Scheme Recognition Based on One-Class SVM Bayesian Algorithm

This paper proposed a digital signal modulation scheme recognition method using a novel one-class SVM based multi-class Bayesian classification algorithm. It is proven that the solution of one-class SVM using the Gaussian kernel can be normalized as an estimate of probability density, and the probability density is used to construct the two-class and multi-class Bayesian classifier. The statistical characterization parameters of the multi communication signals are extracted as the input feature vectors of the one-class SVM. Experimental result showed that the correct mod scheme classification probability of the proposed classifier is comparable to traditional multi-class SVM classifier. In the condition of SNR=5dB, the recognition probability is 98.13%. However, in the case of multi-class signal recognition and large amount of training samples of each communication signal class, the calculation amount of training and storage is only 0.5 percent of the traditional SVM classifier, which leads to less training time for the proposed classifier, and can be widely used in on-line recognition software radio system.