Research of communication signal modulation scheme recognition based on one-class SVM bayesian algorithm

Authors:
Yin Zhendong
Affiliations:
School of Electronics and Information Technology, Harbin Institute of Technology, Harbin, P. R. China
Venue:
WiCOM'09 Proceedings of the 5th International Conference on Wireless communications, networking and mobile computing
Year:
2009

Citing 7
Cited 0

A general approach to the automatic classification of radiocommunication signals

Signal Processing
Automatic analogue modulation recognition

Signal Processing
Modulation recognition using artificial neural networks

Signal Processing
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
One-class svms for document classification

The Journal of Machine Learning Research
A Novel Kernel Method for Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
Estimating the Support of a High-Dimensional Distribution

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.