A Collaborative Spectrum Sensing Method Based on Covariance Eigenvalue and Mean Shift Clustering

Abstract

The invention discloses a collaborative spectrum sensing method based on covariance eigenvalues ​​and mean shift clustering. First, the covariance matrix is ​​calculated by using the received sensing data, the eigenvalues ​​of the covariance matrix are calculated, and the maximum eigenvalue and the minimum eigenvalue are used Constitute a two-dimensional signal eigenvector. Finally, the classifier is obtained by training mean-shift clustering. The invention can not only well avoid the derivation of the traditional threshold value, but also avoid the need to preprocess the covariance matrix to construct the two-dimensional signal feature vector. At the same time, the classifier obtained by training the mean shift clustering algorithm can avoid setting the number of classes and better display the hidden classes of the training set.

Description

technical field [0001] The present invention relates to the field of cognitive radio, and more particularly, to a cooperative spectrum sensing method based on covariance eigenvalue and mean shift clustering. Background technique [0002] In recent years, the number of various wireless devices and smart mobile terminals has increased rapidly, people's demand for wireless spectrum has increased, and the scale of wireless communication networks has continued to expand, which undoubtedly makes spectrum resources increasingly tight. Cognitive radio technology aims to alleviate the current shortage of spectrum. The main idea of ​​cognitive radio technology is to enable radio communication devices to discover free spectrum and make reasonable use of spectrum resources. Spectrum sensing technology is not only one of the important technologies of cognitive radio, but also the basis for other applications such as spectrum sharing and spectrum management. However, in the actual radio...

AI Technical Summary

Problems solved by technology

Some literature proposes a spectrum sensing based on random matrix theory. This algorithm still uses the judgment method of threshold judgment. Of course, there will be problems of inaccurate threshold derivation and complicated calculation.

Images