CNN cooperative spectrum sensing method and system based on covariance matrix Cholesky decomposition

Abstract

The invention relates to a CNN cooperative spectrum sensing method and system based on covariance matrix Cholesky decomposition, and the method comprises the following steps: S1, carrying out the preprocessing of an original signal, and obtaining a covariance matrix; s2, the covariance matrix obtained in the step S1 is used as an input parameter, calculation is executed according to a covariance matrix decomposition method, and each secondary user obtains a lower triangular matrix X of the secondary user; s3, taking the lower triangular matrix X obtained in the step S2 as an input parameter, executing calculation according to a statistical magnitude construction method, and obtaining statistical matrixes under different signal-to-noise ratios as training and testing data of the CNN; and S4, marking the statistical matrix obtained in the step S3, taking the marked statistical matrix as an input parameter, executing calculation according to a CNN spectrum sensing method, and inputting a test set into the trained model to obtain detection probabilities under different signal-to-noise ratios. According to the method, the characteristics of the original signal are fully extracted, the detection performance is greatly improved, and the method has a good application prospect in a cognitive radio system.

Description

technical field [0001] The invention belongs to the technical field of digital communication, and in particular relates to a method and system for collaborative spectrum sensing of a convolutional neural network (Convolutional Neural Network, CNN) based on Cholesky decomposition of a covariance matrix. Background technique [0002] Spectrum resources, as the core elements to promote the development of the communication industry, have become an indispensable and important strategic resource in the information age. In recent years, the fifth generation mobile communication (The 5 th The large bandwidth, high speed, low latency, and machine-to-machine (M2M) communication of Generation Mobile Networks (5G) technology also requires more spectrum resource support. At the same time, with the rapid development of technologies such as the Internet of Things and the Internet of Vehicles, the era of the Internet of Everything will bring geometrically increasing data. The available sp...

AI Technical Summary

Problems solved by technology

[0004] In the process of spectrum sensing, the traditional single-user, single-antenna signal detection method can no longer meet the actual needs. With the development of science and technology, statistical signal processing is developing in the direction of multi-user, multi-antenna, and intelligence, which makes array signal processing become the mainstream. research direction

Images