Compressed sensing signal reconstruction method and system based on dictionary double learning

Abstract

The invention discloses a compressed sensing signal reconstruction method and system based on dictionary double learning. The method comprises the following steps: obtaining a reconstructed signal sample according to a received signal and a finite equidistant principle-based observation matrix optimized via feature decomposition; performing signal processing on the reconstructed signal sample to obtain a compressed sample; carrying out signal reconstruction on the compressed sample according to a sparse dictionary through a preset robustness dictionary learning model to obtain a reconstructedsignal. The invention provides an unknown narrowband signal compressed sensing signal receiving method based on observation sparse double learning, and the method has objective robustness, adaptivityand cognitive ability at the same time.

Description

technical field [0001] The invention relates to the technical field of communication. More specifically, it relates to a method and system for reconstructing compressed sensing signals based on dictionary dual learning. Background technique [0002] With the ever-changing and rapid development of the communication field, the signal acquisition technology of non-partners (that is, third parties) in the communication network in the unknown electromagnetic environment is facing increasingly severe challenges: the number of unknown radiation sources is increasing, the signal density is increasing, and the signal The types continue to diversify, and the signal spectrum continues to expand to higher and lower frequency domains. These factors make it difficult for a third-party receiver to receive and process multiple unknown target signals with a large receiving bandwidth in an unknown electromagnetic environment. With the introduction of Compressed Sensing (CS), a brand-new inf...

AI Technical Summary

Problems solved by technology

[0003] However, there are still two main problems in the application of the CS receiving method by the third party in communication: on the one hand, the CS theoretical framework itself is very sensitive to noise

At this time, the performance of the signal compression observation and reconstruction process will be greatly deteriorated, resulting in a lower signal-to-noise ratio (SNR) of the signal obtained in the noisy environment than the traditional receiving method

The lower signal quality hinders the subsequent signal processing and greatly reduces the actual reception effect of the CS method

On the other hand, the unknown signal scenario faced by the third party poses certain challenges to the CS reception method

Images