Machine-learning-based spectrum sensing method and apparatus

Abstract

The invention discloses a machine-learning-based spectrum sensing method. An RMET feature of a training signal is extracted; a feature vector is determined based on the RMET feature and a classifier is determined according to a K-medoids algorithm and the feature vector; a testing signal is obtained at a current channel and a testing RMET feature of the testing signal is extracted; and the testing RMET feature is classified by using the classifier and a detection probability is calculated based on the classification result. According to the method disclosed by the invention, the RMET is used as the feature; the K-medoids algorithm is used for classification; the classifier is trained; data of the testing signal are inputted into the classifier to carry out classification and the classification result is obtained. On the basis of combination of the RMET and the K-medoids, whether a channel is available is sensed, so that the accuracy of detection is improved.

Description

technical field [0001] The present invention relates to the field of radio technology, and more specifically, to a machine learning-based spectrum sensing method and device. Background technique [0002] With the progress and development of radio technology, all walks of life have more and more demands on radio frequencies, and the problem of scarcity of spectrum resources is becoming more and more serious. At present, the spectrum resource adopts the management mode of national unified allocation and authorization, and the spectrum is divided into two types: authorized frequency band and unlicensed frequency band. Among them, licensed frequency bands occupy most of the spectrum resources, such as TV broadcasting frequency bands, but many licensed frequency bands are idle; unlicensed frequency bands open to use account for a small part of the entire spectrum resources, such as wireless local area networks, wireless metropolitan area networks and other wireless networks. Mos...

AI Technical Summary

Problems solved by technology

At present, the more classic spectrum detection methods include energy detection algorithm. However, in the energy detection algorithm, because the decision threshold is difficult to determine, it is easy to be affected by noise uncertainty in a low signal-to-noise ratio environment and cause misjudgment, which leads to a sharp drop in detection performance. Even with an adaptive threshold, the detector cannot make a correct judgment, so the detection result of the spectrum is not accurate enough

Images