Signal identification method based on extraction of signal power spectrum fitting characteristic

Abstract

The invention discloses a signal identification method based on extraction of signal power spectrum fitting characteristic, and belongs to the field of the wireless communication. The signal identification method comprises the following steps: firstly dividing power spectrum data into a training set and a testing set, intercepting data sample fragments with equal length from the power spectrums corresponding to service class signals of different types in the training set; performing polynomial fitting on one data sample fragment A by using the least square linear regression algorithm to construct a cost function J, and minimizing the cost function J to acquire a parameter of the fitting polynomial; respectively selecting different polynomial orders, repeating w times of polynomial fittingand extracting the highest order item parameter, and acquiring all elements in a characteristic vector of the data sample fragment A; repeating the above steps to obtain a characteristic vector set Fof the service class signal, thereby constructing a training set matrix; and finally constructing a multi-layer neural network classifier model, searching an optimal solution by adopting a self-adaptive moment estimation algorithm, and identifying and classifying power spectrum signals in the testing set. Through the signal identification method disclosed by the invention, the characteristic extraction is simple and efficient, the signal identification rate is high, and the computing complexity is reduced.

Description

technical field [0001] The invention belongs to the field of wireless communication, in particular to a signal recognition method based on feature extraction of signal power spectrum fitting. Background technique [0002] Signal identification is a research hotspot in the field of wireless communication today; with the rapid development of the Internet of Things and mobile communication, the access of massive devices has led to the electromagnetic signals in the air containing more and more radio services, which have great impact on spectrum monitoring, interference coordination and radio Management presents new challenges. [0003] At present, signal recognition mainly includes two methods based on likelihood ratio and feature. In the likelihood ratio-based method, the likelihood function of the received signal is first calculated to generate a likelihood ratio, which is compared with a predefined decision threshold to achieve the theoretically optimal Bayesian detection p...

AI Technical Summary

Problems solved by technology

[0007] The present invention aims at the problem of complex expert features that appear when classifying multiple signals in existing signal recognition, resulting in low recognition efficiency. In order to improve the accurate recognition of different signals, a feature extraction method based on signal power spectrum fitting is proposed. The signal recognition method, uniformly mark the signal to improve the efficiency of recognition

Images