Unlock instant, AI-driven research and patent intelligence for your innovation.

Modulation recognition method, system, readable storage medium and device

A modulation identification and modulation method technology, applied in the field of communication, can solve the problem of uneven modulation identification classification, reduce the overhead of repeated training, optimize the recognition rate, and improve the training efficiency.

Active Publication Date: 2021-12-24
EAST CHINA JIAOTONG UNIVERSITY
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Based on this, the purpose of the present invention is to provide a modulation identification method, system, readable storage medium and equipment to solve the technical problem of the existing modulation identification classification inhomogeneity

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Modulation recognition method, system, readable storage medium and device
  • Modulation recognition method, system, readable storage medium and device
  • Modulation recognition method, system, readable storage medium and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] see figure 1 , shows the modulation identification method in the first embodiment of the present invention, the modulation identification method can be implemented by software and / or hardware, and the method includes step S01-step S05.

[0050] Step S01, acquiring a data set of a received signal, where the received signal carries characteristic parameters used to characterize the modulation mode.

[0051] Among them, the received signal data set contains N received signals, and the N received signals contain M kinds of modulation methods, M ≤ N . In addition, the characteristic parameters carried by the received signal may be, but not limited to, electromagnetic characteristics, frequency spectrum characteristics, statistical characteristics and the like.

[0052] Step S02, perform cluster analysis on the received signal data according to the characteristic parameters carried by the received signal, and divide the modulated signals whose discrimination degree is grea...

Embodiment 2

[0064] see figure 2 , shows the modulation identification method in the second embodiment of the present invention, the modulation identification method can be implemented by software and / or hardware, and the method includes step S11-step S17.

[0065] Step S11, acquiring a data set of a received signal, the received signal carrying characteristic parameters used to characterize the modulation mode.

[0066] Step S12, using an unsupervised sparse autoencoder to perform dimensionality reduction processing on the received signal in the received signal data set.

[0067] Among them, the sparse autoencoder is an artificial neural network that obtains deep feature representations of input data through unsupervised learning. The constraint condition of the self-encoder network is that the input is a data sample, and the output is constantly close to the input of the network. According to this principle, the neural network is continuously trained. After the loss function of the net...

Embodiment 3

[0119] Another aspect of the present invention also provides a modulation identification system, please refer to Figure 8 , shows the modulation recognition system in the third embodiment of the present invention, the system includes:

[0120] A data acquisition module 11, configured to acquire a data set of a received signal, the received signal carrying characteristic parameters for characterizing the modulation mode;

[0121] The cluster analysis module 12 is configured to perform cluster analysis on the received signal data according to the characteristic parameters carried by the received signal, and divide the modulated signals with a degree of discrimination greater than a preset value, and divide the modulated signals with a degree of discrimination smaller than the preset value. The modulated signals are aggregated into a cluster;

[0122] The result judging module 13 is used to judge whether two or more modulation signals are included in the obtained cluster;

[0...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention provides a modulation identification method, system, readable storage medium and equipment. The method includes: acquiring a received signal data set; performing cluster analysis on the received signal according to the characteristic parameters carried by the received signal, so as to divide the received signal data set into Multiple clusters; when all received signals in a cluster contain more than two modulation methods, supervised identification of received signals in a cluster is performed using a supervised learning method based on a convolutional neural network. In the present invention, through the cluster analysis of unsupervised learning, some modulation modes with obvious distinguishing features can be directly identified, and the other modulation modes that are easily confused with each other will be classified into the same cluster because of their high similarity. Clusters containing two or more modulation types are further supervised and recognized by using convolutional neural network-based supervised learning, so that the classification inhomogeneity problem existing in existing modulation recognition methods can be solved.

Description

technical field [0001] The present invention relates to the field of communication technology, in particular to a modulation identification method, system, readable storage medium and equipment. Background technique [0002] Automatic Modulation Classification (AMC for short) refers to the technology of determining the modulation mode of an unknown signal by analyzing the electromagnetic characteristics, spectrum characteristics, and statistical characteristics of the transmitted signal. In the field of military communications, by identifying the modulation mode of the intercepted signal, estimating the modulation parameters, demodulating the signal, analyzing and processing the information, and applying radio interference or electromagnetic interference to the signal more targetedly, the wireless communication of the other party is affected. hinder or even paralyze. In the field of civil communications, modulation recognition technology provides important prior information...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04L27/00G06N3/08G06N3/04G06K9/62G06K9/00
CPCH04L27/0012G06N3/08G06N3/045G06F2218/12G06F2218/08G06F18/23G06F18/241
Inventor 赵军辉秦子杰马小婷
Owner EAST CHINA JIAOTONG UNIVERSITY