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

A Graph Domain Feature Extraction Method of Communication Signal Based on kl Divergence

A KL divergence, communication signal technology, applied in the field of signal processing, can solve the problems of heavy workload, complicated calculation, affecting the recognition effect, etc., and achieve the effect of excellent performance

Active Publication Date: 2020-09-18
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However at AMC G The entire graph domain feature construction in is done manually, the calculation is very cumbersome, and the workload is heavy. If the feature sequence is not properly selected, it is easy to cause a large error, which usually affects the recognition effect.

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
  • A Graph Domain Feature Extraction Method of Communication Signal Based on kl Divergence
  • A Graph Domain Feature Extraction Method of Communication Signal Based on kl Divergence
  • A Graph Domain Feature Extraction Method of Communication Signal Based on kl Divergence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0049] For the convenience of description, the relevant technical terms appearing in the specific implementation are explained first:

[0050]BPSK (binary phase-shift keying): binary phase-shift keying;

[0051] QPSK (quadrature phase-shift keying): quadrature phase-shift keying;

[0052] OQPSK (offset quadrature phase-shift keying): offset quadrature phase-shift keying;

[0053] 2FSK(binary frequency-shift keying): binary frequency shift keying;

[0054] 4FSK(quadrature frequency-shift keying): quadrature frequency-shift keying;

[0055] MSK (minimum shift keying): minimum frequency shift keying;

[0056] LB (Likelihood-based influence): based on maximum likelihood

[0057] FB (feature-based): based on features

[0058] FE (feature-extraction): feature extraction

[0059] PR (pattern recognition): pattern recognition

[0060] AMC G (graph-based automatic modulation classification): Automatic modulation classification based on graph domain;

[0061] KL divergence (Kul...

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 invention discloses a communication signal graph domain feature extraction method based on KL divergence, which uses the cyclic spectrum of the communication signal to realize the automatic construction of the feature sequence under the premise of ensuring the robustness of the algorithm; specifically, the invention firstly adopts The graph-field mapping theory converts the cyclic spectrum of the communication signal into a series of adjacency matrices, and extracts the elements in the adjacency matrix to construct a feature sequence candidate set; then, for each index in the feature sequence candidate set, according to each modulation type in The size of the element value at the index determines the main modulation type, and calculates the KL divergence of the main modulation type relative to other modulation types; finally, the characteristic sequence of each modulation type is established according to the size of the KL divergence.

Description

technical field [0001] The invention belongs to the technical field of signal processing, and more specifically relates to a communication signal graph domain feature extraction method based on KL divergence. Background technique [0002] Automatic modulation classification (AMC) can identify the modulation type of a received signal with little or no prior knowledge and is widely used in military and civilian communications. Typical automatic modulation recognition methods are usually divided into two categories: maximum likelihood based methods (ML) and feature extraction based methods (FB). The method based on maximum likelihood is a theory based on hypothesis testing. Through the likelihood function of the received signal, the likelihood ratio is compared with a threshold value to make a decision. This method can obtain the most Excellent solution, but there are also many disadvantages; the method based on feature recognition includes two stages of feature extraction (FE...

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): H04L27/00
CPCH04L27/0012
Inventor 阎啸王茜刘冠男吴孝纯张国玉
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA