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

Communication signal graph domain feature iterative extraction method based on KL divergence

A KL divergence and communication signal technology, applied in the field of signal processing, can solve the problems of heavy workload, cumbersome calculation, and affecting the recognition effect

Active Publication Date: 2018-06-22
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
  • Communication signal graph domain feature iterative extraction method based on KL divergence
  • Communication signal graph domain feature iterative extraction method based on KL divergence
  • Communication signal graph domain feature iterative extraction method based on KL divergence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0056] For the convenience of description, the relevant technical terms appearing in the specific implementation are explained first:

[0057] BPSK (binary phase-shift keying): binary phase-shift keying;

[0058] QPSK (quadrature phase-shift keying): quadrature phase-shift keying;

[0059] OQPSK (offset quadrature phase-shift keying): offset quadrature phase-shift keying;

[0060] 2FSK(binary frequency-shift keying): binary frequency shift keying;

[0061] 4FSK(quadrature frequency-shift keying): quadrature frequency-shift keying;

[0062] MSK (minimum shift keying): minimum frequency shift keying;

[0063] LB (Likelihood-based influence): based on maximum likelihood

[0064] FB (feature-based): based on features

[0065] FE (feature-extraction): feature extraction

[0066] PR (pattern recognition): pattern recognition

[0067] AMC G (graph-based automatic modulation classification): Automatic modulation classification based on graph domain;

[0068] KL divergence (Ku...

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 iterative extraction method based on KL divergence. Through a cyclic spectrum of a communication signal, a feature sequence is automatically constructed on the premise of ensuring the robustness of an algorithm. In particular, the method comprises the following steps: firstly, converting a cyclic spectrum of a communication signalinto a series of adjacent matrixes through a graph domain mapping theory, and extracting all elements in the adjacent matrixes to construct a feature sequence alternative set; secondly, calculating and adding the KL divergence of each index in the feature sequence alternative set relative to other modulation types for each modulation type to obtain KL divergence belongs to the modulation types, and determining the sequence of feature extraction according to the KL divergence of each modulation type; and lastly, selecting an index with the maximum KL divergence as the feature of a corresponding modulation type, and deleting one feature from the feature sequence alternative set once the feature is extracted until the feature sequences of all the modulation types are constructed.

Description

technical field [0001] The invention belongs to the technical field of signal processing, and more specifically relates to a method for iteratively extracting communication signal graph domain features 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 featu...

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 Applications(China)
IPC IPC(8): H04L27/00
CPCH04L27/0012
Inventor 阎啸王茜张国玉吴孝纯刘冠男
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA