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

Modulation Recognition Method of Underwater Acoustic Communication Signal Based on Feature Selection and Support Vector Machine

A support vector machine and underwater acoustic communication technology, applied in the field of signal processing, can solve problems such as poor recognition effect, achieve the effect of reducing information redundancy, reducing data dimension, and improving efficiency

Active Publication Date: 2021-11-30
OCEAN UNIV OF CHINA
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But when the dimensionality of the input features is low, the recognition effect is not good

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 of Underwater Acoustic Communication Signal Based on Feature Selection and Support Vector Machine
  • Modulation Recognition Method of Underwater Acoustic Communication Signal Based on Feature Selection and Support Vector Machine
  • Modulation Recognition Method of Underwater Acoustic Communication Signal Based on Feature Selection and Support Vector Machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings.

[0021] The present invention proposes an underwater acoustic communication signal modulation recognition method based on sensitive feature selection and support vector machine, referring to figure 1 , the method mainly includes two stages: sensitive feature selection and support vector machine recognition. Among them, the sensitive feature selection part is based on extracting 18 features such as instantaneous features, high-order cumulants, and power spectrum features of the underwater acoustic communication signal, and uses the entropy weight method to assign different weights to each feature to select sensitive features. The greater the weight corresponding to the feature, the greater the role in subsequent modulation recognition, and these features with greater weight are regarded as sensitive features. The recognition part of the support...

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 an underwater acoustic communication signal modulation recognition method based on feature selection and support vector machine. Including: for the simulated or actually acquired underwater acoustic communication data samples, extract the instantaneous features, high-order cumulants, and power spectrum features of each sample to form series features; use the entropy weight method to calculate the weight coefficient of series features, and set the weight coefficient to be greater than The corresponding features of the preset weight threshold are regarded as sensitive features; the sensitive features of each sample are used as sample data, the underwater acoustic data samples of the same modulation mode are marked with the same label, and the underwater acoustic data samples of different modulation modes are marked with different labels to form training; The training set is used as the input of the support vector machine, the Gaussian kernel function is used, and the multi-classification cross entropy function is used as the objective function for training, and the recognition model based on the support vector machine is obtained; the trained recognition model is used to analyze the feature extraction of the underwater sound The communication data is modulated and identified. The method has the advantages of high efficiency and accurate identification.

Description

technical field [0001] The invention relates to the field of signal processing, in particular to a modulation recognition method for underwater acoustic communication. Background technique [0002] With the development and application of machine learning technology, the research on modulation recognition methods has gradually become a hot spot in the field of underwater acoustic communication. Among them, the modulation recognition method based on feature extraction is one of the important research directions. [0003] Generally speaking, the modulation recognition method based on feature extraction is divided into two parts: feature extraction and classifier. However, the underwater acoustic channel is a time-frequency-space variable parameter channel with strong multi-path, Doppler spread and multi-transmission attenuation. These characteristics of the underwater acoustic channel lead to serious distortion of the underwater acoustic communication signal at the receiving e...

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): H04L27/00H04B13/02H04B11/00G06K9/00G06K9/62
CPCH04L27/0012H04B13/02H04B11/00G06F2218/00G06F2218/08G06F18/2411
Inventor 吕曜辉刘炜琪李兴顺殷昊
Owner OCEAN UNIV OF CHINA