A method of identifying communication signal based on deep hybrid routing network

A hybrid routing and network recognition technology, which is applied in the direction of data exchange network, character and pattern recognition, biological neural network model, etc., can solve the problems of lack of in-depth recognition methods, and achieve the effect of improving classification ability, reducing the number of parameters and enhancing performance

Active Publication Date: 2021-02-02
TAISHAN UNIV
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] From the above, DLA has broad application prospects in signal recognition, but there is still a lack of deep recognition methods with good performance.

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 method of identifying communication signal based on deep hybrid routing network
  • A method of identifying communication signal based on deep hybrid routing network
  • A method of identifying communication signal based on deep hybrid routing network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] A method for identifying communication signals based on a deep hybrid routing network, the method comprising the following steps:

[0065] S1: Obtain signal data and extract corresponding signal features;

[0066] S2: Design a hybrid routing network model, which is based on the CNN neural network, adding multiple routing units, and combining each unit through a cross-layer connection network to design more than one hybrid multi-routing network model;

[0067] S3: use the signal data obtained by S1 to train the network model of S2, and select the network model of the hybrid multi-routing unit according to the training effect;

[0068] S4: Using the hybrid multi-routing network model obtained in S3 to identify the signal data, and finally output the identification result.

[0069] One-dimensional convolution in the form of CNN network is suitable for NLU, while two-dimensional convolution and three-dimensional convolution have broader applications in CV. Two-dimensional...

Embodiment 2

[0095] Example 2: Taking underwater acoustic communication signals as an example to specifically verify the effectiveness of this method

[0096] The underwater wireless communication process is mainly affected by the underwater environment. The main influencing factors are multipath in the underwater acoustic channel, Doppler effect, more time delay and additive white Gaussian noise (AWGN) . channel can be expressed as Figure 7 , the signal form at the receiving end is as follows:

[0097]

[0098] where s(t) is the transmitted signal, h(t, δ) is the channel impulse response with multipath, Doppler effect and time delay, n(t) is the AWGN, e i (t) is the attenuation of the i-th path, Indicates signal convolution, δ i (t) is the i-th path delay, I is the total number of multipath signals, and similar Doppler scaling factors are set in all paths. The transmitted signal can be an analog signal or a digital signal.

[0099] The method provided in Example 1 and the multi...

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 method for identifying a communication signal based on a deep hybrid routing network, and the method comprises the steps of obtaining signal data, and extracting a corresponding signal feature; designing a hybrid routing network model which takes a CNN neural network as a basic model, adding multiple routing units, combining all the units in a cross-layer connection network mode, and designing more than one hybrid routing network model; training a network model by utilizing the acquired signal data, and selecting the network model of the hybrid multi-routing unit according to a training effect; and identifying the signal data by using the obtained hybrid multi-routing network model, and finally outputting an identification result. The hybrid routing network structure provided by the invention provides a simple form for a complex routing logic network design, and the used network can generate a plurality of routing modes, so that the performance of extracting signal features is enhanced, and the training speed is higher.

Description

technical field [0001] The invention relates to the technical field of deep learning algorithms, in particular to a method for classifying and identifying communication signal types. Background technique [0002] With the development of wireless communication, identifying certain emission parameters at the transmitter has become a hot topic in the field of telecommunication research and has a wide range of applications. Often, the time-frequency information of a signal comes from unknown or partially known sources. Today, signal class classification has been an important part of smart radios used in military and civilian wireless communications. [0003] Signal type identification plays an important role in the military field. Modern electronic warfare (Electronic Warfare, EW) includes three main aspects: electronic support (Electronic Support, ES), electronic attack (Electronic Attack, EA) and electronic protection (Electronic Protect, EP). The goal of ES is to obtain in...

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): G06K9/00G06K9/62G06N3/04H04L12/24
CPCH04L41/044H04L41/0823H04L41/145H04L41/147G06N3/045G06F2218/08G06F2218/12G06F18/214
Inventor 王岩
Owner TAISHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap