Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

VHF/UHF frequency band radio signal modulation mode identification method based on deep neural network

A deep neural network and modulation method recognition technology, applied in the field of modulation method recognition based on deep neural network, can solve the problems of low recognition accuracy, single type of recognition signal, inability to complete radio signal recognition tasks, etc. The effect of low accuracy and wide recognition signal category

Active Publication Date: 2020-02-21
DALIAN UNIV OF TECH +2
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the shortcomings of the existing modulation recognition method, which recognizes single types of signals, low recognition accuracy, and cannot complete common radio signal recognition tasks in VHF / UHF frequency bands, the present invention provides a new modulation method recognition method based on a deep neural network

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
  • VHF/UHF frequency band radio signal modulation mode identification method based on deep neural network
  • VHF/UHF frequency band radio signal modulation mode identification method based on deep neural network
  • VHF/UHF frequency band radio signal modulation mode identification method based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The specific implementation manners of the present invention will be further described below in conjunction with the accompanying drawings and technical solutions.

[0017] A new method for identifying modulation modes based on deep neural networks, the main steps of which are as follows:

[0018] The first step is signal feature extraction. Feature extraction is performed on the radio signal s collected by the receiver. A total of 26 features were extracted from three categories: instantaneous parameters, high-order statistics, and transform domains, as shown below.

[0019] (1) Features 1 to 7 are related features of instantaneous amplitude, frequency and phase.

[0020] The instantaneous amplitude is defined as: A(i)=|s(i)|, where |·| is a modulo operation.

[0021] The instantaneous unwinding phase is defined as: arg[·] represents the operation of finding the main value of the argument, and unwrap[·] represents the unwrapping operation.

[0022] The instantane...

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 VHF / UHF frequency band radio signal modulation mode identification method based on a deep neural network, and belongs to the technical field of communication. According to the method, on the basis of a deep learning theory, a three-layer neural network is selected as a signal classifier, three categories of 26 signal characteristics are taken as classifier input vectors,and 14-dimensional vectors are output to respectively correspond to 14 common radio signals in a VHF / UHF frequency band. A neural network uses ReLU as an activation function of neurons, and the outputlayer uses a Softmax function to calculate the probability that input signals belong to various types. In classifier training, an Adam optimization method is used to realize network parameter updating, a cross entropy is used as a cost function to calculate an error of a network, and a dropout skill is used to improve identification accuracy of the network. According to the method, common radio signals of the VHF / UHF frequency band can be accurately identified, and the identification signals are wide in category, large in quantity and high in accuracy; and the recognition algorithm is low incomplexity, short in time consumption and good in real-time performance.

Description

technical field [0001] The invention belongs to the technical field of communication, and relates to a new modulation mode identification method based on a deep neural network. The method can accurately identify 14 common radio signals in the VHF / UHF frequency band, including civil aviation AM, wideband FM (WFM), narrowband FM (NFM), 2FSK, 4FSK, GSM, OFDM, Pi / 4DQPSK, MPSK (2 / 4 / 8), MQAM (16 / 32 / 64). Background technique [0002] Modulation identification, also known as modulation classification or modulation discrimination, is an important step between signal detection and signal demodulation at the receiving end of a communication system. Its main task is to judge the modulation mode of the signal by analyzing and processing the received signal without prior knowledge or insufficient prior knowledge, and provide a basis for subsequent signal analysis and processing. [0003] The modulation method of the radio signal is one of its important characteristics. The determination...

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
IPC IPC(8): G06K9/00G06K9/62G06N3/04
CPCG06N3/045G06F2218/12G06F18/214
Inventor 谢欣戴江安唱亮孙浩邱天爽陈兴丑远婷高宏杰
Owner DALIAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com