Intelligent detection and recognition method of Morse messages based on deep learning

A recognition method and deep learning technology, applied in the field of message recognition of Morse signals, can solve problems such as large channel influence and poor recognition effect, so as to save labor, reduce labor intensity and damage to the body, and avoid mistakes Effect

Active Publication Date: 2019-07-12
PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above problems, the present invention proposes a method for intelligent detection and recognition of Morse messages based on deep learning, which solves the problem that the current Morse message automatic recognition te

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
  • Intelligent detection and recognition method of Morse messages based on deep learning
  • Intelligent detection and recognition method of Morse messages based on deep learning
  • Intelligent detection and recognition method of Morse messages based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] Such as figure 1 As shown, a method for intelligent detection and recognition of Morse messages based on deep learning includes the following steps:

[0038] Step S11: Perform time-frequency analysis and clustering calculation of the decision threshold on the received Morse signal, and detect signal energy through the decision threshold, thereby identifying the position of the Morse code word interval;

[0039] Step S12: Using the neural network to identify the Morse signal corresponding to the Morse code word between the two intervals segment by segment.

[0040] Specifically, the step S11 includes:

[0041] Step S111: Shift the frequency of the received Morse signal to zero intermediate frequency, and perform low-pass filtering;

[0042] Step S112: Set the frame length, perform time-frequency analysis and clustering calculation of the judgment threshold for each frame of Morse signal, detect the energy of each frame of Morse signal through the judgment threshold, lo...

Embodiment 2

[0057] In this embodiment, for the Morse wireless signal transmitted in the short wave mode, the quality of the signal to be processed is required to reach a level that can be clearly distinguished by the human ear, and the code rate is between 50 yards / minute and 140 yards / minute. In this embodiment, it is considered that the processing system (such as a communication terminal, radio monitoring equipment) has completed signal reception and sampling (the sampling rate is much higher than the signal code rate), and it is considered that the current received data only contains a single Morse signal.

[0058] Such as figure 2 As shown, another intelligent detection and recognition method for Morse messages based on deep learning includes two major processes of codeword interval recognition (step S21) and codeword content recognition (step S22):

[0059] Step S21: The processing system first filters the frequency of the received signal; performs energy detection (level detection)...

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 relates to the technical field of message identification of Morse signals in various communication systems. The invention discloses an intelligent detection and recognition method of Morse messages based on deep learning, and the method comprises the steps: carrying out the time-frequency analysis and clustering of a received Morse signal, calculating a judgment threshold, detectingthe energy of a signal through the judgment threshold, and recognizing the position of a Morse code word interval; and identifying the Morse code words corresponding to the Morse signals between the two intervals section by section by using a neural network. According to the invention, the problems that the current Morse message automatic recognition technology has poor recognition effects on manual shot Morse messages and is greatly affected by channel are solved, and the method has relatively high automatic identification speed and accuracy of the Morse code.

Description

technical field [0001] The invention relates to the technical field of message recognition of Morse signals in various communication systems, and in particular to an intelligent detection and recognition method for Morse messages based on deep learning. Background technique [0002] Various advanced communication methods are flourishing today, but in military communication, short-wave Morse communication is still widely used due to its particularity, and it is an indispensable communication method. In 1837, Samuel Finley BreeseMorse got inspiration from the phenomenon of sparks appearing when the current suddenly cut off, and designed a simple signal composed of electrical pulse signals of different lengths, which later developed into a signal composed of "dot" and "dash". and intervals in Morse code. According to international standards, punctuation marks, Arabic numerals and English letters are represented by a specific combination of "dot", "dash" and interval, and can a...

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): H04L15/24G06N3/04
CPCH04L15/24G06N3/045
Inventor 王成王鼎崔以博杨宾唐涛吴瑛尹洁昕张莉吴志东
Owner PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
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