MSK signal demodulation method based on deep learning under mixed noises

A technology of deep learning and signal demodulation, which is applied in the field of communication, can solve problems such as difficult channel model parameter estimation, and achieve the effects of avoiding pulse parameter estimation, improving soft demodulation accuracy, and good bit error performance

Active Publication Date: 2019-09-13
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, using deep learning's ability to express data features, the potential channel features can be learned directly from the transmitted and received data, thereby solving the problem of difficult channel model parameter estimation in complex noise environments.

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
  • MSK signal demodulation method based on deep learning under mixed noises
  • MSK signal demodulation method based on deep learning under mixed noises
  • MSK signal demodulation method based on deep learning under mixed noises

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0026] The first step is to construct the MSK signal band-pass demodulation network.

[0027] The neural network structure proposed in this embodiment for MSK band-pass signal demodulation under the mixed noise channel is as follows figure 2 shown. The specific structure of each layer of the network is as follows:

[0028] The first layer is the input layer, and the network inputs time_step×T each time b The sampling sequence within a time period, in this embodiment, the value of time_step is 5, and the input size of the network is (5, 30).

[0029] The second layer is the LSTM layer. The output dimension of this layer is 30, and returns a sequence of size (5,30).

[0030] The third layer is the LSTM layer. The output dimension of this layer is 18, and a sequence of size (5,18) is returned.

[0031] The fourth layer is the Reshape layer, which connects the sequence of size (5,18) into a one-dimensional sequence of size 90 by row.

[0032] The fifth layer is a fully conne...

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 belongs to the technical field of communication, and relates to an MSK signal demodulation method based on deep learning under mixed noises. The invention aims at solving the problems existing in a traditional wireless communication signal receiving strategy. Under a Gaussian noise and impulse noise mixed channel, the network structure provided by the invention has good error code performance when demodulating the MSK signal, the soft demodulation accuracy is effectively improved, modeling and parameter estimation do not need to be carried out on Gaussian and pulse mixed noise, and complex pulse parameter estimation in a traditional wireless communication signal receiving strategy is avoided.

Description

technical field [0001] The invention belongs to the technical field of communication, and relates to an MSK signal demodulation method based on deep learning under mixed noise. Background technique [0002] Minimum shift keying (Minimum Shift Keying, MSK) is a continuous phase modulation, which has the characteristics of constant envelope, small out-of-band interference, and high spectrum efficiency. It can take into account both power efficiency and spectrum efficiency, and is widely used in power and bandwidth. Simultaneously limited wireless communication systems. In many application scenarios, in addition to Gaussian noise, the noise at the receiver of the wireless communication system also contains strong impulse components. If the classical signal receiving method based on Gaussian noise is directly used, only extremely poor performance can be obtained. Impulse noise is a typical non-Gaussian noise, and many impulsive noises faced by wireless communication can be mode...

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): H04L27/14G06N3/04
CPCH04L27/14G06N3/045
Inventor 王希王军党泽黄巍
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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