Baseband precoding MSK signal demodulation method based on deep learning under pulse noise

A deep learning and impulse noise technology, applied in the field of communication, can solve problems such as difficulty in channel model parameter estimation, and achieve the effect of avoiding complexity and effectiveness problems

Active Publication Date: 2019-08-23
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF6 Cites 15 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
  • Baseband precoding MSK signal demodulation method based on deep learning under pulse noise
  • Baseband precoding MSK signal demodulation method based on deep learning under pulse noise
  • Baseband precoding MSK signal demodulation method based on deep learning under pulse noise

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0029] In this embodiment, the parameters of the baseband precoded MSK signal are: the interval T of the information source transmitting bit information b =0.01s, every T b Number of sampling points N sample =32. The impulse noise model is the SαS model, the characteristic index α=1.5, the symmetry parameter β=0, the position parameter μ=0, and the scale parameter γ describe the strength of the impulse noise, which is used to define the signal-to-noise ratio SNR(dB)=P s / 2γ 2 , where P s is the signal power. The implementation steps are as follows:

[0030] Step 1: Preprocess the IQ two-way signal received by the receiving end, and the clipping threshold p threshold =20, every 128 sampling data is a data block.

[0031] Step 2: Construct the CLDNN demodulation network, the overall structure is as follows figure 1 shown. Under the condition of selecting impulse noise SαS(α=1.5) b / N 0 When =7dB, the preprocessed data of the received signal Q channel is used as a trai...

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 a baseband precoding MSK signal demodulation method based on deep learning under pulse noise. The demodulation method based on deep learning is designed to solve the problem that pulse noise model parameter estimation is complex when a traditional baseband precoding MSK signal is demodulated. According to the method, under the condition that a channel model is not known, a channel feature training demodulation network can be learned from transmitting and receiving data, a transmitting sequence is recovered or codingbit soft information is output at a receiving end in real time, reliable receiving is guaranteed, and meanwhile operation complexity is reduced.

Description

technical field [0001] The invention belongs to the technical field of communication, and relates to a baseband precoded MSK signal demodulation method based on deep learning under impulse noise. Background technique [0002] Minimum Shift Keying (MSK) is a modulation technique with constant envelope, continuous phase, high frequency utilization, and low out-of-band radiation power. It is widely used in military and commercial wireless communication systems. In many application scenarios, the noise at the receiver of these wireless communication systems contains strong pulse components and no longer obeys the Gaussian distribution. If the communication receiving algorithm designed for Gaussian noise is directly used, the performance of the system will be seriously degraded. Impulse noise is a typical non-Gaussian noise, and many impulsive noises faced by wireless communication can be modeled as a symmetrical α-stable (SαS) distribution. [0003] In traditional wireless comm...

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 党泽王军王希黄巍
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