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

Coordinate Transformation Normal Modal Blind Equalization Method Based on Gated Recurrent Unit Neural Network

A neural network and cyclic unit technology, applied to the shaping network, baseband system, electrical components and other directions in the transmitter/receiver, can solve the problems of phase deflection, etc., and achieve the goal of correcting the phase deflection, improving the perception ability, and improving work efficiency. Effect

Active Publication Date: 2021-03-30
NANJING UNIV OF INFORMATION SCI & TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Using GRUNN's blind equalization method, the convergence speed is fast, and the ability to track channel changes is strong, but there are still defects of phase deflection

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
  • Coordinate Transformation Normal Modal Blind Equalization Method Based on Gated Recurrent Unit Neural Network
  • Coordinate Transformation Normal Modal Blind Equalization Method Based on Gated Recurrent Unit Neural Network
  • Coordinate Transformation Normal Modal Blind Equalization Method Based on Gated Recurrent Unit Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The technical solutions and beneficial effects of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0028] Such as figure 1 As shown, the present invention provides a coordinate transformation normal mode blind equalization method based on the gated recurrent unit neural network, including the gated recurrent unit neural network and the coordinate transformation method. After the signal is added to the noise through the channel, it is input into the gated recurrent unit neural network , the network weight vector is updated iteratively through the coordinate transformation method, and the network output is judged by the decision device as the output of the equalizer.

[0029] The method comprises the steps of:

[0030] Step 1, after the input signal y(k) passes through the channel h(k), the output sequence s(k) of the channel is obtained, and Gaussian white noise n(k) is added to the output sequence s(k), and the ob...

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 coordinate transformation norm blind equalization method based on a neural network of a gated circulation unit. The method comprises: step one, inputting a signal y(k) and enabling the signal to pass through a channel h(k) to obtain an output sequence s(k) of the channel, adding a Gaussian white noise n(k) into the output sequence s(k) to obtain a sequence x(k) as the input of a gated circulation unit neural network; and step two, updating a gated weight vector of the gated circulation unit neural network by using a coordinate transformation method and carrying out blind equalization calculation on the input sequence x(k) by using the updated neural network as an equalizer to obtain an output signal sequence X~(k). With the method disclosed by the invention, the bit error rate of a receiving terminal of a communication system is reduced effectively. The coordinate transformation norm blind equalization method is one for different harsh environments.

Description

technical field [0001] The invention belongs to the technical field of blind equalization, in particular to a coordinate transformation normal mode blind equalization method based on a gated recurrent unit neural network. Background technique [0002] In modern digital communication technology, inter-symbol interference (ISI, Inter-Symbol Interference) caused by channel multipath effect and environmental noise leads to a high bit error rate in the decision device of the communication system, which reduces the communication quality. An effective method to suppress intersymbol interference is the blind equalization technique without training sequence. The essence of blind equalization technology is to adjust the equalizer parameters in real time through a method with excellent performance to reduce the bit error rate of the communication system. [0003] In the traditional neural network structure, the adjacent layers are fully connected, but the units in each layer are not c...

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 Patents(China)
IPC IPC(8): H04L25/03H04L27/00
CPCH04L25/03089H04L25/03165H04L27/0012
Inventor 郭业才魏海文施钰鲲
Owner NANJING UNIV OF INFORMATION SCI & 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