Complex channel equalizer design method based on complex value forward neural network

A technology of neural network and design method, applied in the field of artificial intelligence and communication, which can solve the problems of linear equalizer equalization performance degradation, etc.

Pending Publication Date: 2021-04-02
SUZHOU UNIV
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the transmission channel is nonlinear or the noise interference...

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
  • Complex channel equalizer design method based on complex value forward neural network
  • Complex channel equalizer design method based on complex value forward neural network
  • Complex channel equalizer design method based on complex value forward neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, so that those skilled in the art can better understand the present invention and implement it, but the examples given are not intended to limit the present invention.

[0040] refer to figure 1 , the present invention provides a kind of complex channel equalizer design method based on complex-valued forward neural network, adopts a kind of optional search direction training method to train complex-valued forward neural network, in complex-valued forward neural network training process, Introduce the direction factor to construct multiple search directions, use the strong Wolfe linear search strategy to determine the learning step size in the search direction, and use the breadth-first search strategy to select the appropriate search direction and learning step size as the actual search direction and learning step size, So that the value of 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 complex channel equalizer design method based on a complex value forward neural network, and relates to the field of artificial intelligence and communication. The complex channel equalizer design method based on the complex value forward neural network comprises the steps: employing a selectable search direction training method to train the complex value forward neural network, and enabling a target function value to be reduced as much as possible after each time of training, wherein the trained complex value forward neural network serves as a channel equalizer and is used in a digital communication system. The complex channel equalizer design method based on the complex value forward neural network has the beneficial effects that in the training process, a groupof direction factors are introduced to construct a plurality of search directions, the optimal training direction is selected from the search directions by adopting a breadth-first search strategy, and the optimal search direction is selected from the search directions. The high-efficiency training of the complex number forward neural network is completed, so that the design of the complex channel equalizer is realized, and excellent performance is obtained.

Description

technical field [0001] The invention relates to the fields of artificial intelligence and communication, in particular to a method for designing a complex channel equalizer based on a complex-valued forward neural network. Background technique [0002] With the rapid development of Internet technology, people's requirements for digital communication technology and digital communication quality are constantly improving, and efficient data transmission has become an important research hotspot. However, in the process of signal transmission, there are situations such as channel delay and multipath propagation, which inevitably lead to the degradation of communication quality. Therefore, when a signal passes through a wireless channel, the received signals will overlap each other, resulting in intersymbol interference. In addition, some other factors such as thermal noise, impulse noise and the nature of the channel itself will further lead to the degradation of communication q...

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): G06N3/02G06N3/08
CPCG06N3/02G06N3/08
Inventor 黄鹤董忠蓥
Owner SUZHOU UNIV
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