Hysteretic all feedback neural network-based signal blind detection method

A neural network, total feedback technology, applied in the field of signal blind detection based on hysteresis total feedback neural network, can solve the problems of lack of flexibility, algorithm falling into local optimum, etc.

Inactive Publication Date: 2013-06-12
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the activation functions used in these literature algorithms are f...

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
  • Hysteretic all feedback neural network-based signal blind detection method
  • Hysteretic all feedback neural network-based signal blind detection method
  • Hysteretic all feedback neural network-based signal blind detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] Below in conjunction with accompanying drawing, a kind of signal blind detection method based on hysteresis full feedback neural network that the present invention proposes is described in detail:

[0047] A blind signal detection method based on hysteresis full feedback neural network, its implementation process is as follows:

[0048] When ignoring noise, the receiver equation for a discrete-time channel is defined as

[0049] x N =SΓ T (1)

[0050] In the formula, X N is the received data array, S is the transmitted signal array, Γ is the channel impulse response h jj composed of blocks

[0051] Toeplitz matrix; ( ) T Represents matrix transposition;

[0052] Among them, the sending signal array:

[0053] S=[sL+M (k),...,s L+M (k+N-1)] T =[s N (k),...,s N (k-M-L)] N×(L+M+1) ,

[0054] M is the channel order, L is the equalizer order, and N is the required data length;

[0055] the s L+M (k)=[s(k),…,s(k-L-M)] T ; Among them, s∈{±1}, time k is a nat...

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 provides a hysteretic all feedback neural network-based signal blind detection method. According to the method, hysteresis activation functions used by two sequential cycles just form a hysteresis loop, so that not only the stability of a network is guaranteed, but also the network shows better flexibility; the domain of attraction of a pseudo equilibrium point is effectively avoided by using the method in the all feedback neural network, so that the blind detection performance is improved; and in a synchronous updating mode or an asynchronous updating mode, the error code performance of the hysteretic all feedback neural network-based signal blind detection method is superior to that of the conventional Hopfield signal blind detection algorithm.

Description

technical field [0001] The invention belongs to the field of wireless communication technology and neural network technology, and in particular relates to a signal blind detection method based on hysteresis full-feedback neural network. Background technique [0002] With the rapid development of high-speed data communication and wireless sensor network technology, higher requirements are put forward for the blind detection of communication signals. The so-called blind detection can detect the transmitted signal only by using the received signal itself, thereby eliminating inter-symbol interference (ISI) to improve the information transmission rate and reliability. [0003] In order to solve the problems caused by various intelligent algorithms such as genetics, ant colony, immunity, and particle swarms, which are easy to fall into local minima and have slow convergence speed, many literatures have begun to use full-feedback neural networks to study the problem of blind signa...

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): H04L1/00H04L25/03
Inventor 于舒娟张昀冯迪
Owner NANJING UNIV OF POSTS & TELECOMM
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