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

Initial state vector control-based full-feedback neural network blind detection method

An initial state and neural network technology, applied in the transmitter/receiver shaping network, transmission monitoring, baseband system components, etc., can solve the problem of slow algorithm convergence speed, blind detection performance limitation, and algorithm easy to fall into a false equilibrium point and other problems to achieve the effect of improving the detection performance and speeding up the convergence speed

Active Publication Date: 2014-07-16
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The blind detection of communication signals realized by full feedback network can effectively solve the problem of blind detection of binary and multi-valued signals, but randomly setting the initial state vector of the network will make the algorithm easy to fall into a false equilibrium point, and the algorithm convergence speed is too slow, and the blind detection performance is also poor. restricted

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
  • Initial state vector control-based full-feedback neural network blind detection method
  • Initial state vector control-based full-feedback neural network blind detection method
  • Initial state vector control-based full-feedback neural network blind detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Before going into details, some nouns, symbols and formulas used in the system are first defined:

[0033] P: channel order

[0034] L: equalizer order

[0035] N: the data length required by the algorithm of this scheme

[0036] q: oversampling factor

[0037] (·) H : Hermitian transpose

[0038] (·) T :Matrix transpose

[0039] The idea of ​​the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0040] Definition 1 When the noise is neglected, the receiving equation of the discrete-time channel is defined as follows

[0041] x N =SГ H (1)

[0042] Among them, the sending signal array S=[s L+P (t),...,s L+P (t+N-1)] T =[s N (t),...,s N (t-P-L)] N×(L+P+1) ,s L+P (t)=[s(t),...,s(t-L-P)] T ; Г is derived from h jj , jj=0, 1,..., the block Toeplitz matrix composed of P, [h 0 ,...,h P ] q×(P+1) is the channel impulse response, and the received data array is (X N ) N×(L+1)q =[x L (t),......

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 an initial state vector control-based full-feedback neural network blind detection method. In a full-feedback neural network, when the method is adopted, the convergence speed of algorithm can be accelerated efficiently, the attraction domain of a pseudo equilibrium point can be avoided, and the detection performance of the algorithm can be improved to a certain extent. In the method, a new matrix is reconstructed by receiving a value space matrix obtained by resolving a singular value of a signal matrix, the row vector corresponding to the minimal index of the new matrix is calculated and used as the initial state vector, the vector of the pseudo equilibrium point is recorded during blind detection, and a set of column vectors are searched from the vectors of the new matrix to make the Euclidean distance between the base vector and the pseudo equilibrium point greater than the radius of the attraction domain of the pseudo equilibrium point, and thus, the algorithm can be converged quickly.

Description

technical field [0001] The invention relates to the field of wireless communication signal processing and the field of neural network, in particular to the field of signal blind detection of a receiving system of a wireless communication network. Background technique [0002] In recent years, the rapid development of wireless communication technology and the introduction of various communication standards / concepts have greatly increased the signal transmission rate and enhanced the time-varying characteristics of wireless transmission channels, which will inevitably put forward stricter technical requirements for blind detection technology. For example, the fast time-varying characteristics of the channel require that the blind detection algorithm needs to be able to effectively eliminate the Inter Symbol Interference (ISI) by using only a short data block; Applicability and adaptability need to be enhanced urgently; in order to reduce energy consumption and system overhead,...

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): H04L25/03H04B17/00H04L27/34
Inventor 张志涌阮秀凯张昀
Owner NANJING UNIV OF POSTS & TELECOMM
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