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

A Blind Detection Method for Multilevel Signals Based on Discrete Full Feedback Neural Network

A neural network, multi-level technology, used in transmitter/receiver shaping networks, electrical components, multi-carrier systems, etc.

Inactive Publication Date: 2012-02-01
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Technical problem: the purpose of this invention is to provide a kind of multi-level signal blind detection method based on discrete full feedback neural network, which solves the problem of optimal solution in the complex number field under the condition of unknown signal, and provides a solution for wireless communication network, especially wireless sensor network. Sink provides an accurate blind detection method for signals

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
  • A Blind Detection Method for Multilevel Signals Based on Discrete Full Feedback Neural Network
  • A Blind Detection Method for Multilevel Signals Based on Discrete Full Feedback Neural Network
  • A Blind Detection Method for Multilevel Signals Based on Discrete Full Feedback Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Using the complex discrete multi-level activation function and using the appropriate gain coefficient a, construct the complex discrete Hopfield neural network to realize the blind detection of the multi-level multi-ary system quadrature amplitude modulation MQAM (Multi-Quadrature Amplitude Modulated) signal. The specific steps are as follows conduct:

[0036] A. The gateway Sink terminal receives the signal transmitted by a single intermediate node and performs oversampling to obtain the receiving equation of the discrete time channel at the gateway Sink terminal

[0037] x N =SΓ H

[0038] In the formula, S = [ s L + M ( k ) , . . . , s ...

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 multilevel signal blind detection method based on a discrete full feedback neural network. According to the subspace relationship between the signal received by the gateway (Sink) node of the wireless sensor network and the signal sent by the intermediate processing node, the method establishes an optimal performance function for direct blind detection of the sent signal, and transforms the blind detection problem into a quadratic programming problem. Then a discrete complex multi-level Hopfield neural network is constructed. According to the specific requirements of multi-level signal blind detection, the neuron table energy function, operating equation and gain coefficient of the complex multi-level discrete Hopfield neural network are redefined. Ping Hopfield neural network is used as a blind detection algorithm for MQAM signals in wireless sensor networks. This algorithm can achieve the calculation goal only by receiving data in a very short time, and can be applied to occasions where statistics are meaningless. The search space is reduced, the difficulty is greatly reduced, the search time is significantly better than other blind detection algorithms, and the system performance is improved accordingly.

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 multi-level signal blind detection between the intermediate processing node of the wireless sensor network and the receiving end of a gateway (Sink). Background technique [0002] Wireless sensor networks enable multiple devices to collaboratively detect stress and deformation of buildings and bridges, detect event threats, track hostile targets, support unmanned robot vehicles, etc., and have collaborative real-time detection, perception and collection of various environments Or monitor the object information and process it, and send it to the user who needs it. As a special wireless network, the wireless sensor network emphasizes the communication between devices. Because its network nodes use a small battery as a power source, they cannot be charged and replaced, so there are very strict capacity limitations. Reducing ...

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): H04L27/00H04L27/34H04L25/03
Inventor 张志涌张昀阮秀凯
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