Unlock instant, AI-driven research and patent intelligence for your innovation.

An improved method for amp detection based on machine learning

A machine learning and message passing technology, applied in digital transmission systems, forward error control, error prevention, etc., can solve problems such as differences in convergence speed and inability to guarantee convergence, reduce the number of iterations, increase convergence speed, and reduce divergence The effect of probability

Active Publication Date: 2022-03-11
SOUTH CENTRAL UNIVERSITY FOR NATIONALITIES
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that the above-mentioned AMP detection cannot guarantee convergence in all scenarios; and in scenarios where better convergence can be maintained, there is a large difference in convergence speed; and a machine learning-based AMP detection improvement method is provided

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
  • An improved method for amp detection based on machine learning
  • An improved method for amp detection based on machine learning
  • An improved method for amp detection based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention will be further described in conjunction with the accompanying drawings and embodiments.

[0022] A method for improving AMP detection based on machine learning, characterized in that it proceeds in the following steps:

[0023] Step A, constructing the process of AMP detection as a multi-layer messaging network such as figure 2 , and set learning parameters for some of the messages transmitted in AMP detection during the message delivery process, such as image 3 As shown, the parameters that can be used for learning include: the coefficients of the compressed matrix brought into the operation during the message passing process, the coefficients of the compressed data brought into the operation during the message passing process, the threshold coefficient of the soft threshold function and the output value of the soft threshold function coefficient. In the multi-layer message passing network built by AMP detection, the coefficients that can be ...

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 an improved method for AMP detection based on machine learning, which is carried out in the following steps: constructing the process of AMP detection iterative message delivery into a multi-layer message delivery network, and setting learning parameters for some messages during the message delivery process ; Construct the objective function or where Ξ t Indicates the set of learning parameters set in step A, R t Indicates the divergence probability, E t Indicates the estimated error when the message passing converges; using the big data of the actual application scene, the learning parameter set Ξ set in step A t Carry out training; the present invention greatly reduces the probability of divergence of the AMP detection method, and effectively improves the speed of convergence.

Description

technical field [0001] The present invention relates to a distributed message passing signal detection method, called an approximate message passing (AMP, approximate message passing) detection method, in particular to an improved method of AMP detection based on machine learning. This method belongs to the research content in the field of artificial intelligence and big data analysis. Background technique [0002] AMP detection has low computational complexity and small estimation error, and has great potential application value in the fields of compressed sensing and MIMO wireless transmission. Compressed sensing, also known as compressed sampling, is a technology that uses the sparsity of the signal to compress and reconstruct the signal. Compressed sensing is widely used in many applications in the field of electronic engineering, such as image compression, nuclear magnetic resonance, etc. Multiple-Input Multiple-Output (MIMO) technology refers to a technology that use...

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): H04L1/00H04B7/0413H04B7/0456
CPCH04L1/0048H04L1/005H04B7/0413H04B7/0456
Inventor 杨杨代光发陈少平
Owner SOUTH CENTRAL UNIVERSITY FOR NATIONALITIES