Proportional affine projection method based on minimum error entropy

An affine projection and proportional technology, applied in baseband system components, speech analysis, instruments, etc., can solve problems such as slow convergence speed

Inactive Publication Date: 2019-05-17
SHENYANG POLYTECHNIC UNIV
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this PMEE algorithm based on the gradient descent method has the disadvantage of slow convergence speed when dealing with highly correlated 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
  • Proportional affine projection method based on minimum error entropy
  • Proportional affine projection method based on minimum error entropy
  • Proportional affine projection method based on minimum error entropy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] 1. Proportional minimum error entropy algorithm

[0061] 1.1 Minimum error entropy criterion

[0062] The Shannon entropy of a random variable X is defined as:

[0063]

[0064] where N represents the number of data, P k Represents the probability of the kth data. The α-order Renyi entropy derived from Shannon entropy can be expressed as:

[0065]

[0066]

[0067] When α=2, H 2 (X) is the Renyi quadratic entropy of the random variable X. V α (X) is the α-order information potential energy. But in general, it is usually impossible to get an accurate probability density function, so the estimated value of the probability density obtained by using the Parzen window method is:

[0068]

[0069] where K σ is the kernel function, and σ is the width of the kernel function. In practical applications, the choice of kernel function will also vary according to the actual situation. Generally, the commonly used kernel functions include polynomial kernel funct...

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 relates to a proportional affine projection algorithm based on a minimum error entropy. The invention discloses a novel algorithm MEE-MPAPA-Newton which is based on a Newton method framework and introduces an affine projection method into a PMEE algorithm. Such novel algorithm can better solve a problem of sparse system identification in non-Gaussian noise when a strongly correlatedsignal is input. The method, on the basis of a proportionality coefficient, a minimum error entropy criterion and a Newton method, discloses an affine projection adaptive filtering algorithm for solving the problem of sparse system identification in a non-Gaussian noise environment when the strongly correlated signal is input.

Description

technical field [0001] The invention provides a proportional affine projection method based on minimum error entropy. Background technique [0002] Sparse systems and non-Gaussian noise, these two phenomena that commonly exist in nature have a serious impact on engineering applications, such as acoustic echo cancellation. In order to solve these two problems, many adaptive filtering algorithms based on non-second-order statistics, such as the proportional minimum error entropy algorithm (PMEE), have been proposed, and are widely used in sparse systems with non-Gaussian noise. The PMEE algorithm solves the problem of non-Gaussian noise through constraints based on Renyi entropy, and at the same time introduces a proportional coefficient matrix to ensure that the algorithm can work more effectively in sparse systems. However, this PMEE algorithm based on the gradient descent method has the disadvantage of slow convergence speed when dealing with signals with strong correlatio...

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 Applications(China)
IPC IPC(8): G10L21/0208G10L21/0216H04L25/02
Inventor 郭莹侯威翰
Owner SHENYANG POLYTECHNIC 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