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

GMM and EM algorithm-based non-Gaussian distribution CEP estimation method

A non-Gaussian distribution and Gaussian component technology, which can be used in complex mathematical operations and other directions, and can solve problems such as the decline in the accuracy of CEP evaluation.

Inactive Publication Date: 2017-12-22
中国人民解放军63870部队
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, the CEP calculation method widely used in engineering is only applicable to the case where the observed data obey or approximately obey the Gaussian distribution. When the observed data presents a non-Gaussian distribution such as multiple dense centers, the accuracy of the evaluation CEP calculated by the existing method will drop significantly.

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
  • GMM and EM algorithm-based non-Gaussian distribution CEP estimation method
  • GMM and EM algorithm-based non-Gaussian distribution CEP estimation method
  • GMM and EM algorithm-based non-Gaussian distribution CEP estimation method

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0051] The present invention includes the following steps.

[0052] S.1 Observational data collection and collation;

[0053]The observation data refers to the coordinate value of the impact point or the target positioning point, which is written in the form of vector x; the coordinate system selects the Cartesian coordinate system, and the coordinate origin selects the target or the center point of the target to be reconnaissance; when M experiments are performed, the M observation data are written as vector collection {x 1 , x 2 ,...,x M}form;

[0054] S.2 Given the initial value of the parameter;

[0055] Take the initial weight parameter w k ∈(0,1), and All mean vectors μ k In the collection containing observation data {x 1 , x 2 ,...,x M} selected from the smallest rectangle; all covariance matrices R k The diagonal elements of and the set of observation data {x 1 , x 2 ,...,x M} The squares of the corresponding side lengths of the smallest rectangle are eq...

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 GMM and EM algorithm-based non-Gaussian distribution CEP estimation method, belongs to the field of equipment performance testing and statistic signal processing, and aims to solve the problem of CEP estimation when observation data obeys non-Gaussian distribution. The method comprises the steps of firstly performing modeling and representation on any non-Gaussian distribution by using GMM; secondly based on a maximum likelihood thought, solving model parameters by using an EM algorithm; and finally for an obtained Gaussian mixture model, calculating out a circular probable error value by using a bisection method. When the observation data obeys the non-Gaussian distribution, the CEP estimation precision is remarkably superior to that of a conventional method.

Description

technical field [0001] The invention relates to a non-Gaussian distribution CEP estimation method based on GMM and EM algorithms, which belongs to the field of equipment performance appraisal and statistical signal processing. Background technique [0002] At present, the CEP calculation method widely used in engineering is only applicable to the case where the observation data obeys or approximately obeys the Gaussian distribution. When the observation data presents a non-Gaussian distribution such as multiple dense centers, the accuracy of the evaluation CEP calculated by the existing method drops significantly. Contents of the invention [0003] The purpose of the present invention is to provide a high-precision CEP estimation method when the observed data obeys the non-Gaussian distribution. [0004] Principle of the present invention: firstly, any non-Gaussian distribution is modeled through the GMM model; secondly, the parameters of the GMM model are solved by using ...

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): G06F17/18G06F17/16
CPCG06F17/18G06F17/16
Inventor 井沛良吴玉生范革平郭荣化撒彦成姬强赵鹏江山马子龙宋平
Owner 中国人民解放军63870部队
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