|
|
【答案】应助回帖
★ ★ ★ ★ ★ ★ ★ ★ ★ ★ 感谢参与,应助指数 +1 peng_weishi: 金币+10, ★★★★★最佳答案, 谢谢 2016-03-10 21:05:12 lazy锦溪: LS-EPI+1, 感谢应助! 2016-03-10 23:34:00
Accession number:
20160902007039
Title: Two approximation algorithms of error spectrum for estimation performance evaluation
Authors: Peng, Wei-Shi1, 2 Email author peng_weishi@163.com; Fang, Yang-Wang1 Email author ywfang2008@sohu.com; Zhan, Ren-Jun2 Email author zhanrenjun@aliyun.com; Wu, You-Li1 Email author wu_youli@126.com
Author affiliation: 1 School of Aeronautics and Astronautics Engineering, Air Force Engineering University, Xi'an, Shaanxi, China
2 School of Equipment Engineering, Armed Police Force Engineering University, Xi'an, Shaanxi, China
Corresponding author: Peng, Wei-Shi (peng_weishi@163.com)
Source title: Optik
Abbreviated source title: Optik
Volume: 127
Issue: 5
Issue date: March 1, 2016
Publication year: 2016
Pages: 2811-2821
Language: English
ISSN: 00304026
Document type: Journal article (JA)
Publisher: Elsevier GmbH
Abstract: Error spectrum is a comprehensive metric for evaluation of estimation performance in that it is an aggregation of many incomprehensive measures. However, error spectrum requires computing the expectation of the rth power of the estimation-error-norm as using it to evaluate an estimator's performance. Therefore unless the error distribution is given, it's usually not easy to obtain the error spectrum. To alleviate this difficulty, two approximation algorithms are proposed. One is the Gaussian mixture method, which calculated the error spectrum by capturing the probability density function. The other using the sample is the power means error method. Furthermore, how the Gaussian mixture method and power means error method can be used in estimation performance evaluation are analyzed not only in the large sample case but also in the small sample case. Numerical examples are provided to illustrate the effectiveness of the above two algorithms. It is shown that the two proposed algorithms can be applied easily to calculate the error spectrum in estimator performance evaluation. © 2015 Elsevier GmbH. All rights reserved.
Number of references: 30
Main heading: Approximation algorithms
Controlled terms: Algorithms - Errors - Estimation - Gaussian distribution - Probability density function
Uncontrolled terms: Error distributions - Error spectrum - Estimation errors - Estimation performance - Gaussian mixture methods - Gaussian mixtures - Power means - Small sample case
Classification code: 921 Mathematics - 922.1 Probability Theory
DOI: 10.1016/j.ijleo.2015.11.204
Database: Compendex
Compilation and indexing terms, © 2016 Elsevier Inc. |
|