基于高斯混合模型和期望最大化算法的非高斯分布圆概率误差估计方法研究

doi:10.3969/j.issn.1000-1093.2019.02.017

兵工学报 ›› 2019, Vol. 40 ›› Issue (2): 369-376.doi: 10.3969/j.issn.1000-1093.2019.02.017

基于高斯混合模型和期望最大化算法的非高斯分布圆概率误差估计方法研究

井沛良¹，段宇²，韩超¹，郭荣化¹，宁小磊¹，刘瑜³

（1.中国华阴兵器试验中心，陕西华阴 714200； 2.空军军医大学，陕西西安 714299； 3.海军航空大学，山东烟台 264001）

收稿日期:2018-04-27 修回日期:2018-04-27 上线日期:2019-04-08
通讯作者: 段宇（1988—），女，助理研究员 E-mail:duanyu11@nudt.edu.cn
作者简介:井沛良（1987—），男，工程师。E-mail：jingpeiliang@nudt.edu.cn

Circular Error Probable Estimation Method Based on Gaussian Mixture Model and Expectation Maximum Algorithm for Non-GaussianDistribution

JING Peiliang¹， DUAN Yu²， HAN Chao¹， GUO Ronghua¹， NING Xiaolei¹， LIU Yu³

(1.Huayin Ordnance Test Center， Huayin 714200， Shaanxi， China； 2.The Fourth Military Medical University， Xi'an 714299， Shaanxi， China； 3.Naval Aviation University， Yantai 264001， Shandong， China)

Received:2018-04-27 Revised:2018-04-27 Online:2019-04-08

摘要/Abstract

摘要： 传统圆概率误差（CEP）估计方法无法处理兵器攻击点/观测点数据服从非高斯分布的情况。为了解决这一问题，提出了一种基于高斯混合模型（GMM）和期望最大化（EM）算法的CEP估计新方法。该方法利用 GMM对兵器攻击点/观测点非高斯分布概率密度函数（PDF）进行建模，通过EM算法迭代估计GMM参数得到兵器攻击点/观测点PDF，并依据所得到的兵器攻击点/观测点PDF，使用二分法得到兵器攻击点/观测点的CEP指标值。采用大量非高斯分布场景生成兵器攻击点/观测点数据，应用所提方法和传统方法进行CEP估计实验。实验结果表明：所提方法估计的CEP均方误差约为传统方法的1/10，由此说明所提方法性能显著好于传统方法，可以有效解决兵器攻击点/观测点数据服从非高斯分布时的CEP估计问题。

关键词: 圆概率误差, 非高斯分布, 高斯混合模型, 期望最大化算法

Abstract: For the situation when the ordnance attacking and/or observing points do not obey the Gaussian distribution, the traditional circular error probability (CEP) computation method could not effectively deal with the experimental data. In order to resolve this problem, one new CEP estimation method based on Gaussian mixture model (GMM) and expectation maximum (EM) algorithm is proposed. In the proposed method, GMM is used to depict the ordnance attacking and/or observing points probability density function（PDF）, the EM algorithm is used to solve the model parameters, and the bisection method is used to compute CEP. A lot of scenes are used to generate the ordnance attacking and/or observing points, and the traditional method and the proposed method are used to estimate the CEP. Experimental results show that the mean square error of CEP computed by the proposed method is about 1/10 of that computed by the traditional method. This illustrates that the performance of the proposed method is better than that of the traditional method. The proposed method could be used effectively to estimate CEP when the ordnance attacking and/or observing points do not obey the Gaussian distribution. Key

Key words: circularerrorprobability, non-Gaussiandistribution, Gaussianmixturemodel, expectationmaximumalgorithm

中图分类号:

E920.8

井沛良，段宇，韩超，郭荣化，宁小磊，刘瑜. 基于高斯混合模型和期望最大化算法的非高斯分布圆概率误差估计方法研究[J]. 兵工学报, 2019, 40(2): 369-376.

JING Peiliang， DUAN Yu， HAN Chao， GUO Ronghua， NING Xiaolei， LIU Yu. Circular Error Probable Estimation Method Based on Gaussian Mixture Model and Expectation Maximum Algorithm for Non-GaussianDistribution[J]. Acta Armamentarii, 2019, 40(2): 369-376.

参考文献

［1］ MORANDA P B. Comparison of estimates of circular probable error [J]. Journal of the American Statistical Association, 1959, 54(288): 794-800.
[2］ KAMAT A R. Some more estimates of circular probable error [J]. Journal of the American Statistical Association, 1962, 57(297): 191-195.
[3］ PAL N, LIM W K. Estimation of circular error probable and measuring the accuracy of a missile system [J]. Statistical Methods, 2003, 2(2): 97-120.
[4］张领科, 王中原, 王枫. 基于命中概率建立通用射表判据的研究[J]. 兵工学报, 2006, 27(2):206-209.
ZHANG L K, WANG Z Y, WANG F. A study on establishing the criterion of current firing table based on hit probability[J]. Acta Armamentarii, 2006, 27(2):206-209. (in Chinese)
[5］王光辉，王瑞琪，朱兴邦，等.超视距反舰导弹命中概率分析[J]. 弹箭与制导学报，2008, 28(2): 33-35.
WANG G H, WANG R Q, ZHU X B, et al. Analysis of beyond-line-of-sight anti-ship missile's hit probability [J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2008, 28(2): 33-35. （in Chinese）
[6］ SCHULA K F, CHALMERS I, HAYES R J, et al. Empirical evidence of bias: dimensions of methodological quality associated with estimates of treatment effects in controlled trials[J]. Journal of the American Medical Association, 1995, 273(5): 408-412.
[7］ LANDIS J R, KOCH G G. A one-way components of variance model for categorical data [J]. Biometrics, 1977, 33(4): 671-679.
[8］ TRAAT I. Introduction to variance estimation, 2nd edition by WOLTER K M [J]. International Statistical Review, 2007, 75(3): 409-438.
[9］ CAMPBELL W M, STURIM D E, REYNOLDS D A. Support vector machines using GMM supervectors for speaker verification [J]. IEEE Signal Processing Letters, 2006, 13(5): 308-311.

[10］ JING P L, TU R B, XU S Y, et al. Binomial splitting Gaussian mixture implementation of the unscented Kalman probability hypothesis density filter[C]∥IEEE International Radar Conference. Krakow, Poland: IEEE, 2016.
[11］ MCLACHLAN G J, KRISHNAN T. The EM algorithm and extensions [J]. Biometrics, 2008, 382(1): 154-156.
[12］ PASHA S A, TUAN H D, VO B N. Nonlinear Bayesian filtering using the unscented linear fractional transformation model [J]. IEEE Transactions on Signal Processing, 2010, 58(2): 477-489.
[13］井沛良. 复杂条件下多目标跟踪关键技术研究[D]. 长沙:国防科技大学, 2016.
JING P L. Research on key technologies of multi-target tracking under complex conditions [D]. Changsha: National University of Defense Technology, 2016. (in Chinese)
[14］ DEMPSTER A P, LAIRD N M, RUBIN D B. Maximum likelihood from incomplete data via the EM algorithm [J]. Journal of the Royal Statistical Society, 1977, 39(1): 1-38.
[15］ COX I J, HINGORANI S L, RAO S B, et al. A maximum likelihood stereo algorithm [J]. Computer Vision & Image Understanding, 1996, 63(3):542-567.
[16］ MARCO D, CHRISTIAN B. Ant colony optimization theory: a survey [J]. Theoretical Computer Science, 2005, 344(2/3): 243-278.
[17］ MARCO D, MONTES D, SABRINA O, et al. Ant colony optimization [J]. IEEE Computational Intelligence Magazine, 2006, 1(4): 28-39.
[18］ WHITLEY D. A genetic algorithm tutorial [J]. Statistics and Computing, 1994, 4(2): 65-85.
[19］刘志浩, 高钦和, 刘准, 等. 重载轮胎面内刚柔耦合动力学建模及振动传递特性分析[J]. 兵工学报, 2018, 39(2):224-233.
LIU Z H, GAO Q H, LIU Z, et al. In-plane rigid-elastic coupling dynamic modeling and vibration response prediction of heavy duty radial tire[J]. Acta Armamentarii, 2018, 39(2):224- 233. (in Chinese)
[20］ LUO X L, FU X L. Configuration optimization method of Hadoop system performance based on genetic simulated annealing algorithm[J]. Cluster Computing, 2018(2): 1-9.
[21］ OTTEN R, GINNEKEN L. The annealing algorithm[M]. Boston, MA, US: Kluwer Academic Publishers, 1989.
[22］ MAHLER R P S. Statistical multisource multitarget information fusion[M]. Norwood: Artech House, 2007.
[23］ ABBASBANDY S. Improving Newton-Raphson method for nonlinear equations by modified Adomian decomposition method [J]. Applied Mathematics & Computation, 2003, 145(2): 887-893.
[24］ YPMA T J. Historical development of the Newton-Raphson method [J]. SIAM Review, 1995, 37(4): 531-551.
[25］ FRIEDLAND S, HERSONSKY S. Gensen's inequality for discrete groups in normed algebras [J]. Duke Mathematical Journal, 1993, 69(3): 593-614.
[26］ KULLBACK S. The Kullback-Leibler distance [J]. The American Statistician, 1987, 41(4): 340-341.

第40卷第2期
2019 年2月兵工学报ACTA
ARMAMENTARIIVol.40No.2Feb. 2019

[1]	许晓东，唐圣金，谢建，于传强，王凤飞，韩洋洋. 随机退化应力作用下设备剩余寿命预测方法[J]. 兵工学报, 2022, 43(3): 712-719.
[2]	宁小磊，吴颖霞，赵新. 融合仿真数据的小子样圆概率误差评估[J]. 兵工学报, 2021, 42(2): 388-398.
[3]	王博洋，龚建伟，熊光明，张瑞增，陈慧岩，席军强. 有级转向履带车辆的驾驶员操控行为模型[J]. 兵工学报, 2020, 41(12): 2379-2388.
[4]	梁文利，陈慧岩，王博洋. 基于独立电驱动履带车辆的地面参量估计方法研究[J]. 兵工学报, 2019, 40(6): 1146-1153.
[5]	张永顺，朱卫纲，孟祥航，贾鑫，曾创展，王满喜. 基于块稀疏贝叶斯学习的跳频通信梳状干扰抑制[J]. 兵工学报, 2018, 39(9): 1864-1872.

基于高斯混合模型和期望最大化算法的非高斯分布圆概率误差估计方法研究

Circular Error Probable Estimation Method Based on Gaussian Mixture Model and Expectation Maximum Algorithm for Non-GaussianDistribution

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价