基于直觉模糊c均值聚类核匹配追踪的弹道中段目标识别方法

doi:10.3969/j.issn.1000-436x.2012.11.017

通信学报 ›› 2012, Vol. 33 ›› Issue (11): 136-143.doi: 10.3969/j.issn.1000-436x.2012.11.017

基于直觉模糊c均值聚类核匹配追踪的弹道中段目标识别方法

雷阳¹,孔韦韦²,雷英杰³

¹ 武警工程大学电子技术系网络与信息安全武警部队重点实验室，陕西西安 710086
² 武警工程大学通信工程系，陕西西安 710086
³ 空军工程大学防空反导学院，陕西西安 710051

出版日期:2012-11-25 发布日期:2017-07-25
基金资助:
国家自然科学基金资助项目;国家自然科学基金资助项目

Technique for target recognition based on intuitionistic fuzzy c-means clustering and kernel matching pursuit

Yang LEI¹,Wei-wei KONG²,Ying-jie LEI³

¹ Network andInformation Security Key Laboratoryof Electronics Department,Engineering University of Armed Police Force,Xi’an 710086,China
² Department of Information Engineering,Engineering Uni rsity of Armed Police Force,Xi’an 710086,China
³ Institute of Air Defense Against Missle,Air Force Engineering University,Xi’an 710051,China

Online:2012-11-25 Published:2017-07-25
Supported by:
The National Natural Science Foundation of China;The National Natural Science Foundation of China

摘要/Abstract

摘要：

针对核匹配追踪算法(KMP,kernel matching pursuit)进行全局最优搜索导致学习时间过长这一缺陷，汲取直觉模糊c均值聚类(IFCM,intuitionistic fuzzy c-means)算法的动态聚类特性优势，提出一种基于直觉模糊c均值聚类的核匹配追踪(IFCM-KMP,intuitionistic fuzzy c-means kernel matching pursuit)算法，且对UCI库中4组实际样本数据进行了分类实验及有效性测试。最后，选取高分辨距离像(HRRP)这一弹道中段目标识别常用的特征属性，对其进行特征提取获得子像，并分别采用FCM，KMP，IFCM-KMP 3 种算法对真弹头进行目标识别仿真实验及结果对比分析，充分表明了IFCM-KMP算法用于弹道中段目标识别较之FCM、KMP的优越性及有效性。

关键词: 直觉模糊集, c均值聚类, 模糊c均值聚类, 核匹配追踪, 高分辨距离像, 目标识别

Abstract:

Kernel matching pursuit requires every step of searching process be global optimal searching in the redundant dictionary of function.Namely,the dictionary learning time of KMP was too long.To the above drawbacks,a novel technique for KMP based on IFCM was proposed to substitute local searching for global searching by the property superiority of dynamic clustering performance,which was also the superiority in Intuitionistic fuzzy c-means algorithm.Then two testing including classification and effectiveness were carried out towards four real sample data.Subsequently,high resolution range profile (HRRP)was selected from the classical properties of target recognition in e middle ballistic trajectory,which were extracted for getting sub-range profile.Finally,three algorithms including FCM,KMP,IFCM-KMP were carried out respectively towards different kinds of sub-range profile samples in emulation platform,the conclusion of which fully demonstrates that the IFCM-KMP algorithm is superior over FCM and KMP when it comes to target recognition in the middle ballistic trajectory.

Key words: intuitionistic fuzzy sets, c-means clustering, fuzzy c-means clustering, kernel matching pursuit, high resolution range profile, target recognition

雷阳,孔韦韦,雷英杰. 基于直觉模糊c均值聚类核匹配追踪的弹道中段目标识别方法[J]. 通信学报, 2012, 33(11): 136-143.

Yang LEI,Wei-wei KONG,Ying-jie LEI. Technique for target recognition based on intuitionistic fuzzy c-means clustering and kernel matching pursuit[J]. Journal on Communications, 2012, 33(11): 136-143.

图/表 9

图1

表1

图2

表2

图3

图4

图5

图6

表3

参考文献 14

[1]	POPOVICI V , BENGIO S , THIRAN J P . Kernel maching pursuit for large datasets[J]. Pattern Recgnition, 2005,38(12): 2385-2390.
[2]	PASCAL V , YOSHUA B . Kernel matching pursuit[J]. Machine Learning, 2002,48: 165-187.
[3]	LIAO X J , LI H , KRISHNAPURAM B . An M-ary kernel macthing pursuit classifier for multi-aspect target classification[A]. Proceedings of IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP)[C]. Montreal,Canada, 2004. 61-64.
[4]	缑水平, 焦李成 . 基于多尺度几何分析与核匹配追踪的图象识别[J]. 模式识别与人工智能, 2007,20(6): 776-781. GOU S P , JIAO L C . Image recognition based on multi-scale geometric analysis and kernel matching pursuit[J]. Pattern Recognition and Artificial Intelligence, 2007,20(6): 776-781.
[5]	缑水平, 焦李成, 张向荣 . 基于免疫克隆与核匹配追踪的快速图象目标识别[J]. 电子与信息学报, 2008,30(5): 1104-1108. GOU S P , JIAO L C , ZHANG X R . Kernel matching pursuit on immune clonal fast algorithm for image object recognition[J]. Journal of Electronics ＆ Information Technology, 2008,30(5): 1104-1108.
[6]	缑水平, 焦李成, 张向荣 . 基于免疫克隆的核匹配追踪集成图象识别算法[J]. 模式识别与人工智能, 2009,22(1): 79-85. GOU S P , JIAO L C , ZHANG X R . Image recognition with kernel matching pursuit classifier ensemble based on immune c ne[J]. Pattern Recognition and Artificial Intelligence, 2009,22(1): 79-85.
[7]	马建华, 刘宏伟, 保铮 . 利用核匹追踪算法进行雷达高分辨距离像识别[J]. 西安电子科技大学学报（自然科学版）, 2005,32(1): 84-88. MA J H , LIU H W , BAO Z . Radar HRRP recognition based on the kernel matching pursuit classifier[J]. Journal of Xi’an Electronic Technology University(Natural Science Edition), 2005,32(1): 84-88.
[8]	李青, 焦李成, 周伟达 . 基于模糊核匹配追寻的特征模式识别[J]. 计算机学报, 2009,32(8): 1687-1694. LI Q , JIAO L C , ZHOU W D . Pattern recognition based on the fuzzy kernel matchingpursuit[J]. Chinese Journal of Computers, 2009,32(8): 1687-1694.
[9]	申晓勇, 雷英杰, 李进 . 基于目标函数的直觉模糊集合数据的聚类方法[J]. 系统工程与电子技术, 2009,11(31): 2732-2735. SHEN X Y , LEI Y J , LI J . A clustering technique to int itionistic fuzzy sets based on objective function[J]. Systems Engineering and Electronics, 2009,11(31): 2732-2735.
[10]	DAVIS G , MALLAT S , ZHANG Z . Adaptive time-frequency decompositions[J]. Optical Engineering, 1994,33(7): 2183-2191.
[11]	MALLAT S , ZHANG Z . Matching pursuit with time-frequency dictionaries[J]. IEEE Transactions on Signal processing, 41(12): 3397-3415.
[12]	PATI Y , REZAIIFAR R , KRISHNAPRASAD P . Orthogonal mathcing pursuit:recursive function approximation with applications to wavelet decomposition[A]. Proceedings of the 27th Annual Asilomar Conference on Signals,Systems and Computers[C]. CA,USA, 1993. 40-44.
[13]	李康乐, 刘永祥, 黎湘 . 弹道导弹中段防御系统目标识别仿真研究[J]. 现代雷达, 2006,11(28): 12-19. LI K L , LIU Y X , LI X . A study on simulation of target discrimination in ballistic missile mid-course defense system[J]. Modern Radar, 2006,11(28): 12-19.
[14]	赵峰, 张军英, 刘敬 . 基于核最优变换与聚类中心的雷达目标识别[J]. 控制与决策, 2008,23(7): 736-740. ZHAO F , ZHANG J Y , LIU J . Radar target recognition based on kernel optimal transformation and cluster centers[J]. Control and Decision, 2008,23(7): 736-740.

数据集	FCM	KMP	IFCM-KMP
Iris	0.072 1	0.05 39	0.031 1
Wine	0.065 2	0.048 4	0.031 2
Wisconsin	0.074 4	0.045 8	0.032 3
Motorcycle	0.068 9	0.050 4	0.028 8

性能指标	FCM	KMP	IFCM-KMP
PC	0.647 8	0.789 1	0.852 0
CE	0.643 3	0.332 4	0.852 1
SC	1.897 0	1.666 6	1.575 0
S	0.007 7	0.010 1	0.013 1
XB	3.111 0	2.841 2	2.110 1
DI	0.033 0	0.012 2	0.048 0
ADI	0.035 1	0.013 3	0.049 6

算法	平均错分误差e’	平均识别率?	平均识别速度s
FCM	0.755	0.481	0.800
KMP	0.381	0.773	12.100
IFCM-KMP	0.241	0.867	3.211

基于直觉模糊c均值聚类核匹配追踪的弹道中段目标识别方法

Technique for target recognition based on intuitionistic fuzzy c-means clustering and kernel matching pursuit

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 14

相关文章 7

Metrics

推荐阅读 0

[1]	王晓飞,胡凡奎,黄硕. 基于分布信息直觉模糊c均值聚类的红外图像分割算法[J]. 通信学报, 2020, 41(5): 120-129.
[2]	范晓诗,雷英杰,路艳丽,王亚男. 基于DTW的长期直觉模糊时间序列预测模型[J]. 通信学报, 2016, 37(8): 95-104.
[3]	余晓东,雷英杰,岳韶华,王睿. 基于粒子群优化的直觉模糊核聚类算法研究[J]. 通信学报, 2015, 36(5): 74-80.
[4]	余晓东,雷英杰,宋亚飞,岳韶华,胡军红. 基于直觉模糊核匹配追踪集成的目标识别方法[J]. 通信学报, 2015, 36(10): 165-171.
[5]	王荣杰,詹宜巨,周海峰. 基于零空间表示和最大似然的欠定盲源分离方法[J]. 通信学报, 2012, 33(3): 183-190.
[6]	黄波,赵晓晖,曹昕艳,赵继印,时公涛. 基于两尺度自卷积的直方图仿射不变量提取方法[J]. 通信学报, 2012, 33(12): 140-146.
[7]	孙欣尧,王雪,王晟. 无线传感网络协同概率多模识别方法[J]. 通信学报, 2011, 32(6): 141-147.