整数矩阵变换的选择集成及对雷达目标的识别

doi:10.3969/j.issn.1001-2400.2015.02.003

J4 ›› 2015, Vol. 42 ›› Issue (2): 13-19.doi: 10.3969/j.issn.1001-2400.2015.02.003

整数矩阵变换的选择集成及对雷达目标的识别

熊霖;焦李成;毛莎莎

(西安电子科技大学智能感知与图像理解教育部重点实验室，陕西西安 710071)

收稿日期:2013-12-03 出版日期:2015-04-20 发布日期:2015-04-14
作者简介:熊霖(1981-)，男，西安电子科技大学博士研究生，E-mail: bruinxiong@me.com．
基金资助:
国家重点基础研究发展计划资助项目(2013CB329402)；国家自然科学基金资助项目(61003198, 61072106, 61173092)；高等学校学科创新引智计划(111计划)资助项目(B07048)

Selective ensemble based on the integer matrix linear transformation and its application to radar target recognition

XIONG Lin;JIAO Licheng;MAO Shasha

(Ministry of Education Key Lab. of Intelligent Perception and Image Understanding, Xidian Univ., Xi'an 710071, China)

Received:2013-12-03 Online:2015-04-20 Published:2015-04-14

摘要/Abstract

摘要：

为了改善单个分类器对雷达目标的识别性能，分别从差异性和准确率两个因素出发，提出了一种通过变换分类器选择集成对雷达目标识别的算法．首先，为了增加集成个体差异性，将个体分类器的预测标记作为变换的原始目标，将正确标记引入来代替变换中的目标均值，以此构造一个整数矩阵．通过将个体分类器的预测标记投影到经过正确标记的直线上，从而获得一组新的预测标记．然后，根据准确率和RPF-measure这两种衡量分类器性能的准则，选择一些性能提高了的个体进行集成，以此保证个体分类器的准确率．最后，通过结合被选择的个体预测标记来改善对雷达目标的识别性能．对于UCI机器学习资源库中数据集和雷达一维距离像的实验结果表明，该算法能有效平衡个体差异性和个体准确率两个因素，并且相比单个分类器和其他集成方法，该方法提高了对雷达目标的识别准确率．

关键词: 分类器集成, 选择性集成, 雷达目标识别

Abstract:

Diversity among individuals and accuracy of individuals are two important factors to decide the ensemble generalization error, whereas enhancing diversity is at the cost of decreasing the accuracy of individuals. Hence, in order to improve the performance of radar target recognition classified by a single classifier, this paper introduces a new radar target recognition method based on the integer matrix linear transformation selective classifier ensemble that considers the balance of diversity and accuracy. Firstly, in order to enhance the diversity, the individual classifiers are considered as original targets of the linear transformation, and instead of the mean value of samples, the true labels are considered to construct an integer matrix. By projecting individual classifiers on the lines through the true labels, a set of new classifiers is obtained based on the project transformation. Secondly, according to two rules that measuring the performance of the classifier, the accuracy rate and RPF-measure, some new classifiers that can obtain better performance are selected to ensemble for increasing the accuracy of classifiers of an ensemble. Finally, the performance of radar target recognition is improved by combining the selected new classifiers. Experimental results of UCI datasets and the radar range profile indicate that the proposed method balances effectively diversity and accuracy, and that it can obtain better performance for radar target recognition compared with single classifier algorithms and other methods.

Key words: classifier ensemble, selective ensemble, radar target recognition.

熊霖;焦李成;毛莎莎 . 整数矩阵变换的选择集成及对雷达目标的识别[J]. J4, 2015, 42(2): 13-19.

XIONG Lin;JIAO Licheng;MAO Shasha . Selective ensemble based on the integer matrix linear transformation and its application to radar target recognition[J]. J4, 2015, 42(2): 13-19.

参考文献

［1］杜兰. 雷达高分辨距离像目标识别方法研究［D］. 西安:西安电子科技大学，2007.
［2］ Du Lan, Wang Penghui, Liu Hongwei, et al. Bayesian Spatiotemporal Multitask Learning for Radar HRRP Target Recognition ［J］. IEEE Transactions on Signal Processing, 2011, 59(7): 3182-3196.
［3］李志鹏, 马田香, 杜兰, 等. 在雷达HRRP识别中多特征融合多类分类器设计［J］. 西安电子科技大学学报, 2013, 40(1): 111-117.
Li Zhipeng, Ma Tianxiang, Du Lan, et al. Multi-class Classifier Design for Feature Fusion in Radar HRRP Rrecognition ［J］. Journal of Xidian University, 2013, 40(1): 111-117.
［4］ Hansen L K, Salamon P. Neural Network Ensembles ［J］. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1990, 12(10): 993-1001.
［5］ Kuncheva L I. Combining Pattern Classifiers: Methods and Algorithms ［M］. Hoboken: Published by John Wiley ＆ Sons, Incorporated, 2004.
［6］ Beriman L. Bagging Predictors ［J］. Machine Learning, 1996, 24(2): 123-140.
［7］ Mao Shasha, Jiao Licheng, Xiong Lin, et al. Greedy Optimization Classifiers Ensemble Based on Diversity ［J］. Pattern Recognition, 2011, 44(6): 1245-1261.
［8］ Margineantu D D, Dietterich T G. Pruning Adaptive Boosting ［DB/OL］. ［2013-02-11］. http://www.informatik.uni-trier.de/~lev/db/conf/icml/icml1997.html#MargineantuD97.
［9］ Zhou Zhihua, Wu Jianxin, Jiang Yuan, et al. Genetic Algorithm Based Selective Neural Network Ensemble ［DB/OL］. ［2013-03-11］. http://www.informatik.uni-trier.de/~lev/db/conf/ijcai/ijcai2001.html#ZhouWJC01.
［10］ Patra A, Das S. Enhancing Decision Combination of Face and Fingerprint by Exploitation of Individual Classifier Space: an Approach to Multi-modal Biometry ［J］. Pattern Recognition, 2008, 41(7): 2298-2308.
［11］ Ghorai S, Mukherjee A, Sengupta S, et al. Cancer Classification from Gene Expression Data by NPPC Ensemble ［J］. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2011, 8(3): 659-671.
［12］ Song Xiangfa, Jiao Licheng, Yang Shuyuan, et al. Sparse Coding and Classifier Ensemble Based Multi-instance Learning for Image Categorization ［J］. Signal Processing, 2013, 93(1): 1-11.
［13］ Duda R O, Hart P E, Stock D G, et al. Pattern Classification ［M］. Second Edition. Beijing: China Machine Press, 2003.
［14］ Huang Y J, Powers R, Montelione G T. Protein NMR Recall, Precision, and F-measure Scores (RPF Scores): Structure Quality Assessment Measures Based on Information Retrieval Statistics ［J］. Journal American Chemical Society, 2005, 127(6): 1665-1674.
［15］ Quinlan J R. C4.5: Programs for Machine Learning ［M］. San Mateo: Morgan Kaufmann, 1993.
［16］ Burges C J C. A Tutorial on Support Vector Machines for Pattern Recognition ［J］. Data Mining and Knowledge Discovery, 1998, 2(2): 121-167.

[1]	郭泽坤,田隆,韩宁,王鹏辉,刘宏伟,陈渤. 采用CNN-SSD的雷达HRRP小样本目标识别方法[J]. 西安电子科技大学学报, 2021, 48(2): 7-14.
[2]	徐丹蕾;杜兰;王鹏辉;刘宏伟. 采用多任务稀疏学习的雷达HRRP小样本目标识别[J]. 西安电子科技大学学报, 2016, 43(2): 23-28.
[3]	李志鹏;马田香;杜兰;徐丹蕾;刘宏伟;张子敬. 在雷达HRRP识别中多特征融合多类分类器设计[J]. J4, 2013, 40(1): 111-117.
[4]	王鹏辉;杜兰;刘宏伟;李彦兵;吴兆平. 雷达高分辨距离像分帧新方法[J]. J4, 2011, 38(6): 22-29.
[5]	关永胜;左群声;刘宏伟;杜兰;李彦兵. 空间锥体目标微动特性分析与识别方法[J]. J4, 2011, 38(2): 105-111.
[6]	李丽亚;刘宏伟;纠博;吴顺君. 基于核函数的多极化雷达HRRP目标识别[J]. J4, 2010, 37(1): 49-55.
[7]	侯庆禹;刘宏伟;保铮. 一种新的宽带目标识别雷达杂波抑制方法 [J]. J4, 2008, 35(5): 769-773.
[8]	裴炳南1;2;保铮1;陈江峰2. 雷达一维距离像目标识别方法性能的研究[J]. J4, 2003, 30(2): 141-145.
[9]	姬红兵;高新波;谢维信. 雷达目标双谱特征分析与分类方法研究[J]. J4, 1999, 26(6): 691-695.
[10]	暂时无作者信息. 基于子波和进化网络的目标识别[J]. J4, 1999, 26(3): 328-332.
[11]	暂时无作者信息. 基于多层前向网络的雷达目标一维距离像识别[J]. J4, 1997, 24(1): 0-0.

整数矩阵变换的选择集成及对雷达目标的识别

Selective ensemble based on the integer matrix linear transformation and its application to radar target recognition

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

Metrics

本文评价

推荐阅读 0