Optimizing Subspace SVM Ensemble for Hyperspectral Imagery Classification

被引:46
作者
Chen, Yushi [1 ]
Zhao, Xing [1 ]
Lin, Zhouhan [1 ]
机构
[1] Harbin Inst Technol, Sch Elect & Informat Engn, Dept Informat Engn, Harbin 150001, Peoples R China
基金
中国国家自然科学基金;
关键词
Ensemble; hyperspectral imagery classification; optimal subspace; random subspace; support vector machine (SVM); FEATURE-SELECTION; GENETIC ALGORITHMS; FRAMEWORK; SYSTEM;
D O I
10.1109/JSTARS.2014.2307356
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In hyperspectral remote sensing image classification, ensemble systems with support vector machine (SVM), such as the Random Subspace SVM Ensemble (RSSE), have significantly outperformed single SVM on the robustness and overall accuracy. In this paper, we introduce a novel subspace mechanism, the Optimizing Subspace SVM Ensemble (OSSE), to improve RSSE by selecting discriminating subspaces for individual SVMs. The framework is based on Genetic Algorithm (GA), adopting the Jeffries-Matusita (JM) distance as a criterion, to optimize the selected subspaces. The combination of optimizing subspaces is more suitable for classification than the random one, at the same time having the ability to accommodate requisite diversity within the ensemble. The modifications have improved the accuracies of individual classifiers; as a result, better overall accuracies are present. Experiments on the classification of two hyperspectral datasets reveal that our proposed OSSE obtains sound performances compared with RSSE, single SVM, and other ensemble with GA to optimize SVM.
引用
收藏
页码:1295 / 1305
页数:11
相关论文
共 53 条
[1]  
[Anonymous], 1993, P 3 INT WORKSHOP FRO
[2]   Pixel classification using variable string genetic algorithms with chromosome differentiation [J].
Bandyopadhyay, S ;
Pal, SK .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2001, 39 (02) :303-308
[3]   Toward an optimal SVM classification system for hyperspectral remote sensing images [J].
Bazi, Yakoub ;
Melgani, Farid .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2006, 44 (11) :3374-3385
[4]   A Multiple SVM System for Classification of Hyperspectral Remote Sensing Data [J].
Bigdeli, Behnaz ;
Samadzadegan, Farhad ;
Reinartz, Peter .
JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING, 2013, 41 (04) :763-776
[5]  
Boser B. E., 1992, Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory, P144, DOI 10.1145/130385.130401
[6]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[7]  
Brown G, 2010, LECT NOTES COMPUT SC, V5997, P124, DOI 10.1007/978-3-642-12127-2_13
[8]   A technique for feature selection in multiclass problems [J].
Bruzzone, L ;
Serpico, SB .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2000, 21 (03) :549-563
[9]   An extension of the Jeffreys-Matusita distance to multiclass cases for feature selection [J].
Bruzzone, L ;
Roli, F ;
Serpico, SB .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1995, 33 (06) :1318-1321
[10]   LIBSVM: A Library for Support Vector Machines [J].
Chang, Chih-Chung ;
Lin, Chih-Jen .
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)