A Hybrid Feature Extraction Selection Approach for High-Dimensional Non-Gaussian Data Clustering

被引:99
作者
Boutemedjet, Sabri [1 ]
Bouguila, Nizar [2 ]
Ziou, Djemel [1 ]
机构
[1] Univ Sherbrooke, Dept Informat, Sherbrooke, PQ J1K 2R1, Canada
[2] Concordia Univ, Concordia Inst Informat Engn CIISE, Montreal, PQ H3G 1T7, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Unsupervised learning; mixture models; feature selection; dimensionality reduction; generalized Dirichlet mixture; EM; MML; information theory; object image categorization; STATISTICAL PATTERN-RECOGNITION; DIRICHLET MIXTURE MODEL; UNSUPERVISED SELECTION;
D O I
10.1109/TPAMI.2008.155
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper presents an unsupervised approach for feature selection and extraction in mixtures of generalized Dirichlet (GD) distributions. Our method defines a new mixture model that is able to extract independent and non-Gaussian features without loss of accuracy. The proposed model is learned using the Expectation-Maximization algorithm by minimizing the message length of the data set. Experimental results show the merits of the proposed methodology in the categorization of object images.
引用
收藏
页码:1429 / 1443
页数:15
相关论文
共 42 条
[1]  
[Anonymous], Journal of machine learning research
[2]  
[Anonymous], 2001, The Bayesian choice
[3]  
BOSCH A, 2006, P ECCV, P517, DOI DOI 10.1007/11744085_40
[4]   Unsupervised learning of a finite mixture model based on the Dirichlet distribution and its application [J].
Bouguila, N ;
Ziou, D ;
Vaillancourt, J .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2004, 13 (11) :1533-1543
[5]  
BOUGUILA N, 2003, P 3 INT C MACH LEARN, P172
[6]  
BOUGUILA N, 2006, STAT COMPUTING, V16
[7]  
Bouguila N, 2007, IEEE T PATTERN ANAL, V29, P1716, DOI [10.1109/TPAMI.2007.1095, 10.1109/TPAMl.2007.1095]
[8]   Unsupervised selection of a finite Dirichlet mixture model: An MML-based approach [J].
Bouguila, Nizar ;
Ziou, Djemel .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2006, 18 (08) :993-1009
[9]   A hybrid SEM algorithm for high-dimensional unsupervised learning using a finite generalized dirichlet mixture [J].
Bouguila, Nizar ;
Ziou, Djemel .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2006, 15 (09) :2657-2668
[10]  
BOUTEMEDJET S, 2007, P INT C IM AN REC, P330