© The Institution of Engineering and Technology
The least absolute shrinkage and selection operator (lasso) is a promising feature selection technique. However, it has traditionally not been a focus of research in ensemble classification methods. In this study, the authors propose a robust classification algorithm that makes use of an ensemble of classifiers in lasso feature subspaces. The algorithm consists of two stages: the first is a lasso-based multiple feature subsets selection cycle, which tries to find a number of relevant and diverse feature subspaces; the second is an ensemble-based decision system that intends to preserve the classification performance in case of abrupt changes in the representation space. Experimental results on the two-class textured image segmentation problem prove the effectiveness of the proposed classification method.
References
-
-
1)
-
He, X., Beauseroy, P., Smolarz, A.: `Nearest neighbor ensembles in lasso feature subspaces', Proc. Fifth IET Int. Conf. on Visual Information Engineering, 29 July–1 August 2008, Xi'an, China, p. 100–105.
-
2)
-
L.K. Hansen ,
P. Salamon
.
Neural network ensembles.
IEEE Trans. Pattern Anal. Mach. Intell.
,
10 ,
993 -
1001
-
3)
-
Opitz, D.W.: `Feature selection for ensembles', Proc. 16th National Conf. on Artificial Intelligence, 18–22 July 1999, Orlando, FL, USA, p. 379–384.
-
4)
-
K. Tumer ,
J. Ghosh
.
Error correlation and error reduction in ensemble classifiers.
Connect. Sci.
,
385 -
404
-
5)
-
S.D. Bay
.
Nearest neighbor classification from multiple feature subsets.
Intell. Data Anal.
,
3 ,
191 -
209
-
6)
-
V. Roth
.
The generalized lasso.
IEEE Trans. Neural Netw.
,
1 ,
16 -
28
-
7)
-
R. Tibshirani
.
Regression shrinkage and selection via the lasso.
J. R. Stat. Soc. B (Methodol.)
,
1 ,
267 -
288
-
8)
-
V. Vapnik
.
(1995)
The nature of statistical learning theory.
-
9)
-
V.N. Vapnik
.
(1998)
Statistical learning theory.
-
10)
-
Krogh, A., Vedelsby, J.: `Neural network ensembles, cross validation, and active learning', Proc. Eighth Annual Conf. on Neural Information Processing System, 3–8 December 1994, Vancouver, British Columbia, Canada, p. 231–238.
-
11)
-
Beauseroy, P., Smolarz, A.: `Optimisation de la géométrie du voisinage pour la segmentation d'images texturées', Proc. XXXVIèmes Journées de Statistique, 24–28 May 2004, Montpellier, France, p. 6, (in French).
-
12)
-
C.J. Veenman ,
D.M.J. Tax
.
LESS: a model-based classifier for sparse subspaces.
IEEE Trans. Pattern Anal. Mach. Intell.
,
9 ,
1496 -
1500
-
13)
-
T.K. Ho
.
The random subspace method for constructing decision forests.
IEEE Trans. Pattern Anal. Mach. Intell.
,
8 ,
832 -
844
-
14)
-
Smolarz, A.: `Etude qualitative du modèle auto-binomial appliqué à la synthèse de texture', Proc. XXIXèmes Journées de Statistique, 26–30 May 1997, Carcassonne, France, p. 712–715, (in French).
-
15)
-
L. Breiman
.
Bagging predictors.
Mach. Learn.
,
2 ,
123 -
140
-
16)
-
Kim, Y., Kim, J.: `Gradient lasso for feature selection', Proc. 21st Int. Conf. on Machine Learning, 4–8 July 2004, Banff, Alberta, Canada, p. 60–67.
-
17)
-
Cunningham, P., Carney, J.: `Diversity versus quality in classification ensembles based on feature selection', Proc. 11th European Conf. on Machine Learning, 30 May–2 June 2000, Barcelona, Catalonia, Spain, p. 109–116.
-
18)
-
D.W. Opitz ,
R. Maclin
.
Popular ensemble methods: an empirical study.
J. Artif. Intell. Res.
,
169 -
198
-
19)
-
Dietterich, T.G.: `Ensemble methods in machine learning', Proc. First Int. Workshop on Multiple Classifier Systems, 21–23 June 2000, Cagliari, Italy, p. 1–15.
-
20)
-
P. Beauseroy ,
A. Smolarz ,
X. He
.
Sélection aléatoire d'espaces de représentation pour la décision binaire en environnement non-stationnaire: application à la segmentation d'images texturées.
Rev. Nouvelles Technol. Inf.
,
87 -
105
-
21)
-
E. Bauer ,
R. Kohavi
.
An empirical comparison of voting classification algorithms: bagging, boosting, and variants.
Mach. Learn.
,
105 -
139
-
22)
-
Li, F., Yang, Y., Xing, E.P.: `From lasso regression to feature vector machine', Proc. 19th Annual Conf. on Neural Information Processing Systems, 5–10 December 2005, Vancouver and Whistler, British Columbia, Canada, p. 779–786.
-
23)
-
C.J.C. Burges
.
A tutorial on support vector machines for pattern recognition.
Data Min. Knowl. Discov.
,
2 ,
121 -
167
-
24)
-
Keerthi, S.S.: `Generalized lars as an effective feature selection tool for text classification with svms', Proc. 22nd Int. Conf. on Machine Learning, 7–11 August 2005, Bonn, Germany, p. 417–424.
-
25)
-
A. Tsymbal ,
S. Puuronen ,
D.W. Patterson
.
Ensemble feature selection with the simple bayesian classification.
Inf. Fusion
,
2 ,
87 -
100
-
26)
-
P. Brodatz
.
(1966)
Textures: a photographic album for artists and designers.
-
27)
-
Zenobi, G., Cunningham, P.: `Using diversity in preparing ensembles of classifiers based on different feature subsets to minimize generalization error', Proc. 12th European Conf. on Machine Learning, 3–7 September 2001, Freiburg, Germany, p. 576–587.
-
28)
-
Ng, A.Y.: `Feature selection, ', Proc. 21st Int. Conf. on Machine Learning, 4–8 July 2004, Banff, Alberta, Canada, p. 78–85.
-
29)
-
N. Cristianini ,
J. Shawe-Taylor
.
(2000)
An introduction to support vector machines.
-
30)
-
Freund, Y., Schapire, R.E.: `Experiments with a new boosting algorithm', Proc. 13th Int. Conf. on Machine Learning, 3–6 July 1996, Bari, Italy, p. 148–156.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2009.0056
Related content
content/journals/10.1049/iet-cvi.2009.0056
pub_keyword,iet_inspecKeyword,pub_concept
6
6