论文信息 - Data description in subspaces

Data description in subspaces

We investigate how the boundary of a data set can be obtained in case of (very) low sample sizes. This boundary can be used to detect if new objects resemble the data set and therefore make the subsequent classification more confident. When a large number of training objects is available it is possible to directly estimate the density. After thresholding the probability density a boundary around the data is obtained. However, in the case of very low sample sizes, extrapolations have to be performed. In this paper we propose a simple method based on nearest neighbor distances which is capable of finding data boundaries in these low sample sizes. It appears to be especially useful when the data is distributed in subspaces.

Robert P. W. Duin | David M. J. Tax | D. Tax | R. Duin

[1] Michael Brady,et al. Novelty detection for the identification of masses in mammograms , 1995 .

[2] M. M. Moya,et al. One-class classifier networks for target recognition applications , 1993 .

[3] Christopher M. Bishop,et al. Novelty detection and neural network validation , 1994 .

[4] Richard O. Duda,et al. Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[5] Robert P. W. Duin,et al. Support vector domain description , 1999, Pattern Recognit. Lett..

[6] Gunter Ritter,et al. Outliers in statistical pattern recognition and an application to automatic chromosome classification , 1997, Pattern Recognit. Lett..

[7] Vladimir Vapnik,et al. Statistical learning theory , 1998 .

[8] Robert P. W. Duin,et al. Data domain description using support vectors , 1999, ESANN.

[9] Stephen Grossberg,et al. ART 2-A: An adaptive resonance algorithm for rapid category learning and recognition , 1991, Neural Networks.

[10] Teuvo Kohonen,et al. Self-Organizing Maps , 2010 .

[11] Nathalie Japkowicz,et al. Concept learning in the absence of counterexamples: an autoassociation-based approach to classification , 1999 .