Context-sensitive intra-class clustering

dc.contributor.authorYu, Yingwei
dc.contributor.authorGutierrez-Osuna, Ricardo
dc.contributor.authorChoe, Yoonsuck
dc.contributor.institutionIHS Inc., Houston, United States
dc.contributor.institutionTexas A and M University, College Station, United States
dc.date.accessioned2016-02-25T12:57:41Z
dc.date.available2016-02-25T12:57:41Z
dc.date.issued2014-02
dc.description.abstractThis paper describes a new semi-supervised learning algorithm for intra-class clustering (ICC). ICC partitions each class into sub-classes in order to minimize overlap across clusters from different classes. This is achieved by allowing partitioning of a certain class to be assisted by data points from other classes in a context-dependent fashion. The result is that overlap across sub-classes (both within- and across class) is greatly reduced. ICC is particularly useful when combined with algorithms that assume that each class has a unimodal Gaussian distribution (e.g., Linear Discriminant Analysis (LDA), quadratic classifiers), an assumption that is not always true in many real-world situations. ICC can help partition non-Gaussian, multimodal distributions to overcome such a problem. In this sense, ICC works as a preprocessor. Experiments with our ICC algorithm on synthetic data sets and real-world data sets indicated that it can significantly improve the performance of LDA and quadratic classifiers. We expect our approach to be applicable to a broader class of pattern recognition problems where class-conditional densities are significantly non-Gaussian or multi-modal. © 2013 Elsevier Ltd. All rights reserved.
dc.description.sponsorshipThis publication is based in part on work supported by Award No. KUSC1-016-04, made by King Abdullah University of Science and Technology (KAUST).
dc.identifier.citationYu Y, Gutierrez-Osuna R, Choe Y (2014) Context-sensitive intra-class clustering. Pattern Recognition Letters 37: 85–93. Available: http://dx.doi.org/10.1016/j.patrec.2013.04.031.
dc.identifier.doi10.1016/j.patrec.2013.04.031
dc.identifier.issn0167-8655
dc.identifier.journalPattern Recognition Letters
dc.identifier.urihttp://hdl.handle.net/10754/597845
dc.publisherElsevier BV
dc.subjectClustering
dc.subjectICC
dc.subjectIntra-class clustering
dc.subjectLDA
dc.subjectLinear discriminant analysis
dc.subjectSemi-supervised learning
dc.titleContext-sensitive intra-class clustering
dc.typeArticle
display.details.left<span><h5>Type</h5>Article<br><br><h5>Authors</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.author=Yu, Yingwei,equals">Yu, Yingwei</a><br><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.author=Gutierrez-Osuna, Ricardo,equals">Gutierrez-Osuna, Ricardo</a><br><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.author=Choe, Yoonsuck,equals">Choe, Yoonsuck</a><br><br><h5>KAUST Grant Number</h5>KUSC1-016-04<br><br><h5>Date</h5>2014-02</span>
display.details.right<span><h5>Abstract</h5>This paper describes a new semi-supervised learning algorithm for intra-class clustering (ICC). ICC partitions each class into sub-classes in order to minimize overlap across clusters from different classes. This is achieved by allowing partitioning of a certain class to be assisted by data points from other classes in a context-dependent fashion. The result is that overlap across sub-classes (both within- and across class) is greatly reduced. ICC is particularly useful when combined with algorithms that assume that each class has a unimodal Gaussian distribution (e.g., Linear Discriminant Analysis (LDA), quadratic classifiers), an assumption that is not always true in many real-world situations. ICC can help partition non-Gaussian, multimodal distributions to overcome such a problem. In this sense, ICC works as a preprocessor. Experiments with our ICC algorithm on synthetic data sets and real-world data sets indicated that it can significantly improve the performance of LDA and quadratic classifiers. We expect our approach to be applicable to a broader class of pattern recognition problems where class-conditional densities are significantly non-Gaussian or multi-modal. © 2013 Elsevier Ltd. All rights reserved.<br><br><h5>Citation</h5>Yu Y, Gutierrez-Osuna R, Choe Y (2014) Context-sensitive intra-class clustering. Pattern Recognition Letters 37: 85–93. Available: http://dx.doi.org/10.1016/j.patrec.2013.04.031.<br><br><h5>Acknowledgements</h5>This publication is based in part on work supported by Award No. KUSC1-016-04, made by King Abdullah University of Science and Technology (KAUST).<br><br><h5>Publisher</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.publisher=Elsevier BV,equals">Elsevier BV</a><br><br><h5>Journal</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.journal=Pattern Recognition Letters,equals">Pattern Recognition Letters</a><br><br><h5>DOI</h5><a href="https://doi.org/10.1016/j.patrec.2013.04.031">10.1016/j.patrec.2013.04.031</a></span>
kaust.grant.numberKUSC1-016-04
orcid.authorYu, Yingwei
orcid.authorGutierrez-Osuna, Ricardo
orcid.authorChoe, Yoonsuck
Files