Goowe : geometrically optimum and online-weighted ensemble classifier for evolving data streams

buir.advisorCan, Fazlı
dc.contributor.authorAsl-Bonab, Hamed Rezanejad
dc.date.accessioned2016-08-29T10:35:50Z
dc.date.available2016-08-29T10:35:50Z
dc.date.copyright2016-07
dc.date.issued2016-07
dc.date.submitted2016-08-26
dc.departmentDepartment of Computer Engineeringen_US
dc.descriptionCataloged from PDF version of article.en_US
dc.descriptionThesis (M.S.): Bilkent University, Department of Computer Engineering, İhsan Doğramacı Bilkent University, 2016.en_US
dc.descriptionIncludes bibliographical references (leaves 50-55).en_US
dc.description.abstractDesigning adaptive classifiers for an evolving data stream is a challenging task due to its size and dynamically changing nature. Combining individual classifiers in an online setting, the ensemble approach, is one of the well-known solutions. It is possible that a subset of classifiers in the ensemble outperforms others in a timevarying fashion. However, optimum weight assignment for component classifiers is a problem which is not yet fully addressed in online evolving environments. We propose a novel data stream ensemble classifier, called Geometrically Optimum and Online-Weighted Ensemble (GOOWE), which assigns optimum weights to the component classifiers using a sliding window containing the most recent data instances. We map vote scores of individual classifiers and true class labels into a spatial environment. Based on the Euclidean distance between vote scores and ideal-points, and using the linear least squares (LSQ) solution, we present a novel dynamic and online weighting approach. While LSQ is used for batch mode ensemble classifiers, it is the first time that we adapt and use it for online environments by providing a spatial modeling of online ensembles. In order to show the robustness of the proposed algorithm, we use real-world datasets and synthetic data generators using the MOA libraries. We compare our results with 8 state-ofthe- art ensemble classifiers in a comprehensive experimental environment. Our experiments show that GOOWE provides improved reactions to different types of concept drift compared to our baselines. The statistical tests indicate a significant improvement in accuracy, with conservative time and memory requirements.en_US
dc.description.degreeM.S.en_US
dc.description.statementofresponsibilityby Hamed Rezanejad Asl-Bonab.en_US
dc.embargo.release2018-08-25
dc.format.extentxi, 55 leaves : illustrations (some color), charts.en_US
dc.identifier.itemidB153995
dc.identifier.urihttp://hdl.handle.net/11693/32179
dc.language.isoEnglishen_US
dc.publisherBilkent Universityen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectEnsemble classi eren_US
dc.subjectConcept driften_US
dc.subjectEvolving data streamen_US
dc.subjectDynamic weightingen_US
dc.subjectGeometry of votingen_US
dc.subjectLeast squaresen_US
dc.subjectSpatial modeling for online ensemblesen_US
dc.titleGoowe : geometrically optimum and online-weighted ensemble classifier for evolving data streamsen_US
dc.title.alternativeGoowe : değişen veri akışları için geometrik açıdan optimum ağırlıklı çevrim içi çoklu sınıflandırıcıen_US
dc.typeThesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
myThesis-finalPDF-9Aug2016.pdf
Size:
996.48 KB
Format:
Adobe Portable Document Format
Description:
Full printable version
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: