Please use this identifier to cite or link to this item: https://ruomo.lib.uom.gr/handle/7000/1167
Full metadata record
DC FieldValueLanguage
dc.contributor.authorXouveroudis, Konstantinos-
dc.contributor.authorOugiaroglou, Stefanos-
dc.contributor.authorEvangelidis, Georgios-
dc.contributor.authorDervos, Dimitris A.-
dc.date.accessioned2022-08-26T07:35:13Z-
dc.date.available2022-08-26T07:35:13Z-
dc.date.issued2021-10-08-
dc.identifier10.1109/IISA52424.2021.9555514en_US
dc.identifier.isbn978-1-6654-0032-9en_US
dc.identifier.urihttps://doi.org/10.1109/IISA52424.2021.9555514en_US
dc.identifier.urihttps://ruomo.lib.uom.gr/handle/7000/1167-
dc.description.abstractInstance-based classifiers become inefficient when the size of their training dataset or model is large. Therefore, they are usually applied in conjunction with a Data Reduction Technique that collects prototypes from the available training data. The set of prototypes is called the condensing set and has the benefit of low computational cost during classification, while, at the same time, accuracy is not negatively affected. In case of imbalanced training data, the number of prototypes collected for the minority (rare) classes may be insufficient. Even worse, the rare classes may be eliminated. This paper presents three methods that preserve the rare classes when data reduction is applied. Two of the methods apply data reduction only on the instances that belong to common classes and avoid costly under-sampling or over-sampling procedures that deal with class imbalances. The third method utilizes SMOTE over-sampling before data reduction. The three methods were tested by conducting experiments on twelve imbalanced datasets. Experimental results reveal high recall and very good reduction rates.en_US
dc.language.isoenen_US
dc.rightsAttribution-ShareAlike 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-sa/4.0/*
dc.subjectFRASCATI::Natural sciences::Computer and information sciencesen_US
dc.subject.otherk-NN Classificationen_US
dc.subject.otherImbalanced dataen_US
dc.subject.otherPrototype Selectionen_US
dc.subject.otherPrototype Generationen_US
dc.subject.otherSMOTEen_US
dc.subject.otherRare classesen_US
dc.titlePrototype Selection and Generation with Minority Classes Preservationen_US
dc.typeConference Paperen_US
dc.contributor.departmentΤμήμα Εφαρμοσμένης Πληροφορικήςen_US
local.identifier.firstpage1en_US
local.identifier.lastpage8en_US
local.identifier.volumetitle2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA)en_US
Appears in Collections:Department of Applied Informatics

Files in This Item:
File Description SizeFormat 
2021_IISA_rare_classes.pdf282,57 kBAdobe PDFThumbnail
View/Open


This item is licensed under a Creative Commons License Creative Commons