Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Classifier fusion approaches for diagnostic cancer models

Zervakis Michalis, Dimou Ioannis, G.C. Manikis

Simple record

URIhttp://purl.tuc.gr/dl/dias/FA7A92E8-8C81-4CE7-B0C8-B835AE977FF8-
Identifierhttps://doi.org/10.1109/IEMBS.2006.260778-
Languageen-
Extent4 pagesen
TitleClassifier fusion approaches for diagnostic cancer modelsen
CreatorZervakis Michalisen
CreatorΖερβακης Μιχαληςel
CreatorDimou Ioannisen
CreatorΔημου Ιωαννηςel
CreatorG.C. Manikisen
PublisherInstitute of Electrical and Electronics Engineersen
Content SummaryClassifier ensembles have produced promising results, improving accuracy, confidence and most importantly feature space coverage in many practical applications. The recent trend is to move from heuristic combinations of classifiers to more statistically sound integrated schemes to produce quantifiable results as far as error bounds and overall generalization capability are concerned. In this study, we are evaluating the use of an ensemble of 8 classifiers based on 15 different fusion strategies on two medical problems. We measure the base classifiers correlation using 11 commonly accepted metrics and provide the grounds for choosing an improved hyper-classifieren
Type of ItemΑφίσα σε Συνέδριοel
Type of ItemConference Posteren
Licensehttp://creativecommons.org/licenses/by/4.0/en
Date of Item2015-10-23-
Date of Publication2006-
SubjectClinical laboratory techniciansen
SubjectMedical laboratory techniciansen
Subjectmedical technologistsen
Subjectclinical laboratory techniciansen
Subjectmedical laboratory techniciansen
Bibliographic CitationI.N. Dimou, G.C. Manikis, M.E. Zervakis," Classifier fusion approaches for diagnostic cancer models ,"in 2006 28th Annual Intern. Conf. of the IEEEE eng in Medicine and Biol. Society, EMBS,pp.5334 - 5337.doi:10.1109/IEMBS.2006.260778en

Services

Statistics

 

Copyright © DIAS 2013