View source for Publications:A feature selection technique for generation of classification committees and its application to categorization of laryngeal images

<div style='display: none'>
== Do not edit this section ==
</div>
{{PublicationSetupTemplate|Author=Marija Bacauskiene, Antanas Verikas, Adas Gelzinis, Donatas Valincius
|PID=235710
|Name=Bacauskiene, Marija (Department of Applied Electronics, Kaunas University of Technology, Lithuania );Verikas, Antanas [av] (Högskolan i Halmstad [2804], Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE) [3905], Halmstad Embedded and Intelligent Systems Research (EIS) [3938]);Gelzinis, Adas ( Department of Applied Electronics, Kaunas University of Technology, Lithuania );Valincius, Donatas ( Department of Applied Electronics, Kaunas University of Technology, Lithuania )
|Title=A feature selection technique for generation of classification committees and its application to categorization of laryngeal images
|PublicationType=Journal Paper
|ContentType=Refereegranskat
|Language=eng
|Journal=Pattern Recognition
|JournalISSN=0031-3203
|Status=published
|Volume=42
|Issue=5
|HostPublication=
|Conference=
|StartPage=645
|EndPage=654
|Year=2009
|Edition=
|Pages=
|City=New York
|Publisher=Pergamon Press
|Series=
|SeriesISSN=
|ISBN=
|Urls=
|ISRN=
|DOI=http://dx.doi.org/10.1016/j.patcog.2008.08.025
|ISI=000263431200006
|PMID=
|ScopusId=2-s2.0-58249093836
|NBN=urn:nbn:se:hh:diva-100
|LocalId=
|ArchiveNumber=
|Keywords=Feedfoward neural networks;Feature subset-selection;Support vector machine;Evolutionary ensembles;Negative correlation;Genetic algorithms;Classifiers;Recognition;Accuracy;Systems
|Categories=Data- och informationsvetenskap (102)
|ResearchSubjects=
|Projects=
|Notes=
|Abstract=<p>This paper is concerned with a two phase procedure to select salient features (variables) for classification committees. Both filter and wrapper approaches to feature selection are combined in this work. In the first phase, definitely redundant features are eliminated based on the paired t-test. The test compares the saliency of the candidate and the noise features. In the second phase, the genetic search is employed. The search integrates the steps of training, aggregation of committee members, selection of hyper-parameters, and selection of salient features into the same learning process. A small number of genetic iterations needed to find a solution is the characteristic feature of the genetic search procedure developed. The experimental tests performed on five real-world problems have shown that significant improvements in Classification accuracy can be obtained in a small number of iterations if compared to the case of using all the features available.</p>
|Opponents=
|Supervisors=
|Examiners=
|Patent=
|ThesisLevel=
|Credits=
|Programme=
|Subject=
|Uppsok=
|DefencePlace=
|DefenceLanguage=
|DefenceDate=
|CreatedDate=2009-09-17
|PublicationDate=2009-09-17
|LastUpdated=2013-05-06
|diva=http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:235710}}
<div style='display: none'>

== Keep all hand-made modifications below ==
</div>{{PublicationDisplayTemplate}}