Publication:
An evolutionary parallel multiobjective feature selection framework

cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.department38e1f5a7-c9a2-4bf5-bb0e-144731e3aa39
cris.virtualsource.orcid38e1f5a7-c9a2-4bf5-bb0e-144731e3aa39
dc.contributor.affiliationTurk Hava Kurumu University; Turkish Aeronautical Association; Middle East Technical University
dc.contributor.authorKiziloz, Hakan Ezgi; Deniz, Ayca
dc.date.accessioned2024-06-25T11:45:11Z
dc.date.available2024-06-25T11:45:11Z
dc.date.issued2021
dc.description.abstractFeature selection has become an indispensable preprocessing step in data mining problems as high amount of data become prevalent with the advances in technology. The objective of feature selection is twofold: reducing data amount and improving learning performance. In this study, we leverage the multi-core nature of a regular PC to build a robust framework for feature selection. This framework executes the feature selection algorithm on four processors, in parallel. As per the No Free Lunch Theorem, we facilitate 40 different execution settings for the processors by employing two multiobjective selection algorithms, four initial population generation methods, and five machine learning techniques. Besides, we introduce six setting selection schemes to decide the most fruitful setting for each processor. We carry out extensive experiments on 11 UCI benchmark datasets and analyze the results with statistical tests. Finally, we compare our proposed method with state-of-the-art studies and record remarkable improvement in terms of maximum accuracy.
dc.description.doi10.1016/j.cie.2021.107481
dc.description.pages13
dc.description.researchareasComputer Science; Engineering
dc.description.urihttp://dx.doi.org/10.1016/j.cie.2021.107481
dc.description.volume159
dc.description.woscategoryComputer Science, Interdisciplinary Applications; Engineering, Industrial
dc.identifier.issn0360-8352
dc.identifier.urihttps://acikarsiv.thk.edu.tr/handle/123456789/1244
dc.language.isoEnglish
dc.publisherPERGAMON-ELSEVIER SCIENCE LTD
dc.relation.journalCOMPUTERS & INDUSTRIAL ENGINEERING
dc.subjectFeature selection; Multiobjective optimization; Parallel processing; Evolutionary computation
dc.subjectGENETIC ALGORITHM; OPTIMIZATION; CLASSIFICATION
dc.titleAn evolutionary parallel multiobjective feature selection framework
dc.typeArticle
dspace.entity.typePublication

Files