Gelişmiş Arama

Basit öğe kaydını göster

dc.contributor.authorTulum, Gokalpen_US
dc.contributor.authorArtug, N. Tugrulen_US
dc.contributor.authorBolat, Bulenten_US
dc.date.accessioned2019-10-29T17:32:53Z
dc.date.available2019-10-29T17:32:53Z
dc.date.issued2013
dc.identifier.isbn978-1-4799-0661-1; 978-1-4799-0659-8
dc.identifier.urihttps://hdl.handle.net/20.500.12294/1860
dc.identifier.urihttp://dx.doi.org/10.1109/INISTA.2013.6577634
dc.descriptionIEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA) --JUN 19-21, 2013 -- BULGARIAen_US
dc.descriptionWOS: 000332186500020en_US
dc.description.abstractIn this work, four human activities were classified by using multi layer perceptron and k-nearest neighbours algorithm. Due to mass amount of data, two different feature selection methods, which are ReliefF and t-score, were applied to the data. The best result is obtained as 97.6% with 51 features selected by ReliefF.en_US
dc.description.sponsorshipIEEE, Bulgarian Sci Acad, Bulgarian Acad Sci, Inst Informat & Commun Technologies, IEEE Bulgarian Secten_US
dc.language.isoengen_US
dc.publisherIEEEen_US
dc.relation.ispartof2013 IEEE INTERNATIONAL SYMPOSIUM ON INNOVATIONS IN INTELLIGENT SYSTEMS AND APPLICATIONS (IEEE INISTA)en_US
dc.identifier.doi10.1109/INISTA.2013.6577634en_US
dc.identifier.doi10.1109/INISTA.2013.6577634
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectFeature selectionen_US
dc.subjectReliefFen_US
dc.subjectt-scoreen_US
dc.subjecthuman activity detectionen_US
dc.titlePerformance Evaluation of Feature Selection Algorithms on Human Activity Classificationen_US
dc.typeconferenceObjecten_US
dc.departmentİstanbul Arel Üniversitesien_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.department-temp[Tulum, Gokalp] Yeni Yuzyil Univ, Elect & Elect Engn, Istanbul, Turkey -- [Artug, N. Tugrul] Istanbul Arel Univ, Elect & Elect Engn, Istanbul, Turkey -- [Bolat, Bulent] Yildiz Tech Univ, Elect & Commun Engn, Istanbul, Turkeyen_US


Bu öğenin dosyaları:

Thumbnail

Bu öğe aşağıdaki koleksiyon(lar)da görünmektedir.

Basit öğe kaydını göster