Fuzzy parameterized fuzzy soft k-nearest neighbor classifier

Basit Öğe Kaydı
dc.authoridErkan, Ugur/0000-0002-2481-0230
dc.authoridEnginoglu, Serdar/0000-0002-7188-9893
dc.contributor.authorMemis, S.
dc.contributor.authorEnginoglu, S.
dc.contributor.authorErkan, U.
dc.date.accessioned2025-01-27T20:57:53Z
dc.date.available2025-01-27T20:57:53Z
dc.date.issued2022
dc.departmentÇanakkale Onsekiz Mart Üniversitesi
dc.description.abstractIn this paper, we propose a new kNN algorithm, i.e., Fuzzy Parameterized Fuzzy Soft kNN (FPFS-kNN), based on multiple pseudo-metrics of fuzzy parameterized fuzzy soft matrices (fpfs-matrices). FPFS-kNN can consider the impacts of parameters on classification using pseudo-metrics of fpfs-matrices - a new concept. Furthermore, FPFS-kNN detects the nearest neighbors for each pseudo-metric and classifies data applying the aforementioned multiple distance functions. To demonstrate the classification success of the proposed method, we carry out an experimental study using 35 UCI datasets and comparing it with the state-of-the-art kNN-based and non-kNN-based algorithms. All the methods are trained and tested for ten runs through five-fold cross-validation. We then compare the results of FPFS-kNN with those of the others in terms of the most frequently used measures, such as accuracy (ACC), precision (PRE), recall (REC), micro F-score (MICF), and macro F-score (MACF). Afterward, we pro-vide a statistical evaluation of the results. Experimental and statistical results manifest that the proposed FPFS-kNN, utilized Pearson's correlation coefficient and denoted by FPFS-kNN (P), outperforms the state-of-the-art kNN-based algorithms in 24 of 35 datasets in terms of each considered measure and 31 of 35 datasets in terms of accuracy measure. Besides, the results showed that FPFS-kNN (P) performs better than the others for 29 datasets in terms of ACC and MICF rates, and 24 datasets in terms of PRE, REC and MACF rates. Finally, we discuss FPFS-kNN for further research.(c) 2022 Elsevier B.V. All rights reserved.
dc.description.sponsorshipScientific and Technological Research Council of Turkey (TUBI_TAK); [1649B031905299]
dc.description.sponsorshipThis research study was granted 2211-C Domestic Doctoral Fellowship for Priority Areas by the Scientific and Technological Research Council of Turkey (TUBI_TAK) under Grant 1649B031905299.
dc.identifier.doi10.1016/j.neucom.2022.05.041
dc.identifier.endpage378
dc.identifier.issn0925-2312
dc.identifier.issn1872-8286
dc.identifier.scopus2-s2.0-85131222231
dc.identifier.scopusqualityQ1
dc.identifier.startpage351
dc.identifier.urihttps://doi.org/10.1016/j.neucom.2022.05.041
dc.identifier.urihttps://hdl.handle.net/20.500.12428/26540
dc.identifier.volume500
dc.identifier.wosWOS:000809656200015
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherElsevier
dc.relation.ispartofNeurocomputing
dc.relation.publicationcategoryinfo:eu-repo/semantics/openAccess
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_WoS_20250125
dc.subjectFuzzy sets
dc.subjectSoft sets
dc.subjectfpfs-matrices
dc.subjectDistance measure
dc.subjectSupervised learning
dc.titleFuzzy parameterized fuzzy soft k-nearest neighbor classifier
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu