A new fuzzy k-nearest neighbor classifier based on the Bonferroni mean

•Two new variants of the k-nearest neighbor classifier are introduced, both use the Bonferroni mean.•The new variants are less sensitive to class imbalances than their original counterparts.•The proposed methods produce improved classification accuracy compared to benchmarks•The methods achieve the...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Pattern recognition letters Jg. 140; S. 172 - 178
Hauptverfasser:	Mailagaha Kumbure, Mahinda, Luukka, Pasi, Collan, Mikael
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Amsterdam Elsevier B.V 01.12.2020 Elsevier Science Ltd
Schlagworte:	Bonferroni mean Classification Classifiers Datasets Fuzzy k-nearest neighbor K-nearest neighbors algorithm Local means Performance measures Bonferroni mean Local means Performance measures Fuzzy k-nearest neighbor Classification
ISSN:	0167-8655, 1872-7344
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!