Hybridization of K Nearest Neighbors Classifier with Cuckoo Search Algorithm

Katarzyna Prokop

Hybridization of K Nearest Neighbors Classifier with Cuckoo Search Algorithm

Katarzyna Prokop

Department of Artificial Intelligence Modelling (RMS/RMS2)

Research output: Contribution to journal › Conference article › peer-review

Abstract

Artificial intelligence methods are one of the most used algorithms in big data and Internet of Things solutions. Therefore, a very important aspect is to create new algorithms and improve existing ones. In this paper, the proposition of a hybrid method for classifying elements in certain datasets is presented. The proposed method joins properties of K Nearest Neighbors Algorithm (a classifier) and Cuckoo Search Algorithm (a heuristic algorithm). The proposed model was presented, tested, and discussed on a selected dataset of Iris Flowers. The effectiveness of the method is compared for different variants of input parameters to show the efficiency of the proposition.

Original language	English
Pages (from-to)	18-25
Number of pages	8
Journal	CEUR Workshop Proceedings
Volume	3118
Publication status	Published - 2021
Event	2021 International Conference of Yearly Reports on Informatics, Mathematics and Engineering, ICYRIME 2021 - Virtual, Online Duration: 9 Jul 2021 → …

Keywords

clustering
data classification
heuristic
knn

ASJC Scopus subject areas

General Computer Science

Cite this

@article{680316f355d5478fb06f6072d8fe20c6,

title = "Hybridization of K Nearest Neighbors Classifier with Cuckoo Search Algorithm",

abstract = "Artificial intelligence methods are one of the most used algorithms in big data and Internet of Things solutions. Therefore, a very important aspect is to create new algorithms and improve existing ones. In this paper, the proposition of a hybrid method for classifying elements in certain datasets is presented. The proposed method joins properties of K Nearest Neighbors Algorithm (a classifier) and Cuckoo Search Algorithm (a heuristic algorithm). The proposed model was presented, tested, and discussed on a selected dataset of Iris Flowers. The effectiveness of the method is compared for different variants of input parameters to show the efficiency of the proposition.",

keywords = "clustering, data classification, heuristic, knn",

author = "Katarzyna Prokop",

note = "Publisher Copyright: {\textcopyright} 2021 Copyright for this paper by its authors; 2021 International Conference of Yearly Reports on Informatics, Mathematics and Engineering, ICYRIME 2021 ; Conference date: 09-07-2021",

year = "2021",

language = "English",

volume = "3118",

pages = "18--25",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

}

TY - JOUR

T1 - Hybridization of K Nearest Neighbors Classifier with Cuckoo Search Algorithm

AU - Prokop, Katarzyna

PY - 2021

Y1 - 2021

N2 - Artificial intelligence methods are one of the most used algorithms in big data and Internet of Things solutions. Therefore, a very important aspect is to create new algorithms and improve existing ones. In this paper, the proposition of a hybrid method for classifying elements in certain datasets is presented. The proposed method joins properties of K Nearest Neighbors Algorithm (a classifier) and Cuckoo Search Algorithm (a heuristic algorithm). The proposed model was presented, tested, and discussed on a selected dataset of Iris Flowers. The effectiveness of the method is compared for different variants of input parameters to show the efficiency of the proposition.

AB - Artificial intelligence methods are one of the most used algorithms in big data and Internet of Things solutions. Therefore, a very important aspect is to create new algorithms and improve existing ones. In this paper, the proposition of a hybrid method for classifying elements in certain datasets is presented. The proposed method joins properties of K Nearest Neighbors Algorithm (a classifier) and Cuckoo Search Algorithm (a heuristic algorithm). The proposed model was presented, tested, and discussed on a selected dataset of Iris Flowers. The effectiveness of the method is compared for different variants of input parameters to show the efficiency of the proposition.

KW - clustering

KW - data classification

KW - heuristic

KW - knn

UR - https://www.scopus.com/pages/publications/85128500046

M3 - Conference article

AN - SCOPUS:85128500046

SN - 1613-0073

VL - 3118

SP - 18

EP - 25

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

T2 - 2021 International Conference of Yearly Reports on Informatics, Mathematics and Engineering, ICYRIME 2021

Y2 - 9 July 2021

ER -

Hybridization of K Nearest Neighbors Classifier with Cuckoo Search Algorithm

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this