KNN-SC: Novel Spectral Clustering Algorithm Using k-Nearest Neighbors

Spectral clustering is a well-known graph-theoretic clustering algorithm. Although spectral clustering has several desirable advantages (such as the capability of discovering non-convex clusters and applicability to any data type), it often leads to incorrect clustering results because of high sensi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jeong-Hun Kim, Jong-Hyeok Choi, Young-Ho Park, Carson Kai-Sang Leung, Aziz Nasridinov
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	k-nearest neighbors nearest neighbor graph potential noise detection spectral clustering Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/411c0af5a74c4e0b80e4e417506947de
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:411c0af5a74c4e0b80e4e417506947de
record_format	dspace
spelling	oai:doaj.org-article:411c0af5a74c4e0b80e4e417506947de2021-11-20T00:01:37ZKNN-SC: Novel Spectral Clustering Algorithm Using k-Nearest Neighbors2169-353610.1109/ACCESS.2021.3126854https://doaj.org/article/411c0af5a74c4e0b80e4e417506947de2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9610073/https://doaj.org/toc/2169-3536Spectral clustering is a well-known graph-theoretic clustering algorithm. Although spectral clustering has several desirable advantages (such as the capability of discovering non-convex clusters and applicability to any data type), it often leads to incorrect clustering results because of high sensitivity to noise points. In this study, we propose a robust spectral clustering algorithm known as KNN-SC that can discover exact clusters by decreasing the influence of noise points. To achieve this goal, we present a novel approach that filters out potential noise points by estimating the density difference between data points using <inline-formula> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula>-nearest neighbors. In addition, we introduce a novel method for generating a similarity graph in which various densities of data points are effectively represented by expanding the nearest neighbor graph. Experimental results on synthetic and real-world datasets demonstrate that KNN-SC achieves significant performance improvement over many state-of-the-art spectral clustering algorithms.Jeong-Hun KimJong-Hyeok ChoiYoung-Ho ParkCarson Kai-Sang LeungAziz NasridinovIEEEarticlek-nearest neighborsnearest neighbor graphpotential noise detectionspectral clusteringElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 152616-152627 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	k-nearest neighbors nearest neighbor graph potential noise detection spectral clustering Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	k-nearest neighbors nearest neighbor graph potential noise detection spectral clustering Electrical engineering. Electronics. Nuclear engineering TK1-9971 Jeong-Hun Kim Jong-Hyeok Choi Young-Ho Park Carson Kai-Sang Leung Aziz Nasridinov KNN-SC: Novel Spectral Clustering Algorithm Using k-Nearest Neighbors
description	Spectral clustering is a well-known graph-theoretic clustering algorithm. Although spectral clustering has several desirable advantages (such as the capability of discovering non-convex clusters and applicability to any data type), it often leads to incorrect clustering results because of high sensitivity to noise points. In this study, we propose a robust spectral clustering algorithm known as KNN-SC that can discover exact clusters by decreasing the influence of noise points. To achieve this goal, we present a novel approach that filters out potential noise points by estimating the density difference between data points using <inline-formula> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula>-nearest neighbors. In addition, we introduce a novel method for generating a similarity graph in which various densities of data points are effectively represented by expanding the nearest neighbor graph. Experimental results on synthetic and real-world datasets demonstrate that KNN-SC achieves significant performance improvement over many state-of-the-art spectral clustering algorithms.
format	article
author	Jeong-Hun Kim Jong-Hyeok Choi Young-Ho Park Carson Kai-Sang Leung Aziz Nasridinov
author_facet	Jeong-Hun Kim Jong-Hyeok Choi Young-Ho Park Carson Kai-Sang Leung Aziz Nasridinov
author_sort	Jeong-Hun Kim
title	KNN-SC: Novel Spectral Clustering Algorithm Using k-Nearest Neighbors
title_short	KNN-SC: Novel Spectral Clustering Algorithm Using k-Nearest Neighbors
title_full	KNN-SC: Novel Spectral Clustering Algorithm Using k-Nearest Neighbors
title_fullStr	KNN-SC: Novel Spectral Clustering Algorithm Using k-Nearest Neighbors
title_full_unstemmed	KNN-SC: Novel Spectral Clustering Algorithm Using k-Nearest Neighbors
title_sort	knn-sc: novel spectral clustering algorithm using k-nearest neighbors
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/411c0af5a74c4e0b80e4e417506947de
work_keys_str_mv	AT jeonghunkim knnscnovelspectralclusteringalgorithmusingknearestneighbors AT jonghyeokchoi knnscnovelspectralclusteringalgorithmusingknearestneighbors AT younghopark knnscnovelspectralclusteringalgorithmusingknearestneighbors AT carsonkaisangleung knnscnovelspectralclusteringalgorithmusingknearestneighbors AT aziznasridinov knnscnovelspectralclusteringalgorithmusingknearestneighbors
_version_	1718419828162691072

KNN-SC: Novel Spectral Clustering Algorithm Using k-Nearest Neighbors

Ejemplares similares