ANDClust: An Adaptive Neighborhood Distance-Based Clustering Algorithm to Cluster Varying Density and/or Neck-Typed Datasets

Basit Öğe Kaydı
dc.authoridSENOL, Ali/0000-0003-0364-2837
dc.contributor.authorSenol, Ali
dc.date.accessioned2025-03-18T12:27:46Z
dc.date.available2025-03-17T12:27:46Z
dc.date.issued2024
dc.departmentTarsus Üniversitesi
dc.description.abstractAlthough density-based clustering algorithms can successfully define clusters in arbitrary shapes, they encounter issues if the dataset has varying densities or neck-typed clusters due to the requirement for precise distance parameters, such as eps parameter of DBSCAN. These approches assume that data density is homogenous, but this is rarely the case in practice. In this study, a new clustering algorithm named ANDClust (Adaptive Neighborhood Distance-based Clustering Algorithm) is propoesed to handle datasets with varying density and/or neck-typed clusters. The algorithm consists of three parts. The first part uses Multivariate Kernel Density Estimation (MulKDE) to find the dataset's peak points, which are the start points for the Minimum Spanning Tree (MST) to construct clusters in the second part. Lastly, an Adaptive Neighborhood Distance (AND) ratio is used to weigh the distance between the data pairs. This method enables this approach to support inter-cluster and intra-cluster density varieties by acting as if the distance parameter differs for each data of the dataset. ANDClust on synthetic and real datasets are tested to reveal its efficiency. The algorithm shows superior clustering quality in a good run-time compared to its competitors. Moreover, ANDClust could effectively define clusters of arbitrary shapes and process high-dimensional, imbalanced datasets may have outliers. This study proposes a new clustering algorithm named ANDClust to handle datasets with varying density and neck-typed clusters. In the proposed algorithm, an Adaptive Neighborhood Distance (AND) ratio is used to weigh the distance between the data pairs as if it differs for each data pair in the dataset. This method makes the approach support not only the varying density among clusters but also the varying density inside the cluster. image
dc.identifier.doi10.1002/adts.202301113
dc.identifier.issn2513-0390
dc.identifier.issue4
dc.identifier.scopus2-s2.0-85186949835
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1002/adts.202301113
dc.identifier.urihttps://hdl.handle.net/20.500.13099/2427
dc.identifier.volume7
dc.identifier.wosWOS:001180736200001
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorSenol, Ali
dc.language.isoen
dc.publisherWiley-V C H Verlag Gmbh
dc.relation.ispartofAdvanced Theory and Simulations
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WOS_20250316
dc.subjectadaptive neighborhood distance
dc.subjectclustering
dc.subjectminimum spanning tree
dc.subjectvarying density
dc.titleANDClust: An Adaptive Neighborhood Distance-Based Clustering Algorithm to Cluster Varying Density and/or Neck-Typed Datasets
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu