Conference
Προβολή σε EDS

A K-Means Variation based on Careful Seeding and Constrained Silhouette Coefficients

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: A K-Means Variation based on Careful Seeding and Constrained Silhouette Coefficients
Συγγραφείς: Libero Nigro, Franco Cicirelli, Francesco Pupo
Πηγή: 2nd International Conference on Advances in Data-driven Computing and Intelligent Systems, 21/09/2023,23/09/2023 ; info:cnr-pdr/source/autori:Libero Nigro, Franco Cicirelli, Francesco Pupo/congresso_nome:2nd International Conference on Advances in Data-driven Computing and Intelligent Systems/congresso_luogo:/congresso_data:21092023,23092023/anno:2023/pagina_da:/pagina_a:/intervallo_pagine
Έτος έκδοσης: 2023
Συλλογή: PUMAlab (ISTI CNR - Consiglio Nazionale delle Ricerche / National Research Council)
Θεματικοί όροι: Clustering, Hartigan & Wong K-Means, Careful seeding, Silhouette coefficients, Compact and well-separated clusters, Java parallel streams
Περιγραφή: K-means is well-known clustering algorithm very often used for its simplicity and efficiency. Its properties have been thoroughly investigated. It emerged that K-means heavily depends on the seeding method used to initialize the cluster centroids and that, besides the seeding procedure, it mainly acts as a local refiner of the centroids and can easily become stuck around a local sub-optimal solution of the objective function cost. As a consequence, K-means is often repeated many times, always starting with a different centroids configuration, to increase the likelihood of finding a clustering solution near the optimal one. In this paper, the Hartigan & Wong variation of K-Means (HWKM) is chosen because of its increased probability to ending up near the optimal solution. HWKM is then enhanced with the use of careful seeding methods and by an incremental technique which constrains the movement of points among clusters according to their Silhouette coefficients. The result is HWKM+ which, through a small number of re-starts, is capable of generating a careful clustering solution with compact and well-separated clusters. The current implementation of HWKM+ rests on Java parallel streams. The paper describes the design and development of HWKM+ and demonstrates its abilities through a series of benchmark and real-world datasets.
Τύπος εγγράφου: conference object
Γλώσσα: English
Relation: info:cnr-pdr/author/matricola:17072/CICIRELLI/FRANCO DOMENICO; http://www.cnr.it/prodotto/i/486107; https://publications.cnr.it/doc/486107
Διαθεσιμότητα: http://www.cnr.it/prodotto/i/486107
https://publications.cnr.it/doc/486107
Rights: info:eu-repo/semantics/restrictedAccess
Αριθμός Καταχώρησης: edsbas.F6227B2C
Βάση Δεδομένων: BASE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: http://www.cnr.it/prodotto/i/486107#
    Name: EDS - BASE (ns324271)
    Category: fullText
    Text: View record from BASE
Header DbId: edsbas
DbLabel: BASE
An: edsbas.F6227B2C
RelevancyScore: 874
AccessLevel: 3
PubType: Conference
PubTypeId: conference
PreciseRelevancyScore: 874.480346679688
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A K-Means Variation based on Careful Seeding and Constrained Silhouette Coefficients
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Libero+Nigro%22">Libero Nigro</searchLink><br /><searchLink fieldCode="AR" term="%22Franco+Cicirelli%22">Franco Cicirelli</searchLink><br /><searchLink fieldCode="AR" term="%22Francesco+Pupo%22">Francesco Pupo</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: 2nd International Conference on Advances in Data-driven Computing and Intelligent Systems, 21/09/2023,23/09/2023 ; info:cnr-pdr/source/autori:Libero Nigro, Franco Cicirelli, Francesco Pupo/congresso_nome:2nd International Conference on Advances in Data-driven Computing and Intelligent Systems/congresso_luogo:/congresso_data:21092023,23092023/anno:2023/pagina_da:/pagina_a:/intervallo_pagine
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2023
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: PUMAlab (ISTI CNR - Consiglio Nazionale delle Ricerche / National Research Council)
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Clustering%22">Clustering</searchLink><br /><searchLink fieldCode="DE" term="%22Hartigan+%26+Wong+K-Means%22">Hartigan & Wong K-Means</searchLink><br /><searchLink fieldCode="DE" term="%22Careful+seeding%22">Careful seeding</searchLink><br /><searchLink fieldCode="DE" term="%22Silhouette+coefficients%22">Silhouette coefficients</searchLink><br /><searchLink fieldCode="DE" term="%22Compact+and+well-separated+clusters%22">Compact and well-separated clusters</searchLink><br /><searchLink fieldCode="DE" term="%22Java+parallel+streams%22">Java parallel streams</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: K-means is well-known clustering algorithm very often used for its simplicity and efficiency. Its properties have been thoroughly investigated. It emerged that K-means heavily depends on the seeding method used to initialize the cluster centroids and that, besides the seeding procedure, it mainly acts as a local refiner of the centroids and can easily become stuck around a local sub-optimal solution of the objective function cost. As a consequence, K-means is often repeated many times, always starting with a different centroids configuration, to increase the likelihood of finding a clustering solution near the optimal one. In this paper, the Hartigan & Wong variation of K-Means (HWKM) is chosen because of its increased probability to ending up near the optimal solution. HWKM is then enhanced with the use of careful seeding methods and by an incremental technique which constrains the movement of points among clusters according to their Silhouette coefficients. The result is HWKM+ which, through a small number of re-starts, is capable of generating a careful clustering solution with compact and well-separated clusters. The current implementation of HWKM+ rests on Java parallel streams. The paper describes the design and development of HWKM+ and demonstrates its abilities through a series of benchmark and real-world datasets.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: conference object
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: info:cnr-pdr/author/matricola:17072/CICIRELLI/FRANCO DOMENICO; http://www.cnr.it/prodotto/i/486107; https://publications.cnr.it/doc/486107
– Name: URL
  Label: Availability
  Group: URL
  Data: http://www.cnr.it/prodotto/i/486107<br />https://publications.cnr.it/doc/486107
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: info:eu-repo/semantics/restrictedAccess
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.F6227B2C
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.F6227B2C
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Clustering
        Type: general
      – SubjectFull: Hartigan & Wong K-Means
        Type: general
      – SubjectFull: Careful seeding
        Type: general
      – SubjectFull: Silhouette coefficients
        Type: general
      – SubjectFull: Compact and well-separated clusters
        Type: general
      – SubjectFull: Java parallel streams
        Type: general
    Titles:
      – TitleFull: A K-Means Variation based on Careful Seeding and Constrained Silhouette Coefficients
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Libero Nigro
      – PersonEntity:
          Name:
            NameFull: Franco Cicirelli
      – PersonEntity:
          Name:
            NameFull: Francesco Pupo
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-locals
              Value: edsbas
          Titles:
            – TitleFull: 2nd International Conference on Advances in Data-driven Computing and Intelligent Systems, 21/09/2023,23/09/2023 ; info:cnr-pdr/source/autori:Libero Nigro, Franco Cicirelli, Francesco Pupo/congresso_nome:2nd International Conference on Advances in Data-driven Computing and Intelligent Systems/congresso_luogo:/congresso_data:21092023,23092023/anno:2023/pagina_da:/pagina_a:/intervallo_pagine
              Type: main
ResultId 1