Data mining algorithms

The following data-mining algorithms are included in the ELKI 0.4 release.
For literature references, click on the individual algorithms or the references overview in the JavaDoc documentation. See also RelatedPublications

• Clustering Algorithms:
  • DBSCAN
  • DeLiClu
  • EM
  • KMeans
  • OPTICSXi
  • OPTICS
  • SLINK
  • SNNClustering
  • Correlation clustering algorithms:
    • CASH
    • COPAC
    • ERiC
    • FourC
    • HiCO
    • ORCLUS
  • Subspace (axis-parallel) clustering algorithms:
    • CLIQUE
    • DiSH
    • HiSC
    • PreDeCon
    • PROCLUS
    • SUBCLU
  • Trivial clustering algorithms:
    • ByLabelClustering
    • ByLabelHierarchicalClustering
    • TrivialAllInOne
    • TrivialAllNoise
• Outlier Detection
  • ABOD
  • AggarwalYuEvolutionary
  • AggarwalYuNaive
  • DBOutlierDetection
  • DBOutlierScore
  • EMOutlier
  • GaussianModel
  • GaussianUniformMixture
  • INFLO
  • KNNOutlier
  • KNNWeightOutlier
  • LDOF
  • LOCI
  • LOF
  • LoOP
  • OPTICSOF
  • ReferenceBasedOutlierDetection
  • SOD
  • OnlineLOF
  • Spatial outlier detection:
    • CTLuGLSBackwardSearchAlgorithm
    • CTLuMeanMultipleAttributes
    • CTLuMedianAlgorithm
    • CTLuMedianMultipleAttributes
    • CTLuMoranScatterplotOutlier
    • CTLuRandomWalkEC
    • CTLuScatterplotOutlier
    • CTLuZTestOutlier
    • SLOM
    • SOF
    • TrimmedMeanApproach
  • Meta outlier methods:
    • ExternalDoubleOutlierScore
    • FeatureBagging
    • RescaleMetaOutlierAlgorithm
  • Trivial outlier methods:
    • ByLabelOutlier
    • TrivialAllOutlier
    • TrivialNoOutlier
• APRIORI
• DependencyDerivator
• KNNDistanceOrder
• KNNJoin
• MaterializeDistances
• Data set statistics:
  • EvaluateRankingQuality
  • RankingQualityHistogram
  • DistanceStatisticsWithClasses