Package elki.outlier.distance

Class DBOutlierScore<O>

  • Type Parameters:
    O - Database object type
    All Implemented Interfaces:
    Algorithm, OutlierAlgorithm
    @Title("Distance Based Outlier Score")
@Description("Generalization of the original DB-Outlier approach to a ranking method, by turning the fraction parameter into the output value.")
@Reference(prefix="Generalization of a method proposed in",
           authors="E. M. Knorr, R. T. Ng",
           title="Algorithms for Mining Distance-Based Outliers in Large Datasets",
           booktitle="Proc. Int. Conf. on Very Large Databases (VLDB\'98)",
           url="http://www.vldb.org/conf/1998/p392.pdf",
           bibkey="DBLP:conf/vldb/KnorrN98")
public class DBOutlierScore<O>
extends AbstractDBOutlier<O>
    Compute percentage of neighbors in the given neighborhood with size d.

    Generalization of the DB Outlier Detection by using the fraction as outlier score thus eliminating this parameter and turning the method into a ranking method instead of a labelling one.

    Reference:

    E.M. Knorr, R. T. Ng:
    Algorithms for Mining Distance-Based Outliers in Large Datasets,
    In: Proc. Int. Conf. on Very Large Databases (VLDB'98)

    Since:
    0.3
    Author:
    Lisa Reichert

    • Field Detail

      • LOG

        private static final Logging LOG
        The logger for this class.

    • Constructor Detail

      • DBOutlierScore

        public DBOutlierScore​(Distance<? super O> distance,
                      double d)
        Constructor with parameters.
        Parameters:
        distance - Distance function
        d - distance radius parameter