Class LOCI<O>

  • Type Parameters:
    O - Object type
    All Implemented Interfaces:
    Algorithm, OutlierAlgorithm

    @Title("LOCI: Fast Outlier Detection Using the Local Correlation Integral")
    @Description("Algorithm to compute outliers based on the Local Correlation Integral")
    @Reference(authors="S. Papadimitriou, H. Kitagawa, P. B. Gibbons, C. Faloutsos",
               title="LOCI: Fast Outlier Detection Using the Local Correlation Integral",
               booktitle="Proc. 19th IEEE Int. Conf. on Data Engineering (ICDE \'03)",
               url="https://doi.org/10.1109/ICDE.2003.1260802",
               bibkey="DBLP:conf/icde/PapadimitriouKGF03")
    public class LOCI<O>
    extends java.lang.Object
    implements OutlierAlgorithm
    Fast Outlier Detection Using the "Local Correlation Integral".

    Exact implementation only, not aLOCI. See ALOCI.

    Outlier detection using multiple epsilon neighborhoods.

    This implementation has O(n3 log n) runtime complexity!

    Reference:

    S. Papadimitriou, H. Kitagawa, P. B. Gibbons, C. Faloutsos:
    LOCI: Fast Outlier Detection Using the Local Correlation Integral.
    In: Proc. 19th IEEE Int. Conf. on Data Engineering (ICDE '03)

    Since:
    0.2
    Author:
    Erich Schubert
    • Field Detail

      • LOG

        private static final Logging LOG
        The logger for this class.
      • distance

        private Distance<? super O> distance
        Distance function used.
      • rmax

        private double rmax
        Maximum radius.
      • nmin

        private int nmin
        Minimum neighborhood size.
      • alpha

        private double alpha
        Scaling of averaging neighborhood.
    • Constructor Detail

      • LOCI

        public LOCI​(Distance<? super O> distance,
                    double rmax,
                    int nmin,
                    double alpha)
        Constructor.
        Parameters:
        distance - Distance function
        rmax - Maximum radius
        nmin - Minimum neighborhood size
        alpha - Alpha value
    • Method Detail

      • getInputTypeRestriction

        public TypeInformation[] getInputTypeRestriction()
        Description copied from interface: Algorithm
        Get the input type restriction used for negotiating the data query.
        Specified by:
        getInputTypeRestriction in interface Algorithm
        Returns:
        Type restriction
      • run

        public OutlierResult run​(Relation<O> relation)
        Run the algorithm
        Parameters:
        relation - Relation to process
        Returns:
        Outlier result
      • precomputeInterestingRadii

        protected void precomputeInterestingRadii​(DBIDs ids,
                                                  RangeSearcher<DBIDRef> rangeQuery,
                                                  WritableDataStore<LOCI.DoubleIntArrayList> interestingDistances)
        Preprocessing step: determine the radii of interest for each point.
        Parameters:
        ids - IDs to process
        rangeQuery - Range query
        interestingDistances - Distances of interest