de.lmu.ifi.dbs.elki.algorithm.outlier.spatial
Class CTLuMoranScatterplotOutlier<N>

java.lang.Object
  de.lmu.ifi.dbs.elki.algorithm.AbstractAlgorithm<OutlierResult>
      de.lmu.ifi.dbs.elki.algorithm.outlier.spatial.AbstractNeighborhoodOutlier<N>
          de.lmu.ifi.dbs.elki.algorithm.outlier.spatial.CTLuMoranScatterplotOutlier<N>

Type Parameters:

N - Neighborhood type

All Implemented Interfaces:

Algorithm, OutlierAlgorithm, InspectionUtilFrequentlyScanned, Parameterizable

@Title(value="Moran Scatterplot Outlier")
@Description(value="Spatial Outlier detection based on the standardized deviation from the local means.")
@Reference(authors="S. Shekhar and C.-T. Lu and P. Zhang",
           title="A Unified Approach to Detecting Spatial Outliers",
           booktitle="GeoInformatica 7-2, 2003",
           url="http://dx.doi.org/10.1023/A:1023455925009")
public class CTLuMoranScatterplotOutlier<N>
extends AbstractNeighborhoodOutlier<N>

Moran scatterplot outliers, based on the standardized deviation from the local and global means. In contrast to the definition given in the reference, we use this as a ranking outlier detection by not applying the signedness test, but by using the score (- localZ) * (Average localZ of Neighborhood) directly. This allows us to differentiate a bit between stronger and weaker outliers.

Reference:
S. Shekhar and C.-T. Lu and P. Zhang
A Unified Approach to Detecting Spatial Outliers
in GeoInformatica 7-2, 2003

Moran scatterplot is a plot of normalized attribute values against the neighborhood average of normalized attribute values. Spatial Objects on the upper left or lower right are Spatial Outliers.

Nested Class Summary

static class

CTLuMoranScatterplotOutlier.Parameterizer<N> Parameterization class

Field Summary

private static Logging

logger The logger for this class.

Fields inherited from class de.lmu.ifi.dbs.elki.algorithm.outlier.spatial.AbstractNeighborhoodOutlier

NEIGHBORHOOD_ID

Constructor Summary

CTLuMoranScatterplotOutlier(NeighborSetPredicate.Factory<N> npredf)
Constructor

Method Summary

TypeInformation[]	getInputTypeRestriction() Get the input type restriction used for negotiating the data query.
protected Logging	getLogger() Get the (STATIC) logger for this class.
OutlierResult	run(Relation<N> nrel, Relation<? extends NumberVector<?,?>> relation) Main method

Methods inherited from class de.lmu.ifi.dbs.elki.algorithm.outlier.spatial.AbstractNeighborhoodOutlier

getNeighborSetPredicateFactory

Methods inherited from class de.lmu.ifi.dbs.elki.algorithm.AbstractAlgorithm

makeParameterDistanceFunction, run

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface de.lmu.ifi.dbs.elki.algorithm.outlier.OutlierAlgorithm

run

Field Detail

logger

private static final Logging logger

The logger for this class.

Constructor Detail

CTLuMoranScatterplotOutlier

public CTLuMoranScatterplotOutlier(NeighborSetPredicate.Factory<N> npredf)

Constructor

Parameters:

npredf - Neighborhood

Method Detail

run

public OutlierResult run(Relation<N> nrel,
                         Relation<? extends NumberVector<?,?>> relation)

Main method

Parameters:

nrel - Neighborhood relation

relation - Data relation (1d!)

Returns:

Outlier detection result

getInputTypeRestriction

public TypeInformation[] getInputTypeRestriction()

Description copied from class: AbstractAlgorithm

Get the input type restriction used for negotiating the data query.

Specified by:

getInputTypeRestriction in interface Algorithm

Specified by:

getInputTypeRestriction in class AbstractAlgorithm<OutlierResult>

Returns:

Type restriction

getLogger

protected Logging getLogger()

Description copied from class: AbstractAlgorithm

Get the (STATIC) logger for this class.

Specified by:

getLogger in class AbstractAlgorithm<OutlierResult>

Returns:

the static logger