Package elki.outlier.lof

Class SimplifiedLOF<O>

java.lang.Object

elki.outlier.lof.SimplifiedLOF<O>

Type Parameters:

O - the type of data objects handled by this algorithm

All Implemented Interfaces:

Algorithm, OutlierAlgorithm

@Reference(authors="Erich Schubert, Arthur Zimek, Hans-Peter Kriegel",
           title="Local Outlier Detection Reconsidered: a Generalized View on Locality with Applications to Spatial, Video, and Network Outlier Detection",
           booktitle="Data Mining and Knowledge Discovery 28(1)",
           url="https://doi.org/10.1007/s10618-012-0300-z",
           bibkey="DBLP:journals/datamine/SchubertZK14")
public class SimplifiedLOF<O>
extends java.lang.Object
implements OutlierAlgorithm

A simplified version of the original LOF algorithm, which does not use the reachability distance, yielding less stable results on inliers.

Reference:

Erich Schubert, Arthur Zimek, Hans-Peter Kriegel
Local Outlier Detection Reconsidered: a Generalized View on Locality with Applications to Spatial, Video, and Network Outlier Detection
Data Mining and Knowledge Discovery 28(1)

Since:

0.5.5

Author:

Erich Schubert

Nested Class Summary

Nested classes/interfaces inherited from interface elki.Algorithm

Algorithm.Utils

Field Summary

Fields

Modifier and Type	Field	Description
protected Distance<? super O>	distance	Distance function used.
protected int	kplus	The number of neighbors to query, plus the query point.
private static Logging	LOG	The logger for this class.

Constructor Summary

Constructors

Constructor	Description
SimplifiedLOF(Distance<? super O> distance, int k)	Constructor.

Method Summary

Modifier and Type	Method	Description
private void	computeSimplifiedLOFs(DBIDs ids, KNNSearcher<DBIDRef> knnq, WritableDoubleDataStore slrds, WritableDoubleDataStore lofs, DoubleMinMax lofminmax)	Compute the simplified LOF factors.
private void	computeSimplifiedLRDs(DBIDs ids, KNNSearcher<DBIDRef> knnq, WritableDoubleDataStore lrds)	Compute the simplified reachability densities.
TypeInformation[]	getInputTypeRestriction()	Get the input type restriction used for negotiating the data query.
OutlierResult	run(Relation<O> relation)	Run the Simple LOF algorithm.

Methods inherited from class java.lang.Object

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

Methods inherited from interface elki.outlier.OutlierAlgorithm

autorun

Field Detail

LOG

private static final Logging LOG

The logger for this class.

distance

protected Distance<? super O> distance

Distance function used.

kplus

protected int kplus

The number of neighbors to query, plus the query point.

Constructor Detail

SimplifiedLOF

public SimplifiedLOF(Distance<? super O> distance,
                     int k)

Constructor.

Parameters:

distance - Distance function

k - the number of neighbors

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 Simple LOF algorithm.

Parameters:

relation - Data to process

Returns:

LOF outlier result

computeSimplifiedLRDs

private void computeSimplifiedLRDs(DBIDs ids,
                                   KNNSearcher<DBIDRef> knnq,
                                   WritableDoubleDataStore lrds)

Compute the simplified reachability densities.

Parameters:

ids - IDs to process

knnq - kNN query class

lrds - Density output

computeSimplifiedLOFs

private void computeSimplifiedLOFs(DBIDs ids,
                                   KNNSearcher<DBIDRef> knnq,
                                   WritableDoubleDataStore slrds,
                                   WritableDoubleDataStore lofs,
                                   DoubleMinMax lofminmax)

Compute the simplified LOF factors.

Parameters:

ids - IDs to compute for

knnq - kNN query class

slrds - Object densities

lofs - SLOF output storage

lofminmax - Minimum and maximum scores