de.lmu.ifi.dbs.elki.distance.distancefunction.timeseries

Class EDRDistanceFunction

java.lang.Object

de.lmu.ifi.dbs.elki.distance.distancefunction.AbstractNumberVectorDistanceFunction

de.lmu.ifi.dbs.elki.distance.distancefunction.timeseries.AbstractEditDistanceFunction

de.lmu.ifi.dbs.elki.distance.distancefunction.timeseries.DTWDistanceFunction

de.lmu.ifi.dbs.elki.distance.distancefunction.timeseries.EDRDistanceFunction

All Implemented Interfaces:

DistanceFunction<NumberVector>, NumberVectorDistanceFunction<NumberVector>, PrimitiveDistanceFunction<NumberVector>

@Title(value="Edit Distance on Real Sequence")
 @Reference(authors="L. Chen, M. T. \u00d6zsu, V. Oria",
           title="Robust and fast similarity search for moving object trajectories",
           booktitle="Proc. 2005 ACM SIGMOD Int. Conf. Management of Data",
           url="https://doi.org/10.1145/1066157.1066213",
           bibkey="DBLP:conf/sigmod/ChenOO05")
public class EDRDistanceFunction
extends DTWDistanceFunction

Edit Distance on Real Sequence distance for numerical vectors.

Reference:

L. Chen, M. T. Özsu, V. Oria
Robust and fast similarity search for moving object trajectories
Proc. 2005 ACM SIGMOD Int. Conf. Management of Data

Since:

0.2

Author:

Thomas Bernecker

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	EDRDistanceFunction.Parameterizer Parameterization class.

Field Summary

Fields

Modifier and Type	Field and Description
private double	delta Delta parameter, similarity threshold for attributes.

Fields inherited from class de.lmu.ifi.dbs.elki.distance.distancefunction.timeseries.AbstractEditDistanceFunction

bandSize

Constructor Summary

Constructors

Constructor and Description
EDRDistanceFunction(double bandSize, double delta) Constructor.

Method Summary

Modifier and Type	Method and Description
protected double	delta(double val1, double val2) Compute the delta of two values.
double	distance(NumberVector v1, NumberVector v2) Computes the distance between two given vectors according to this distance function.
boolean	equals(java.lang.Object obj)
int	hashCode()

Methods inherited from class de.lmu.ifi.dbs.elki.distance.distancefunction.timeseries.DTWDistanceFunction

firstRow

Methods inherited from class de.lmu.ifi.dbs.elki.distance.distancefunction.timeseries.AbstractEditDistanceFunction

effectiveBandSize, getInputTypeRestriction

Methods inherited from class de.lmu.ifi.dbs.elki.distance.distancefunction.AbstractNumberVectorDistanceFunction

dimensionality, dimensionality, dimensionality, dimensionality, dimensionality, dimensionality, dimensionality, dimensionality

Methods inherited from class java.lang.Object

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

Methods inherited from interface de.lmu.ifi.dbs.elki.distance.distancefunction.PrimitiveDistanceFunction

instantiate

Methods inherited from interface de.lmu.ifi.dbs.elki.distance.distancefunction.DistanceFunction

isMetric, isSquared, isSymmetric

Field Detail

delta

private final double delta

Delta parameter, similarity threshold for attributes.

Constructor Detail

EDRDistanceFunction

public EDRDistanceFunction(double bandSize,
                           double delta)

Constructor.

Parameters:

bandSize - Band size

delta - Allowed delta

Method Detail

distance

public double distance(NumberVector v1,
                       NumberVector v2)

Description copied from interface: NumberVectorDistanceFunction

Computes the distance between two given vectors according to this distance function.

Specified by:

distance in interface NumberVectorDistanceFunction<NumberVector>

Specified by:

distance in interface PrimitiveDistanceFunction<NumberVector>

Overrides:

distance in class DTWDistanceFunction

Parameters:

v1 - first vector

v2 - second vector

Returns:

the distance between two given vectors according to this distance function

delta

protected double delta(double val1,
                       double val2)

Description copied from class: DTWDistanceFunction

Compute the delta of two values.

TODO: support Euclidean, Manhattan, others?

Overrides:

delta in class DTWDistanceFunction

Parameters:

val1 - First value

val2 - Second value

Returns:

Difference

equals

public boolean equals(java.lang.Object obj)

Overrides:

equals in class AbstractEditDistanceFunction

hashCode

public int hashCode()

Overrides:

hashCode in class AbstractEditDistanceFunction