Package elki.index.tree.spatial.kd.split

Class MeanVarianceSplit

java.lang.Object

elki.index.tree.spatial.kd.split.MeanVarianceSplit

All Implemented Interfaces:

SplitStrategy

@Reference(authors="S. M. Omohundro",
           title="Efficient Algorithms with Neural Network Behaviour",
           booktitle="Journal of Complex Systems 1(2)",
           url="https://www.complex-systems.com/abstracts/v01_i02_a04/",
           bibkey="journals/jcs/Omohundro87")
public class MeanVarianceSplit
extends java.lang.Object
implements SplitStrategy

Split on the median of the axis with the largest variance.

Reference:

S. M. Omohundro
Efficient Algorithms with Neural Network Behaviour
Journal of Complex Systems 1(2)

Since:

0.8.0

Author:

Erich Schubert

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	MeanVarianceSplit.Par	Parameterizer

Nested classes/interfaces inherited from interface elki.index.tree.spatial.kd.split.SplitStrategy

SplitStrategy.Info, SplitStrategy.Util

Field Summary

Fields

Modifier and Type	Field	Description
static MeanVarianceSplit	STATIC	Static instance.

Constructor Summary

Constructors

Constructor	Description
MeanVarianceSplit()

Method Summary

Modifier and Type	Method	Description
SplitStrategy.Info	findSplit(Relation<? extends NumberVector> relation, int dims, ArrayModifiableDBIDs sorted, DBIDArrayMIter iter, int left, int right, VectorUtil.SortDBIDsBySingleDimension comp)	Build the k-d-tree using midpoint splitting.

Methods inherited from class java.lang.Object

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

Field Detail

STATIC

public static final MeanVarianceSplit STATIC

Static instance.

Constructor Detail

MeanVarianceSplit

public MeanVarianceSplit()

Method Detail

findSplit

public SplitStrategy.Info findSplit(Relation<? extends NumberVector> relation,
                                    int dims,
                                    ArrayModifiableDBIDs sorted,
                                    DBIDArrayMIter iter,
                                    int left,
                                    int right,
                                    VectorUtil.SortDBIDsBySingleDimension comp)

Description copied from interface: SplitStrategy

Build the k-d-tree using midpoint splitting.

Specified by:

findSplit in interface SplitStrategy

Parameters:

relation - data relation

dims - data dimensionality

sorted - modifiable array to encode the partitions

iter - reusable iterator to the array

left - left subinterval

right - right subinterval

comp - reusable comparator (bound to the relation above)

Returns:

split info, null if no good split