P - Spatial Vector type@Title(value="Random Walk on Exhaustive Combination") @Description(value="Spatial Outlier Detection using Random Walk on Exhaustive Combination") @Reference(authors="X. Liu, C.-T. Lu, F. Chen", title="Spatial outlier detection: random walk based approaches", booktitle="Proc. SIGSPATIAL Int. Conf. Advances in Geographic Information Systems", url="https://doi.org/10.1145/1869790.1869841", bibkey="DBLP:conf/gis/LiuLC10") public class CTLuRandomWalkEC<P> extends AbstractDistanceBasedAlgorithm<P,OutlierResult> implements OutlierAlgorithm
Note: this method can only handle one-dimensional data, but could probably be easily extended to higher dimensional data by using an distance function instead of the absolute difference.
Reference:
X. Liu, C.-T. Lu, F. Chen
Spatial outlier detection: random walk based approaches
Proc. SIGSPATIAL Int. Conf. Advances in Geographic Information Systems
| Modifier and Type | Class and Description |
|---|---|
static class |
CTLuRandomWalkEC.Parameterizer<N>
Parameterization class.
|
| Modifier and Type | Field and Description |
|---|---|
private double |
alpha
Parameter alpha: Attribute difference exponent.
|
private double |
c
Parameter c: damping factor.
|
private int |
k
Parameter k.
|
private static Logging |
LOG
Logger.
|
ALGORITHM_IDDISTANCE_FUNCTION_ID| Constructor and Description |
|---|
CTLuRandomWalkEC(DistanceFunction<? super P> distanceFunction,
double alpha,
double c,
int k)
Constructor.
|
| Modifier and Type | Method and Description |
|---|---|
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<P> spatial,
Relation<? extends NumberVector> relation)
Run the algorithm.
|
getDistanceFunctionrunclone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitrunprivate static final Logging LOG
private double alpha
private double c
private int k
public CTLuRandomWalkEC(DistanceFunction<? super P> distanceFunction, double alpha, double c, int k)
distanceFunction - Distance functionalpha - Alpha parameterc - C parameterk - Number of neighborspublic OutlierResult run(Relation<P> spatial, Relation<? extends NumberVector> relation)
spatial - Spatial neighborhood relationrelation - Attribute value relationpublic TypeInformation[] getInputTypeRestriction()
AbstractAlgorithmgetInputTypeRestriction in interface AlgorithmgetInputTypeRestriction in class AbstractAlgorithm<OutlierResult>protected Logging getLogger()
AbstractAlgorithmgetLogger in class AbstractAlgorithm<OutlierResult>Copyright © 2019 ELKI Development Team. License information.