comirva.visu
Class ProbabilisticNetworkVisu

java.lang.Object
  java.lang.Thread
      comirva.visu.ProbabilisticNetworkVisu

All Implemented Interfaces:

Runnable

public class ProbabilisticNetworkVisu
extends Thread

This class implements a ProbabilisticNetworkVisu visualization. To avoid blocking the GUI, it is implemented as thread.

Nested Class Summary

Nested classes/interfaces inherited from class java.lang.Thread

Thread.State, Thread.UncaughtExceptionHandler

Field Summary

Fields inherited from class java.lang.Thread

MAX_PRIORITY, MIN_PRIORITY, NORM_PRIORITY

Constructor Summary

ProbabilisticNetworkVisu(VisuPane vp)
Constructs a new ProbabilisticNetworkVisu.

Method Summary

void	initMouseListener() inits the mouse listeners that are needed for this visualisation.
void	run() Start drawing the visualization.

Methods inherited from class java.lang.Thread

activeCount, checkAccess, countStackFrames, currentThread, destroy, dumpStack, enumerate, getAllStackTraces, getContextClassLoader, getDefaultUncaughtExceptionHandler, getId, getName, getPriority, getStackTrace, getState, getThreadGroup, getUncaughtExceptionHandler, holdsLock, interrupt, interrupted, isAlive, isDaemon, isInterrupted, join, join, join, resume, setContextClassLoader, setDaemon, setDefaultUncaughtExceptionHandler, setName, setPriority, setUncaughtExceptionHandler, sleep, sleep, start, stop, stop, suspend, toString, yield

Methods inherited from class java.lang.Object

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

Constructor Detail

ProbabilisticNetworkVisu

public ProbabilisticNetworkVisu(VisuPane vp)

Constructs a new ProbabilisticNetworkVisu.

Parameters:

vp - the VisuPane of CoMIRVA which is responsible for drawing

Method Detail

initMouseListener

public void initMouseListener()

inits the mouse listeners that are needed for this visualisation.

run

public void run()

Start drawing the visualization. Paints a probablistic network visualization based on a random graph (Erd�s-R�nyi). At first, the data items are positioned randomly on the screen and are shown as circles with a diameter equal to the similarity to all other data items. Thus, data items with high similarity to other data items are visualized by bigger circles. In an adaptation step, then, data points i,j with a "strong" connection, meaning that their distance is low (their similiarity is high), are moved closer to each other. Finally, connections between data points are drawn with a probability that equals their similarity multiplied with a probability correction.

Specified by:

run in interface Runnable

Overrides:

run in class Thread

See Also:

Thread.run()