org.joone.util
Class DeltaNormPlugIn

java.lang.Object
  extended by org.joone.util.AbstractConverterPlugIn
      extended by org.joone.util.ConverterPlugIn
          extended by org.joone.util.DeltaNormPlugIn
All Implemented Interfaces:
java.io.Serializable, PlugInListener

public class DeltaNormPlugIn
extends ConverterPlugIn

This plugin calculates the Delta Normalization on a time series. the Delta Normalization technique permits to feed a neural network with the delta values instead of the absolute values of the series, permitting in this manner to avoid the problems correlated with both ascending and descending trends. The normalization is obtained by dividing the delta value by the dynamic range (named Probability Volatility Windows) calculated on the given period. This plugin is very useful for financial predictions when used in combination with the MinMaxExtractorPlugin. To learn more on this technique read the excellent book: "Financial Prediction Using Neural Networks" by Joseph S. Zirilli (you can buy it in electronic format at http://www.mjfutures.com/Book.htm)

Author:
P.Marrone
See Also:
Serialized Form

Field Summary
 
Fields inherited from class org.joone.util.AbstractConverterPlugIn
pluginListeners
 
Constructor Summary
DeltaNormPlugIn()
          Creates a new instance of DeltaNormPlugin
 
Method Summary
protected  double calculatePVW(int delay, int serie)
           
protected  boolean convert(int serie)
          Applies the conversion on the Nth serie of the buffered pattern data.
protected  double funcDelta(int index, int delay, int serie)
          Calculates f(i,delay) used by getDelta >>>> This method can be overriden in order to implement different volatility window algorithms
protected  double getDelta(int index, int delay, int serie, boolean abs)
           
 
Methods inherited from class org.joone.util.ConverterPlugIn
isApplyEveryCycle, newCycle, setApplyEveryCycle
 
Methods inherited from class org.joone.util.AbstractConverterPlugIn
addPlugIn, addPlugInListener, apply, applyOnColumns, applyOnRows, cascade, check, convertPatterns, dataChanged, fireDataChanged, getAdvancedSerieSelector, getInputVector, getName, getNextPlugIn, getPluginListeners, getSerieIndexNumber, getSerieSelected, getValuePoint, isConnected, removeAllPlugIns, removePlugInListener, setAdvancedSerieSelector, setConnected, setInputVector, setName, setNextPlugin, setNextPlugIn
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

DeltaNormPlugIn

public DeltaNormPlugIn()
Creates a new instance of DeltaNormPlugin

Method Detail

convert

protected boolean convert(int serie)
Description copied from class: AbstractConverterPlugIn
Applies the conversion on the Nth serie of the buffered pattern data. The method is abstract and should be overridden by the implementing class. Implementing classes can obtain the input patterns by calling the AbstractConverterPlugIn.getInputVector() method. The result is a Vector of Pattern objects which this method should use by converting the requested serie.

Specified by:
convert in class AbstractConverterPlugIn
Parameters:
serie - the serie to convert

calculatePVW

protected double calculatePVW(int delay,
                              int serie)

getDelta

protected double getDelta(int index,
                          int delay,
                          int serie,
                          boolean abs)

funcDelta

protected double funcDelta(int index,
                           int delay,
                           int serie)
Calculates f(i,delay) used by getDelta >>>> This method can be overriden in order to implement different volatility window algorithms



Submit Feedback to pmarrone@users.sourceforge.net