org.openimaj.ml.timeseries.processor

Class GaussianTimeSeriesProcessor

java.lang.Object

org.openimaj.ml.timeseries.processor.GaussianTimeSeriesProcessor

All Implemented Interfaces:

TimeSeriesProcessor<double[],Double,DoubleTimeSeries>

public class GaussianTimeSeriesProcessor
extends Object
implements TimeSeriesProcessor<double[],Double,DoubleTimeSeries>

Calculates a moving average over a specified window in the past such that data[t_n] = sum^{m}_{i=1}{data[t_{n-i}} This processor returns a value for each time in the underlying time series. For sensible results, consider interpolating a consistent time span using an LinearInterpolationProcessor followed by this processor.

Author:

Sina Samangooei (ss@ecs.soton.ac.uk)

Field Summary

Fields

Modifier and Type	Field and Description
static double	DEFAULT_GAUSS_TRUNCATE The default number of sigmas at which the Gaussian function is truncated when building a kernel

Constructor Summary

Constructors

Constructor and Description
GaussianTimeSeriesProcessor(double sigma)

Method Summary

Modifier and Type	Method and Description
static void	convolveHorizontal(double[] data, double[] kernel) Convolve a double array
static double[]	makeKernel(double sigma, double truncate) Construct a zero-mean Gaussian with the specified standard deviation.
void	process(DoubleTimeSeries series)

Methods inherited from class java.lang.Object

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

Field Detail

DEFAULT_GAUSS_TRUNCATE

public static final double DEFAULT_GAUSS_TRUNCATE

The default number of sigmas at which the Gaussian function is truncated when building a kernel

See Also:

Constant Field Values

Constructor Detail

GaussianTimeSeriesProcessor

public GaussianTimeSeriesProcessor(double sigma)

Parameters:

sigma - the sigma of the guassian function

Method Detail

makeKernel

public static double[] makeKernel(double sigma,
                                  double truncate)

Construct a zero-mean Gaussian with the specified standard deviation.

Parameters:

sigma - the standard deviation of the Gaussian

truncate - the number of sigmas from the centre at which to truncate the Gaussian

Returns:

an array representing a Gaussian function

convolveHorizontal

public static void convolveHorizontal(double[] data,
                                      double[] kernel)

Convolve a double array

Parameters:

data - the image to convolve.

kernel - the convolution kernel.

process

public void process(DoubleTimeSeries series)

Specified by:

process in interface TimeSeriesProcessor<double[],Double,DoubleTimeSeries>

Parameters:

series - alter this time series in place