A set of mutually correlated noise sources (Wiener, Poisson and Ornstein-Uhlenbeck processes). More...

Inheritance diagram for NoiseSource:

Public Member Functions
	NoiseSource (Time *time, int n)
	Construct. More...

	NoiseSource (Time *time, Matrix a)
	Construct. More...

	~NoiseSource ()
	Destruct.

Noise *	createNoise (int n, const string &t)
	Set/Get a noise object. More...

Noise *	operator[] (int n)
	Get a noise object. More...

void	setMixingMatrix (Matrix a)
	Set the mixing matrix. More...

double	getIndicatorVariance (int n)
	Get variance.

double	getCovariationCoeff (int n, int m)
	Get covariation coefficient. More...

void	destructionNotify (int n)
	Callback for Noise objects. More...

virtual void	prepareNextState ()
	Compute next value. More...

virtual void	proceedToNextState ()
	Set next time step. More...

Public Member Functions inherited from StochasticProcess
	StochasticProcess (class Time *time, const string &name="", const string &type="Stochastic")
	Create.

virtual	~StochasticProcess ()
	Destroy.

bool	isNextStatePrepared ()
	Whether.

virtual double	getIncrement ()
	Returns the increment. More...

virtual double	getCurrentValue ()
	Returns the value of the process. More...

virtual double	getNextValue ()
	Returns the next value of the process. More...

virtual void	setNextValue (double d)
	Set the next value of the process. More...

virtual void	setCurrentValue (double d)
	Set the current value of the process. More...

void	setDescription (string s)
	Set stochastic description.

virtual void	init ()
	Initialise time-dependent values.

string	getDescription ()
	Get the name. More...

Public Member Functions inherited from Parametric
string	getType () const
	Type of object.

string	getName () const
	Name of object.

void	setName (const string &name)
	Name of object.

string	getConfiguration () const
	Returns the configuration of the object. More...

string	getAllParameters () const
	String with all parameter settings.

void	addParameter (const string &name)
	Add a parameter. More...

void	rmParameter (const string &name)
	Remove a parameter. More...

virtual void	setParameter (const string &name, const string &value)
	Set parameter. More...

virtual string	getParameter (const string &name) const
	Get parameter. More...

Public Member Functions inherited from TimeDependent
	TimeDependent (class Time *time)
	Construct. More...

virtual class Time *	getTime () const
	Return pointer to the time object.

Public Member Functions inherited from Physical
	Physical ()
	Construct.

	Physical (const Physical &)
	Copy.

	Physical (string name)
	Construct.

	Physical (string name, string unitPrefix, string unitSymbol)
	Construct.

	Physical (string name, Unit unit)
	Construct.

virtual string	getPhysicalDescription ()
	Returns the physical description. More...

virtual string	getUnitName ()
	Returns the unit name.

virtual string	getUnitSymbol ()
	Returns the unit name.

virtual void	setPhysicalDescription (string name)
	Set the name. Same as setDescription(). More...

virtual void	setUnit (Unit u)
	Set the unit.

virtual void	setUnitPrefix (int n)
	Set unit prefix. More...

virtual Unit	getUnit () const
	Retrieve the unit.

Public Member Functions inherited from RandN
	RandN ()
	Construct.

	~RandN ()
	Destruct.

double	dRandN ()
	Retrieve random variable. More...

double	dRandE ()
	Retrieve random variable. More...

Additional Inherited Members
Protected Member Functions inherited from Parametric
	Parametric (const string &name, const string &type)
	Create object of type and name.

virtual	~Parametric ()
	Destroy object.

Protected Attributes inherited from StochasticProcess
double	stochCurrentValue
	the current value

double	stochNextValue
	the next value (direct future)

bool	stochNextStateIsPrepared
	whether prepareNextState() was successful

string	stochDescription
	the name of the quantity

Detailed Description

A set of mutually correlated noise sources (Wiener, Poisson and Ornstein-Uhlenbeck processes).

An object of this class creates various noise source which may be correlated. The correlation is achieved by mixing independent noise sources with a mixing matrix (details below).

Construction and usage: The constructor will set up an object with n noise sources. They can be used straight away. The mixing matrix, as well as type and parameters for each process can be set at runtime. Mean, variance and covariation processes can also be obtained at runtime.

Method:

$\omega -> funtionInput -> dPt / dWt$

$\left<\left[G^i,G^j\right]\right> = \sigma_jc_{ij} c_j w_j\lambda_j$

with

$c_j = \sqrt{\frac{2}{\pi}} \frac {e^{-\frac{\lambda_j^2dt}{2\mbox{Var}\left\{dX^i_t\right\}}}} {\left(1-\mbox{erf}{\frac{\lambda_j\sqrt{dt}}{\sqrt{2\mbox{Var}\left\{dX^i_t\right\}}}}\right)\sqrt{\mbox{Var}\left\{dX^i_t\right\}}}.$

Constructor & Destructor Documentation

NoiseSource::NoiseSource	(	Time *	time,
		int	n
	)

Construct.

Constructs a NoiseSource object, which produces n noise processes. The default mixing matrix is the identity matrix (Zeros with diagonal Ones). Use setMixingMatrix() to change.

Parameters

time	Adress of a (central) time object.
n	Number of processes.

NoiseSource::NoiseSource	(	Time *	time,
		Matrix	a
	)

Construct.

Constructs a NoiseSource object, where the processes are mixed as stated in the given mixing matrix.

Parameters

time	Adress of a (central) time object.
a	Mixing matrix.

Member Function Documentation

Noise* NoiseSource::createNoise	(	int	n,
		const string &	t
	)

Set/Get a noise object.

This will retrieve the address of a noise object. If the object is not existent, or of a different type as stated by the p, it will be created.

Parameters

n	The index of the noise.
t	The type of the noise (can be "Correlated Wiender Process", "Correlated Poisson Process", "Correlated Ornstein-Uhlenbeck Process").

void NoiseSource::destructionNotify ( int n )

Callback for Noise objects.

Called by a noise object n, to notify its parent that it has died.

double NoiseSource::getCovariationCoeff	(	int	n,
		int	m
	)

Get covariation coefficient.

The covariation process (see Covariation) is in many cases just time multiplied by a scalar. The method retrieves this scalar.

Returns: The scalar s, so that $\left[X^n,X^m\right]_t = st$

Parameters

n	Index of first noise process.
m	Index of second noise process.

Noise* NoiseSource::operator[] ( int n )

Get a noise object.

This returns only existent noise objects.

Parameters

n	The index of the noise.

virtual void NoiseSource::prepareNextState ( )

virtual

Compute next value.

This will compute the next value of all indicator variables. The values of the noises are not affected.

Reimplemented from StochasticProcess.

virtual void NoiseSource::proceedToNextState ( )

virtual

Set next time step.

This will set all noises to the next time step.

Reimplemented from StochasticProcess.

void NoiseSource::setMixingMatrix ( Matrix a )

Set the mixing matrix.

Just sets a new mixing matrix to a given set of noises. Note that the dimensions of the matrix must match (i.e. for n noise sources, you want an nxn Matrix.

Parameters

a	The mixing matrix.

Public Member Functions

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation