bdm::KalmanCh Class Reference

Kalman filter in square root form. More...

#include <libKF.h>

Inheritance diagram for bdm::KalmanCh:

[legend]

Collaboration diagram for bdm::KalmanCh:

[legend]

List of all members.

Public Member Functions
	KalmanCh (RV rvx0, RV rvy0, RV rvu0)
	Default constructor.
void	set_parameters (const mat &A0, const mat &B0, const mat &C0, const mat &D0, const chmat &R0, const chmat &Q0)
	Set parameters with check of relevance.
void	set_est (const vec &mu0, const chmat &P0)
	Set estimate values, used e.g. in initialization.
void	bayes (const vec &dt)
	Here dt = [yt;ut] of appropriate dimensions.
const epdf &	_epdf () const
	access function
const enorm< chmat > *	_e () const
	Returns a pointer to the epdf representing posterior density on parameters. Use with care!
mat &	__K ()
	access function
vec	_dP ()
	access function
virtual void	bayesB (const mat &Dt)
	Batch Bayes rule (columns of Dt are observations).
virtual double	logpred (const vec &dt) const
vec	logpred_m (const mat &dt) const
	Matrix version of logpred.
virtual epdf *	predictor (const RV &rv) const
	Constructs a predictive density (marginal density on data).
const RV &	_rv () const
	access function
const RV &	_drv () const
	access function
void	set_drv (const RV &rv)
	set drv
double	_ll () const
	access function
void	set_evalll (bool evl0)
	access function
virtual BM *	_copy_ (bool changerv=false)
Protected Attributes
mat	preA
	pre array (triangular matrix)
mat	postA
	post array (triangular matrix)
RV	rvy
	Indetifier of output rv.
RV	rvu
	Indetifier of exogeneous rv.
int	dimx
	cache of rv.count()
int	dimy
	cache of rvy.count()
int	dimu
	cache of rvu.count()
mat	A
	Matrix A.
mat	B
	Matrix B.
mat	C
	Matrix C.
mat	D
	Matrix D.
chmat	Q
	Matrix Q in square-root form.
chmat	R
	Matrix R in square-root form.
enorm< chmat >	est
	posterior density on $x_t$
enorm< chmat >	fy
	preditive density on $y_t$
mat	_K
	placeholder for Kalman gain
vec &	_yp
	cache of fy.mu
chmat &	_Ry
	cache of fy.R
vec &	_mu
	cache of est.mu
chmat &	_P
	cache of est.R
RV	rv
	Random variable of the posterior.
RV	drv
	Random variable of the data (optional).
double	ll
	Logarithm of marginalized data likelihood.
bool	evalll
	If true, the filter will compute likelihood of the data record and store it in ll . Set to false if you want to save computational time.

---

Detailed Description

Kalman filter in square root form.

---

Member Function Documentation

void bdm::KalmanCh::bayes

(

const vec &

dt

)

[virtual]

Here dt = [yt;ut] of appropriate dimensions.

The following equality hold::

Thus this object evaluates only predictors! Not filtering densities.

Reimplemented from bdm::Kalman< chmat >.

Reimplemented in bdm::EKFCh.

References chmat::_Ch(), bdm::Kalman< chmat >::_K, bdm::Kalman< chmat >::_mu, bdm::Kalman< chmat >::_P, bdm::Kalman< chmat >::_Ry, bdm::Kalman< chmat >::_yp, bdm::Kalman< chmat >::A, bdm::Kalman< chmat >::B, bdm::Kalman< chmat >::C, bdm::Kalman< chmat >::D, bdm::Kalman< chmat >::dimu, bdm::Kalman< chmat >::dimx, bdm::Kalman< chmat >::dimy, bdm::BM::evalll, bdm::eEF::evallog(), bdm::Kalman< chmat >::fy, bdm::BM::ll, postA, and preA.

virtual double bdm::BM::logpred

(

const vec &

dt

)

const [inline, virtual, inherited]

Evaluates predictive log-likelihood of the given data record I.e. marginal likelihood of the data with the posterior integrated out.

Reimplemented in bdm::ARX, bdm::MixEF, and bdm::multiBM.

Referenced by bdm::BM::logpred_m().

virtual BM* bdm::BM::_copy_

(

bool

changerv = false

)

[inline, virtual, inherited]

Copy function required in vectors, Arrays of BM etc. Have to be DELETED manually! Prototype: BM* _copy_(){BM Tmp*=new Tmp(this*); return Tmp; }

Reimplemented in bdm::ARX, and bdm::BMEF.

---

The documentation for this class was generated from the following files:

• libKF.h
• libKF.cpp