\hypertarget{classEKF}{
\section{EKF$<$ sq\_\-T $>$ Class Template Reference}
\label{classEKF}\index{EKF@{EKF}}
}
Extended \hyperlink{classKalman}{Kalman} Filter.  


{\tt \#include $<$libKF.h$>$}

Inheritance diagram for EKF$<$ sq\_\-T $>$:\nopagebreak
\begin{figure}[H]
\begin{center}
\leavevmode
\includegraphics[width=96pt]{classEKF__inherit__graph}
\end{center}
\end{figure}
Collaboration diagram for EKF$<$ sq\_\-T $>$:\nopagebreak
\begin{figure}[H]
\begin{center}
\leavevmode
\includegraphics[width=400pt]{classEKF__coll__graph}
\end{center}
\end{figure}
\subsection*{Public Member Functions}
\begin{CompactItemize}
\item 
\hypertarget{classEKF_ea4f3254cacf0a92d2a820b1201d049e}{
\hyperlink{classEKF_ea4f3254cacf0a92d2a820b1201d049e}{EKF} (\hyperlink{classRV}{RV} rvx, \hyperlink{classRV}{RV} \hyperlink{classKalman_7501230c2fafa3655887d2da23b3184c}{rvy}, \hyperlink{classRV}{RV} \hyperlink{classKalman_44a16ffd5ac1e6e39bae34fea9e1e498}{rvu})}
\label{classEKF_ea4f3254cacf0a92d2a820b1201d049e}

\begin{CompactList}\small\item\em Default constructor. \item\end{CompactList}\item 
\hypertarget{classEKF_28d058ae4d24d992d2f055419a06ee66}{
void \hyperlink{classEKF_28d058ae4d24d992d2f055419a06ee66}{set\_\-parameters} (\hyperlink{classdiffbifn}{diffbifn} $\ast$pfxu, \hyperlink{classdiffbifn}{diffbifn} $\ast$phxu, const sq\_\-T Q0, const sq\_\-T R0)}
\label{classEKF_28d058ae4d24d992d2f055419a06ee66}

\begin{CompactList}\small\item\em Set nonlinear functions for mean values and covariance matrices. \item\end{CompactList}\item 
\hypertarget{classEKF_c79c62c9b3e0b56b3aaa1b6f1d9a7af7}{
void \hyperlink{classEKF_c79c62c9b3e0b56b3aaa1b6f1d9a7af7}{bayes} (const vec \&dt)}
\label{classEKF_c79c62c9b3e0b56b3aaa1b6f1d9a7af7}

\begin{CompactList}\small\item\em Here dt = \mbox{[}yt;ut\mbox{]} of appropriate dimensions. \item\end{CompactList}\item 
\hypertarget{classKalman_239b28a0380946f5749b2f8d2807f93a}{
void \hyperlink{classKalman_239b28a0380946f5749b2f8d2807f93a}{set\_\-parameters} (const mat \&A0, const mat \&B0, const mat \&C0, const mat \&D0, const \hyperlink{classfsqmat}{fsqmat} \&R0, const \hyperlink{classfsqmat}{fsqmat} \&Q0)}
\label{classKalman_239b28a0380946f5749b2f8d2807f93a}

\begin{CompactList}\small\item\em Set parameters with check of relevance. \item\end{CompactList}\item 
\hypertarget{classKalman_80bcf29466d9a9dd2b8f74699807d0c0}{
void \hyperlink{classKalman_80bcf29466d9a9dd2b8f74699807d0c0}{set\_\-est} (const vec \&mu0, const \hyperlink{classfsqmat}{fsqmat} \&P0)}
\label{classKalman_80bcf29466d9a9dd2b8f74699807d0c0}

\begin{CompactList}\small\item\em Set estimate values, used e.g. in initialization. \item\end{CompactList}\item 
\hypertarget{classKalman_67cccaf1c4dcdcd1df110e15ef326bfe}{
const \hyperlink{classepdf}{epdf} \& \hyperlink{classKalman_67cccaf1c4dcdcd1df110e15ef326bfe}{\_\-epdf} () const }
\label{classKalman_67cccaf1c4dcdcd1df110e15ef326bfe}

\begin{CompactList}\small\item\em access function \item\end{CompactList}\item 
\hypertarget{classKalman_980fcd41c6c548c5da7b8b67c8e6da79}{
mat \& \hyperlink{classKalman_980fcd41c6c548c5da7b8b67c8e6da79}{\_\-\_\-K} ()}
\label{classKalman_980fcd41c6c548c5da7b8b67c8e6da79}

\begin{CompactList}\small\item\em access function \item\end{CompactList}\item 
\hypertarget{classKalman_ac9540f3850b74d89a5fe4db6fc358ce}{
vec \hyperlink{classKalman_ac9540f3850b74d89a5fe4db6fc358ce}{\_\-dP} ()}
\label{classKalman_ac9540f3850b74d89a5fe4db6fc358ce}

\begin{CompactList}\small\item\em access function \item\end{CompactList}\item 
\hypertarget{classBM_0186270f75189677f390fe088a9947e9}{
virtual void \hyperlink{classBM_0186270f75189677f390fe088a9947e9}{bayesB} (const mat \&Dt)}
\label{classBM_0186270f75189677f390fe088a9947e9}

\begin{CompactList}\small\item\em Batch Bayes rule (columns of Dt are observations). \item\end{CompactList}\item 
virtual double \hyperlink{classBM_8a8ce6df431689964c41cc6c849cfd06}{logpred} (const vec \&dt) const 
\item 
\hypertarget{classBM_cd0660f2a1a344b56ac39802708ff165}{
vec \hyperlink{classBM_cd0660f2a1a344b56ac39802708ff165}{logpred\_\-m} (const mat \&dt) const }
\label{classBM_cd0660f2a1a344b56ac39802708ff165}

\begin{CompactList}\small\item\em Matrix version of logpred. \item\end{CompactList}\item 
\hypertarget{classBM_a627c5a79cc6f5221b7e09675525e032}{
virtual \hyperlink{classepdf}{epdf} $\ast$ \hyperlink{classBM_a627c5a79cc6f5221b7e09675525e032}{predictor} (const \hyperlink{classRV}{RV} \&\hyperlink{classBM_af00f0612fabe66241dd507188cdbf88}{rv})}
\label{classBM_a627c5a79cc6f5221b7e09675525e032}

\begin{CompactList}\small\item\em Constructs a predictive density (marginal density on data). \item\end{CompactList}\item 
\hypertarget{classBM_126bd2595c48e311fc2a7ab72876092a}{
const \hyperlink{classRV}{RV} \& \hyperlink{classBM_126bd2595c48e311fc2a7ab72876092a}{\_\-rv} () const }
\label{classBM_126bd2595c48e311fc2a7ab72876092a}

\begin{CompactList}\small\item\em access function \item\end{CompactList}\item 
\hypertarget{classBM_87f4a547d2c29180be88175e5eab9c88}{
double \hyperlink{classBM_87f4a547d2c29180be88175e5eab9c88}{\_\-ll} () const }
\label{classBM_87f4a547d2c29180be88175e5eab9c88}

\begin{CompactList}\small\item\em access function \item\end{CompactList}\item 
\hypertarget{classBM_1ffa9f23669aabecc3760c06c6987522}{
void \hyperlink{classBM_1ffa9f23669aabecc3760c06c6987522}{set\_\-evalll} (bool evl0)}
\label{classBM_1ffa9f23669aabecc3760c06c6987522}

\begin{CompactList}\small\item\em access function \item\end{CompactList}\item 
virtual \hyperlink{classBM}{BM} $\ast$ \hyperlink{classBM_eb58c81d6a7b75b05fc6f276eed78887}{\_\-copy\_\-} (bool changerv=false)
\end{CompactItemize}
\subsection*{Protected Attributes}
\begin{CompactItemize}
\item 
\hypertarget{classKalman_7501230c2fafa3655887d2da23b3184c}{
\hyperlink{classRV}{RV} \hyperlink{classKalman_7501230c2fafa3655887d2da23b3184c}{rvy}}
\label{classKalman_7501230c2fafa3655887d2da23b3184c}

\begin{CompactList}\small\item\em Indetifier of output rv. \item\end{CompactList}\item 
\hypertarget{classKalman_44a16ffd5ac1e6e39bae34fea9e1e498}{
\hyperlink{classRV}{RV} \hyperlink{classKalman_44a16ffd5ac1e6e39bae34fea9e1e498}{rvu}}
\label{classKalman_44a16ffd5ac1e6e39bae34fea9e1e498}

\begin{CompactList}\small\item\em Indetifier of exogeneous rv. \item\end{CompactList}\item 
\hypertarget{classKalman_39c8c403b46fa3b8c7da77cb2e3729eb}{
int \hyperlink{classKalman_39c8c403b46fa3b8c7da77cb2e3729eb}{dimx}}
\label{classKalman_39c8c403b46fa3b8c7da77cb2e3729eb}

\begin{CompactList}\small\item\em cache of rv.count() \item\end{CompactList}\item 
\hypertarget{classKalman_ba17b956df1e38b31fbbc299c8213b6a}{
int \hyperlink{classKalman_ba17b956df1e38b31fbbc299c8213b6a}{dimy}}
\label{classKalman_ba17b956df1e38b31fbbc299c8213b6a}

\begin{CompactList}\small\item\em cache of rvy.count() \item\end{CompactList}\item 
\hypertarget{classKalman_b0153795a1444b6968a86409c778d9ce}{
int \hyperlink{classKalman_b0153795a1444b6968a86409c778d9ce}{dimu}}
\label{classKalman_b0153795a1444b6968a86409c778d9ce}

\begin{CompactList}\small\item\em cache of rvu.count() \item\end{CompactList}\item 
\hypertarget{classKalman_5e02efe86ee91e9c74b93b425fe060b9}{
mat \hyperlink{classKalman_5e02efe86ee91e9c74b93b425fe060b9}{A}}
\label{classKalman_5e02efe86ee91e9c74b93b425fe060b9}

\begin{CompactList}\small\item\em Matrix A. \item\end{CompactList}\item 
\hypertarget{classKalman_dc87704284a6c0bca13bf51f4345a50a}{
mat \hyperlink{classKalman_dc87704284a6c0bca13bf51f4345a50a}{B}}
\label{classKalman_dc87704284a6c0bca13bf51f4345a50a}

\begin{CompactList}\small\item\em Matrix B. \item\end{CompactList}\item 
\hypertarget{classKalman_86a805cd6515872d1132ad0d6eb5dc13}{
mat \hyperlink{classKalman_86a805cd6515872d1132ad0d6eb5dc13}{C}}
\label{classKalman_86a805cd6515872d1132ad0d6eb5dc13}

\begin{CompactList}\small\item\em Matrix C. \item\end{CompactList}\item 
\hypertarget{classKalman_d69f774ba3335c970c1c5b1d182f4dd1}{
mat \hyperlink{classKalman_d69f774ba3335c970c1c5b1d182f4dd1}{D}}
\label{classKalman_d69f774ba3335c970c1c5b1d182f4dd1}

\begin{CompactList}\small\item\em Matrix D. \item\end{CompactList}\item 
\hypertarget{classKalman_9b69015c800eb93f3ee49da23a6f55d9}{
\hyperlink{classfsqmat}{fsqmat} \hyperlink{classKalman_9b69015c800eb93f3ee49da23a6f55d9}{Q}}
\label{classKalman_9b69015c800eb93f3ee49da23a6f55d9}

\begin{CompactList}\small\item\em Matrix Q in square-root form. \item\end{CompactList}\item 
\hypertarget{classKalman_11d171dc0e0ab111c56a70f98b97b3ec}{
\hyperlink{classfsqmat}{fsqmat} \hyperlink{classKalman_11d171dc0e0ab111c56a70f98b97b3ec}{R}}
\label{classKalman_11d171dc0e0ab111c56a70f98b97b3ec}

\begin{CompactList}\small\item\em Matrix R in square-root form. \item\end{CompactList}\item 
\hypertarget{classKalman_5568c74bac67ae6d3b1061dba60c9424}{
\hyperlink{classenorm}{enorm}$<$ \hyperlink{classfsqmat}{fsqmat} $>$ \hyperlink{classKalman_5568c74bac67ae6d3b1061dba60c9424}{est}}
\label{classKalman_5568c74bac67ae6d3b1061dba60c9424}

\begin{CompactList}\small\item\em posterior density on \$x\_\-t\$ \item\end{CompactList}\item 
\hypertarget{classKalman_e580ab06483952bd03f2e651763e184f}{
\hyperlink{classenorm}{enorm}$<$ \hyperlink{classfsqmat}{fsqmat} $>$ \hyperlink{classKalman_e580ab06483952bd03f2e651763e184f}{fy}}
\label{classKalman_e580ab06483952bd03f2e651763e184f}

\begin{CompactList}\small\item\em preditive density on \$y\_\-t\$ \item\end{CompactList}\item 
\hypertarget{classKalman_d422f51467c7a06174af2476d2826132}{
mat \hyperlink{classKalman_d422f51467c7a06174af2476d2826132}{\_\-K}}
\label{classKalman_d422f51467c7a06174af2476d2826132}

\begin{CompactList}\small\item\em placeholder for \hyperlink{classKalman}{Kalman} gain \item\end{CompactList}\item 
\hypertarget{classKalman_764bbc95238eda11fc81c5ebd0b1dcfd}{
vec \& \hyperlink{classKalman_764bbc95238eda11fc81c5ebd0b1dcfd}{\_\-yp}}
\label{classKalman_764bbc95238eda11fc81c5ebd0b1dcfd}

\begin{CompactList}\small\item\em cache of fy.mu \item\end{CompactList}\item 
\hypertarget{classKalman_45c9f928d2d62e0c884900fb3380f904}{
\hyperlink{classfsqmat}{fsqmat} \& \hyperlink{classKalman_45c9f928d2d62e0c884900fb3380f904}{\_\-Ry}}
\label{classKalman_45c9f928d2d62e0c884900fb3380f904}

\begin{CompactList}\small\item\em cache of fy.R \item\end{CompactList}\item 
\hypertarget{classKalman_fe803a81d2d847b0b1db3c6b29c18061}{
vec \& \hyperlink{classKalman_fe803a81d2d847b0b1db3c6b29c18061}{\_\-mu}}
\label{classKalman_fe803a81d2d847b0b1db3c6b29c18061}

\begin{CompactList}\small\item\em cache of est.mu \item\end{CompactList}\item 
\hypertarget{classKalman_9fb808cc94a4c2652e1fb93be9bb7dcf}{
\hyperlink{classfsqmat}{fsqmat} \& \hyperlink{classKalman_9fb808cc94a4c2652e1fb93be9bb7dcf}{\_\-P}}
\label{classKalman_9fb808cc94a4c2652e1fb93be9bb7dcf}

\begin{CompactList}\small\item\em cache of est.R \item\end{CompactList}\item 
\hypertarget{classBM_af00f0612fabe66241dd507188cdbf88}{
\hyperlink{classRV}{RV} \hyperlink{classBM_af00f0612fabe66241dd507188cdbf88}{rv}}
\label{classBM_af00f0612fabe66241dd507188cdbf88}

\begin{CompactList}\small\item\em Random variable of the posterior. \item\end{CompactList}\item 
\hypertarget{classBM_5623fef6572a08c2b53b8c87b82dc979}{
double \hyperlink{classBM_5623fef6572a08c2b53b8c87b82dc979}{ll}}
\label{classBM_5623fef6572a08c2b53b8c87b82dc979}

\begin{CompactList}\small\item\em Logarithm of marginalized data likelihood. \item\end{CompactList}\item 
\hypertarget{classBM_bf6fb59b30141074f8ee1e2f43d03129}{
bool \hyperlink{classBM_bf6fb59b30141074f8ee1e2f43d03129}{evalll}}
\label{classBM_bf6fb59b30141074f8ee1e2f43d03129}

\begin{CompactList}\small\item\em If true, the filter will compute likelihood of the data record and store it in {\tt ll} . Set to false if you want to save computational time. \item\end{CompactList}\end{CompactItemize}


\subsection{Detailed Description}
\subsubsection*{template$<$class sq\_\-T$>$ class EKF$<$ sq\_\-T $>$}

Extended \hyperlink{classKalman}{Kalman} Filter. 

An approximation of the exact Bayesian filter with Gaussian noices and non-linear evolutions of their mean. 

\subsection{Member Function Documentation}
\hypertarget{classBM_8a8ce6df431689964c41cc6c849cfd06}{
\index{EKF@{EKF}!logpred@{logpred}}
\index{logpred@{logpred}!EKF@{EKF}}
\subsubsection[logpred]{\setlength{\rightskip}{0pt plus 5cm}virtual double BM::logpred (const vec \& {\em dt}) const\hspace{0.3cm}{\tt  \mbox{[}inline, virtual, inherited\mbox{]}}}}
\label{classBM_8a8ce6df431689964c41cc6c849cfd06}


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

Reimplemented in \hyperlink{classARX_e7f9e7823aec9bf7ddc3b42d9b3304c4}{ARX}, \hyperlink{classMixEF_424ca64f36d4e41de7a7e7ae921d35ea}{MixEF}, and \hyperlink{classmultiBM_13e26a61757278981fd8cac9a7ef91eb}{multiBM}.

Referenced by BM::logpred\_\-m().\hypertarget{classBM_eb58c81d6a7b75b05fc6f276eed78887}{
\index{EKF@{EKF}!\_\-copy\_\-@{\_\-copy\_\-}}
\index{\_\-copy\_\-@{\_\-copy\_\-}!EKF@{EKF}}
\subsubsection[\_\-copy\_\-]{\setlength{\rightskip}{0pt plus 5cm}virtual {\bf BM}$\ast$ BM::\_\-copy\_\- (bool {\em changerv} = {\tt false})\hspace{0.3cm}{\tt  \mbox{[}inline, virtual, inherited\mbox{]}}}}
\label{classBM_eb58c81d6a7b75b05fc6f276eed78887}


Copy function required in vectors, Arrays of \hyperlink{classBM}{BM} etc. Have to be DELETED manually! Prototype: BM$\ast$ \hyperlink{classBM_eb58c81d6a7b75b05fc6f276eed78887}{\_\-copy\_\-()}\{\hyperlink{classBM}{BM} Tmp$\ast$=new Tmp(this$\ast$); return Tmp; \} 

Reimplemented in \hyperlink{classARX_5de61fbd4f97fa3216760b1f733f5af0}{ARX}.

Referenced by MixEF::init().

The documentation for this class was generated from the following file:\begin{CompactItemize}
\item 
work/git/mixpp/bdm/estim/\hyperlink{libKF_8h}{libKF.h}\end{CompactItemize}