Newsgroups: sci.engr.control,comp.ai.neural-nets,sci.stat.math
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!MathWorks.Com!europa.eng.gtefsd.com!howland.reston.ans.net!pipex!uunet!hearst.acc.Virginia.EDU!murdoch!uvacs.cs.Virginia.EDU!alb
From: alb@uvacs.cs.Virginia.EDU (Allen L. Barker)
Subject: tutorial techrep available: "Bayesian Est. & the Kalman Filter"
Message-ID: <CxnzGv.Cyt@murdoch.acc.Virginia.EDU>
Originator: alb@agate.cs.Virginia.EDU
Sender: usenet@murdoch.acc.Virginia.EDU
Organization: University of Virginia Computer Science Department
Date: Fri, 14 Oct 1994 13:14:54 GMT
Lines: 38
Xref: glinda.oz.cs.cmu.edu sci.engr.control:3215 comp.ai.neural-nets:19456 sci.stat.math:2896


An informal tutorial/introduction to some basic Bayesian estimation
results leading to the Kalman filter is available in our recent
techreport

   Barker,Brown & Martin "Bayesian Estimation and the Kalman Filter",
      Techreport IPC-94-02, UVA, 1994.

It does assume a basic knowledge of multivariate densities.  The 
appendix contains some Mathematica code implementing the Kalman 
filter for one of the examples (not especially *good* code, though!).  
The abstract follows, followed by instructions for getting a copy
by FTP.


\begin{abstract}
  In this tutorial article we give a Bayesian derivation of a basic state 
  estimation result for discrete-time
  Markov process models with independent process and measurement noise and
  measurements not affecting the state.  We then list some properties
  of Gaussian random vectors and show how the Kalman filtering algorithm
  follows from the general state estimation result and a linear-Gaussian
  model definition.  We give some illustrative examples including 
  a probabilistic Turing machine, dynamic classification, and tracking
  a moving object.
\end{abstract}

To get the paper by FTP
-------------------------
FTP to uvacs.cs.virginia.edu by typing
   ftp uvacs.cs.virginia.edu
and log in as user "anonymous".  Then type
   cd pub/techreports
   get IPC-94-02.ps.Z
and that should get the compressed postscript
file.  You can then print the file on a postscript
printer as, for example
   zcat IPC-94-02.ps.Z | lpr
