EML 6934 (section 6385)  Fall 2009
Optimal Estimation
Instructor: Dr. Prabir Barooah
Ofce: MAEA 322
Email: pbarooah at uF.edu
Ofce Phone: 352.392.0614
Class time: period 4 (10:4011:30 am) MW±
Class location: MAEB 229
Ofce Hours: 11:30 am  12:30 pm, MW±
Course website
Please check the course website regularly ²or updates and announcements:
http://humdoi.mae.ufl.edu/
∼
prabirbarooah/EML6934F09.html
Teaching Assistant
Takashi Hiramatsu (takashi at uF.edu)
TA ofce hours: Th: 24 pm, location: MAE 224
Course Outline
The purpose o² this course is two²old : (1) provide a ³rm background in the mathematical basis o²
parameter and state estimation methods, and (2) provide training on how to (and how not to) apply
them in practice. The ³rst ²ew weeks o² the course will be an intense crash course in probability, in
which concepts such as random variables, density ²unctions, moments, etc. will be reviewed. A²ter
that, we will start with the problem o² estimating a vector o² parameters
θ
∈
R
n
²rom noisy mea
surements
z
=
H
θ
+
ǫ
, where
ǫ
is a measurement noise vector. We will then examine the general
problem o² estimating one random vector given the measurement o² another. ±inally, we will examine
the state estimation problem in which the state
x
k
o² the linear system
x
k
+1
=
A
k
x
k
+
B
k
u
k
+
w
k
,
y
k
=
C
k
x
k
+
θ
k
is to be estimated, where
w
k
and
θ
k
are noise sequences (called stochastic processes)
a´ecting the dynamic evolution and measurements.
Topics to be covered:
Review o² linear algebra: least squares solution o² linear equations and its application to parameter
estimation o² dynamical systems ²rom inputoutput data.
Review o² Probability and Random Variables. Combinatorics, Probability spaces, random variables,
density ²unctions, moments (esp. mean and variance), concepts related to multiple random variables,
joint density ²unctions, independence, conditional density, etc.
Best Linear Unbiased Estimator and Least Squares Estimator. Recursive Least Squares. Maximum
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview.
Sign up
to
access the rest of the document.
 Fall '08
 Staff
 Least Squares, Probability, Probability theory, Estimation theory, Kalman filter

Click to edit the document details