ee 650

EE 650 Introduction to Estimation
Autumn 2003

Instructor: Prof. Andrea Serrani.
Office: 412 Dreese Lab.

Office hours: By appointment (email: serrani@ee.eng.ohio-state.edu) is preferred, but feel free to knock at my door anytime.

Prerequisite(s): Basic knowledge of probability and random variables, discrete-time systems, z-transforms, signals and systems basics: EE 352, and Math 530 or Stat 427.

Please note: The official web page of the course is developed on WebCT at class.osu.edu
Registered students may access all the additional information on the course, including notes, homework sets, solutions, and the update syllabus through the WebCT system.

Textbook and useful references:

J.M. Mendel, Lessons in Estimation Theory for Signal Processing, Communications, and Control, Prentice Hall, 1995.
I.B. Rhodes, "A tutorial introduction to estimation and filtering", IEEE Transactions on Automatic Control Vol. AC-16, no.6, p.688-706, 1971.

E.W. Kamen and J.K. Su, Introduction to Optimal Estimation, Springer Verlag 1999.
A. Gelb, editor, Applied Optimal Estimation, M.I.T. Press, 1974.
A. Papoulis and S.U. Pillai, Probability, Random Variables, and Stochastic Processes (4th Edition), Mc-Graw Hill, 2002.
V. Strejc, "Least squares parameter estimation", Automatica Vol. 16, 5, pp. 535-550, September, 1980.
K. J. Astrom, "Maximum likelihood and prediction error methods", Automatica Vol. 16, 5, pp. 551-574, September, 1980.

Grading: 30% homework, 30% midterm, 40% final examination.

Homework policy: Homework are generally posted each Wednesday or Friday, and due Friday of the following week. No late submission accepted, unless previous agreements have been made. Homework sets will not be distributed in class: students are required to download and their homework from the WebCT site of the class.

Course description

The course introduces the students to parameter estimation and state estimation in linear systems. Topics include: linear dynamic systems with random inputs, least squares estimation, mean-squared estimation, maximum likelihood,and Kalman filtering with applications in electrical engineering.

Topics

1. Basic probability theory. Linear estimation models

2. Batch least squares.

3. Recursive least squares.

4. Properties of estimators.

5. Properties of LS estimators.

6. Best linear unbiased estimators.

7. Maximum likelihood estimators.

8. Gaussian Random Variables (review).

9. Minimum variance estimators. Conditional expectation.

10. Properties of minimum variance estimators.

11. State estimation: Kalman predictor.

12. State estimation: Kalman filter.

13. Extended Kalman filter.

14. Kalman-Bucy filter.

Return to Andrea Serrani's home page