|
MIT-3016 Analysis of Measurement Data 1, 7 cr |
Risto Ritala
Lecture times and places | Target group recommended to | |
Implementation 1 |
Periods 1 1 - 2 |
Examination and computer exercises. 20 % of homework exercises.
-
Develops capability to assess properties of systems by analyzing and computing characteristics of stochastic measurement signals and pairs of signals.
Content | Core content | Complementary knowledge | Specialist knowledge |
1. | Measurement as reflecting reality, probabilistic view. Measurement uncertainty. | Principles of Bayesian statistics and Bayesian measurement information theory. | |
2. | One and two variable normal distributions and their use in abnormality detection and state recognition. | ||
3. | Identification of statistical models by maximum likelihood or least mean squares. Motivation for identification methods. | General maximum likelihood / maximum a posteriori identification. | |
4. | Covariance function, spectrum and their non-parametric estimation. Effect of sampling on estimates. | Introduction to parametric spectrum estimation. Introduction to time series analysis. | Relationship between cross-covariance/spectrum and joint probability density function of time series. |
5. | Spectral analysis of linear dynamic and stochastic systems. |
Exam 0-30 points. 20% of homework exercises mandatory. By doing homework exercises, up to 5 bonus points for exam. Particpation in 4/5 computer exercises mandatory.
Numerical evaluation scale (1-5) will be used on the course
Prerequisite relations (Requires logging in to POP)There is no equivalence with any other courses
Description | Methods of instruction | Implementation | |
Implementation 1 | Lectures Excercises Practical works |
Contact teaching: 0 % Distance learning: 0 % Self-directed learning: 0 % |