spring 2013

FYS-2007 Statistical signal theory - 10 stp


Last changed: 01.03.2014

The course is administrated by

The course is administrated by

Faculty of Science and Technology
Admission requirements

Admission requirements

The course is available as a singular course. Admission requirements are generell studiekompetanse + REALFA.

Local admission, application code 9336 - enkeltemner i realfag.

The course is also available to exchange students and free-movers.
Course contents

Course contents

The course covers probability theory, random variables and vectors and their probability density functions. Transformations of random variables are discussed, including principal component analysis (whitening). Random time signals are treated in detail, and their characterization in terms of statistical stationarity, correlation functions and power spectral densities, using Fourier transforms, is analyzed. Several different approaches for estimation of correlation functions and power spectral densities based on measurements are developed, and applications e.g. to radar (distance to object) are discussed. Exercises and problem solving, in addition to practical statistical signal processing using programming, are strongly emphasized. Basic programming skills are advantageous.
Recommended prerequisites

Recommended prerequisites

FYS-2006 Signal processing, MAT-1003 Calculus 3, MAT-1004 Linear algebra, STA-1001 Probability and statistics 1
Objective of the course

Objective of the course

Knowledge - The student will be able to:

  • understand probability theory and the characterization of random variables
  • describe the concept of a stochastic process and relate it to noise in measured signals
  • characterize stochastic processes in terms of stationarity, correlation function and power spectral densities

identify relevant estimation procedures

Skills - The student will be able to:

  • calculate probabilities, also by integration over probability density functions
  • analyze stochastic time signals (processes) in terms of correlation and power
  • process discrete-time measurements of a random signals using programming
  • analyze the outcome of the processing in terms of the estimation tools used

General expertise - The student will be able to:

  • appreciate the importance of statistical signal theory in society
  • is able to work with statistical signal processing for data analysis
  • program scripts and functions in Matlab
Language of instruction

Language of instruction

The language of instruction is English and all of the syllabus material is in English. Examination questions will be given in English, but may be answered either in English or a Scandinavian language.
Teaching methods

Teaching methods

Lectures: 40 hours
Exercises: 40 hours
Assessment

Assessment

Portfolio assessment of a take-home examination counting about 25 % and a final 4 hour written examination counting about 75 %. All components in the portfolio are assessed as a whole and one combined grade is given.

Assessment scale: Letter grades A-F.

Re-sit examination (section 22):
Students having failed the last ordinary examination are offered a re-sit examination early in the following semester, if the course is compulsory in their study programme, otherwise given that an examination is already being arranged. 4 hour written examination counting 100 %.

Postponed examination (sections 17 and 21):
Students with valid grounds for absence will be offered a postponed examination. Postponed take-home examination is arranged during the semester if possible, otherwise early in the following semester. Postponed written examination is held early in the following semester.

New ordinary examination (section 25):
A new ordinary examination in the teaching-free semester is not offered.

See indicated sections in Regulations for examinations at the University of Tromsø for more information.

Coursework requirements
Access to the final examination requires submission of take-home examination.
Date for examination

Date for examination

One written 30.05.2013

The date for the exam can be changed. The final date will be announced at your faculty early in May and early in November.

Schedule

Schedule


Course overlap

Course overlap

FYS-261 Statistics signal theory 9 stp
Recommended reading/syllabus

Recommended reading/syllabus

Textbook:
"Probability and Random Processes with Applications to Signal Processing", Henry Stark and John W. Woods, 3rd edition, Prentice Hall, 2001

Syllabus and reading list are available in Fronter, or by contacting the teacher or the student adviser.
Lectures Spring 2013
First attendance Tue 8th of January 11:15 - Auroral Observatory AUD
Lectures Prof. Svein Ketil Jacobsen
Exercises Stip. Lene Østvand


Contact