Main objectives of the course:
Identifying of time-series in variety of real situations. Finding proper time-series models. Solving basic recognition tasks, filtration, interpolation and prediction tasks, based on time-series analysis.
Course information sheet | |||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
University: University of Žilina | |||||||||||||
Faculty: Faculty of Management Science and Informatics | |||||||||||||
Course ID: 5US204 | Course name: Process Analysis (AP) | ||||||||||||
Form, extent and method of teaching activities: | |||||||||||||
Number of classes per week in the form of lectures, laboratory exercises, seminars or clinical practice | Lectures: 2.0 Seminars: 0.0 Lab.exercises: 2.0 | ||||||||||||
Methods by which the educational activity is delivered | Present form of education | ||||||||||||
Applied educational activities and methods suitable for achieving learning outcomes | |||||||||||||
Number of credits: 5.0 | |||||||||||||
Study workload: 125 hours Specification of the study workload: | |||||||||||||
Recommended term of study: 1. year, winter semester | |||||||||||||
Study degree: 2. | |||||||||||||
Required subsidiary courses: Prerequisites: Algebra, Discrete Probability Co-requisites: | |||||||||||||
Course requirements: Continuous assessment / evaluation: Continuous assessment: Working at term: 40% Semester work written: Exam: 60% The examination is a test of the theory and examples. For the test, it is possible to obtain 20 points of which must be at least 10 to continue the experimental section. For examples you can get 20 points of which must be received at least 10. Finally, add up the points gained through semester and during the test. Final assessment /evaluation: Rating points obtained by: 91-100 points A; 81-90 points B; 71-80 points C; 65-70 points D; 61-65 points E; less than 61 points FX. To enroll for an exam student must have 25 points. | |||||||||||||
Course outcomes: Identifying of time-series in variety of real situations. Finding proper time-series models. Solving basic recognition tasks, filtration, interpolation and prediction tasks, based on time-series analysis. | |||||||||||||
Course scheme: Lectures: 1. Main tasks and different applications of process analysis. Variety types of processes and process examples. Vector space (review: linear independence, basis, scalar multiplication, vector distance) 2. Vector space (review: orthogonal basis, basis transformation, basis orthoganalisation, vector projection into vector subspace). 3. Linear regression task solved using vector projection. Non-periodical trends. 4. Linearization of non linear problems. Moving average, prediction, and filtration. 5. Spectral analysis, discrete Fourier transformation. 6. Looking for periodical trends, filtration, shapes sharpening. 7. Random processes – basic terms. Vector space formed by random processes. 8. Karhunen – Loev’s random process decomposition. 9. Cluster analysis, signal compression, process recognition, and signal modulation. 10. Process analysis using linear system. 11. Spectral description of the linear system for process analysis, frequency domain description. 12. Processing of the speech signal using linear analysis method. Seminars and Laboratory work: The seminars content is similar to lectures in the separate weeks. The solved problems are small (processes with 3 or 4 values), next part is homework included same problem solving with bigger sized values, solved in computers. | |||||||||||||
Literature: Ondrej Šuch, Klimo, Martin ; Cimrák, Ivan ; Bachratá, Katarína: Analýza procesov lineárnymi metódami; Žilinská univerzita, 2012, ISBN 978-80-554-0556-8 Štulajter, F.: Odhady v náhodných procesoch, Alfa, 1990, Bratislava, Cipra T.: Statistická analýza časových řad s aplikacemi v ekonomii, SNTL/Alfa, 1986, F.Koschin: Statgrafics aneb statistika pro každého, Praha, Grada, 1992 | |||||||||||||
Instruction language: slovak | |||||||||||||
Notes: | |||||||||||||
Course evaluation:: Total number of evaluated students: 1
| |||||||||||||
A | B | C | D | E | FX | ||||||||
0.00 % | 0.00 % | 0.00 % | 100.00 % | 0.00 % | 0.00 % | ||||||||
Course teachers: | |||||||||||||
Last updated: 2022-07-31 19:12:14.713 | |||||||||||||
The person responsible for the course: doc. Mgr. Juraj Smieško, PhD. | |||||||||||||
Approved by: |