| Course Unit Code | 450-2029/01 |
|---|
| Number of ECTS Credits Allocated | 4 ECTS credits |
|---|
| Type of Course Unit * | Compulsory |
|---|
| Level of Course Unit * | First Cycle |
|---|
| Year of Study * | Third Year |
|---|
| Semester when the Course Unit is delivered | Winter Semester |
|---|
| Mode of Delivery | Face-to-face |
|---|
| Language of Instruction | Czech |
|---|
| Prerequisites and Co-Requisites | Course succeeds to compulsory courses of previous semester |
|---|
| Name of Lecturer(s) | Personal ID | Name |
|---|
| PRA132 | doc. Ing. Michal Prauzek, Ph.D. |
| Summary |
|---|
| The course is focused on the area of artificial intelligent methods application in engineering systems. It presents the sources and principles of artificial intelligence, introduces the classical and multivalue logics. The subject introduces the principles of spars knowledge using, principles of fuzzy mathematics, fuzzy logic and its application in modern expert systems and fuzzy controllers. It presents the principles of probability systems, neural networks and genetic algorithms and applications of this tools in modern cybernetics and robotics systems. |
| Learning Outcomes of the Course Unit |
|---|
The subject represents the introduction to the principles of scientific field of artificial intelligence. The goal of subject is introduce students on analysis and design of artificial intelligence tolls in the field of engineering.
Students will be ready for practical use of basic artificial intelligence tools namely fuzzy expert systems, artificial neural networks and genetic algorithms in their diploma works and next praxix. |
| Course Contents |
|---|
Lectures:
1. Introduction on artificial intelligence scientific field. Principles of artificial intelligence, importace of knowledge in problem solving tasks
2. Problem solving procedures in classical logic
3. Methods of computer knowledge reprezentation
4. Mathematic and linguistc modelling
5. Vagueness formalization of knowledge in linguistic models
6. Principles of fuzzy set and fuzy logic theory
7. Fuzzy models of Mandami type, fuzzy controllers Mandami type
8. Fuzzy models of Takagi-Sugeno type, T-S controlles
9. Diagnostic and planning expert systems
10. Probabilistic expert systems
11. Topology and functions of multilayer artificial neural networks
12. Genetic algorithms - versatil optimization methods
13. Neural network optimization using GA
14. Fuzzy controller optimization using GA
Laboratories:
1. Fuzzy controller using microcomputer
2. Fuzzy controller using PLC
Computer labs:
1. Computer system MATLAB, Fuzzy ToolBox
2. Fuzzy sets and vagueness objects reprezentation in MATLAB
3. Fuzzy conditonal rules formalization in MATLAB, fuzzy modelling of Mandami type
4. Fuzzy modelling of Takagi-Sugeno type in MATLAB
5. Fuzzy controllers of Mandami and T-S types
6. Diagnostic fuzzy expert systems
7. Fuzzy expert systems in practice
8. Probalilistic shell expert systém FEL-EXPERT
9. Neural network synthesis in Neural ToolBoxu of MATLAB
10. Neural controller
11. Real genetic algorithm synthesis in MATLAB
12. Fuzzy controller optimization using genetic algorithm
|
| Recommended or Required Reading |
|---|
| Required Reading: |
|---|
RUSSEL,S., NORVIG,P.: Artificial Intelligence, Prentice-Hall, Inc., 2003, ISBN 0-13-080302-2
LUGER,G.F., STUBBLEFIELD,W.A.: Artificial Intelligence, The Benjamin/Cummings Publishing Company, Inc., 2009, ISBN-13: 978-0-321-54589-3 ISBN-10: 0-321-54589-3
ZIMMERMANN,H.J. Fuzzy Set Theory - and Its Applications. Kluwer Academic Publishers, 2001. ISBN-13: 978-0792374350
|
POKORNÝ,M.,SROVNAL,V. Systémy s umělou inteligencí - Učební text a návody do cvičení. CZ.1.07/2.2.00/15.0113. VŠB - Technická univerzita Ostrava. Ostrava. 2012
VESELÝ,A. Úvod do umělé inteligence. ČZU Praha, 2005. ISBN 80-213-1361-7
JURA, P. Základy fuzzy logiky pro řízení a modelování. Brno: Nakladatelství VUTIUM, 2003, ISBN 80-214-2261-0.
|
| Recommended Reading: |
|---|
C. R. REEVES, J. E. ROW,. Genetic Algorithms: Principles and Perspectives. Kluwer Academic Publishers, New York, 2002.
GRAUPE,D. Principles of Artificial Neural Netvorks. World Scientific. 2013. ISBN: 978-981-4522-73-1
|
VOLNÁ,E. Neuronové sítě. Ostravská univerzita, Ostrava. 2008
HYNEK,J. Genetické algoritmy a genetické programování. Grada, 2008. ISBN: 978-80-247-2695-3
|
| Planned learning activities and teaching methods |
|---|
| Lectures, Individual consultations, Tutorials, Experimental work in labs, Teaching by an expert (lecture or tutorial) |
| Assesment methods and criteria |
|---|
| Task Title | Task Type | Maximum Number of Points
(Act. for Subtasks) | Minimum Number of Points for Task Passing |
|---|
| Graded credit | Graded credit | 100 (100) | 51 |
| Laboratorní práce | Laboratory work | 40 | 21 |
| Písemná práce | Written test | 60 | 30 |