Course detail

Technical Applications of Artificial Intelligence Methods

FSI-RUI Acad. year: 2023/2024 Summer semester

The course consists of two parts. The first part deals with many-valued logic, theory of fuzzy sets and their applications in artificial intelligence. The second part consists of image processing and pattern recognition for applications in technology and science.

Learning outcomes of the course unit

Knowledge of multi-valued logic, fuzzy sets theory, linguistic models and expert systems used in technical applications. Knowledge of image processing, analysis and pattern recognition.

Prerequisites

Basic knowledge of mathematical logic, set theory and mathematical analysis

Planned learning activities and teaching methods

The course is taught through lectures explaining the basic principles and theory of the discipline. Exercises are focused on practical topics presented in lectures.

Assesment methods and criteria linked to learning outcomes

Course-unit credit based on written test.
The exam has a written and oral part.

Language of instruction

Czech

Aims

The aim of the course is to provide students with information about usage of multi-valued logic in technical applications and with computer image analysis and pattern recognition.

Specification of controlled education, way of implementation and compensation for absences

Attendance at seminars is controlled. An absence can be compensated via solving additional problems.

The study programmes with the given course

Programme N-MET-P: Mechatronics, Master's
branch ---: no specialisation, 5 credits, compulsory

Programme N-IMB-P: Engineering Mechanics and Biomechanics, Master's
branch BIO: Biomechanics, 5 credits, compulsory-optional

Programme N-IMB-P: Engineering Mechanics and Biomechanics, Master's
branch IME: Engineering Mechanics, 5 credits, compulsory-optional

Type of course unit

 

Lecture

26 hours, optionally

Teacher / Lecturer

Syllabus

1. Multi-valued logic, formulas, truth evaluation
2. T-norms, T-conorms, generalized implications
3. Fuzzy sets and operations with them
4. Linguistic variables, linguistic models, control systems
5. Expert systems based on multi-valued logic
6. Classical and digital photography
7. CCD a CMOS technology
8. Noise, classification, analysis, filtration
9. MTF a PSF, convolution, deconvolution
10. Fourier methods of image processing
11. Adaptive filters, image segmentation
12. Classification of objects and pattern recognition
13. Classification of objects and pattern recognition

Computer-assisted exercise

26 hours, compulsory

Teacher / Lecturer

Syllabus

1. Multi-valued logic, formulas, truth evaluation
2. T-norms, T-conorms, generalized implications
3. Fuzzy sets and operations with them
4. Linguistic variables, linguistic models, control systems
5. Expert systems based on multi-valued logic
6. Classical and digital photography
7. CCD a CMOS technology
8. Noise, classification, analysis, filtration
9. MTF a PSF, convolution, deconvolution
10. Fourier methods of image processing
11. Adaptive filters, image segmentation
12. Classification of objects and pattern recognition
13. Classification of objects and pattern recognition