Decision Support Systems

The course is a substitute for:

Decision Support Systems (E33SPR)
Decision Support Systems (X33SPR)

Lecturer:

Tutor:

Supervisor:

Department of Cybernetics

Synopsis:

Selected techniques and methods used by decision support systems are studied during the course like expert and knowledge-based systems, knowledge representation, knowledge management, semantical modelling, ucertainty processing, elements of modern data analysis and bayesian nets. Attention is paid to knowledge-based systems interpreting knowledge acquinted during a data mining process. Knowledge management techniques are applied to semantic modelling of information sources, including WEB-mining. Data warehouses are presented as a basis of the data mining process and geographic information systems are presented as representatives of information systems processing unstructured information.

Requirements:

Presence according general regulations, succesful test.

Syllabus of lectures:

1. Data, information, knowledge. Structured and non-structured information

2. Expert and knowledge-based systems

3. Knowledge representation

4. Uncertainty processing

5. Elements of modern data analysis

6. Bayesian nets

7. Knowledge-based systems and knowledge acquinted by data mining process

8. Data warehouses and their application to data mining

9. Knowledge management, semantical modelling

10. WEB-mining, semantic anotation of electronic information resources

11. Ontology-based deduction, semantic annotation-based localisation of information resources

12. Advanced techniques of information systems design

13. Information systems and non-structured information

14. Geographical information systems

Syllabus of tutorials:

1. Organization, safety, passing conditions

2. Simple decision problem formulation

3. Solving the problem using an expert system I

4. Solving the problem using an expert system II

5. Simple semantic network design

6. Solving a data analysis problem I

7. Solving a data analysis problem II

8. Solving a Bayesian net problem I

9. Solving a Bayesian net problem II, test

10. Design of a data warehouse for a given problem

11. Implementation of a data warehouse for a given problem

12. OLAP analyses on implemented data warehouse

13. Semantic annotations of selected URL

14. Locating URLs using semantic annotations and ontology

Study Objective:

Study materials:

[1] Hájek, P., Havránek, T., Jiroušek, R.: Uncertain Information Processing in Expert Systems. CRC Press, Inc. 1992

[2] Neapolitan, R. E.: Probabilistic Reasoning in Expert Systems: Theory and Algorithms. John Willey & Sons. New York, 1989

[3] Weiss, S. M.: Predictive Data Mining - A Practical Guide. Morgan Kaufmann Publishers, Inc., San Francisco, 1998

Note:

Further information:

No time-table has been prepared for this course

The course is a part of the following study plans:

• Computer Science and Engineering (elective course)