Intelligent Systems for Decision Support
Objectives
The aim of this course is to teach students the theoretical foundations of artificial intelligence, systems architecture and the main approaches used in intelligent systems. Particular emphasis is given to the basic principles of approximate reasoning based on fuzzy logic and its application to modeling, control and decision making, combining qualitative and quantitative data. The case studies reflect situations of decision making in uncertain and/or complex environments in the context of Industrial Engineering.
General characterization
Code
10612
Credits
3.0
Responsible teacher
Isabel Maria Nascimento Lopes Nunes, Pedro Emanuel Botelho Espadinha da Cruz
Hours
Weekly - 2
Total - 36
Teaching language
Português
Prerequisites
Not required.
Bibliography
R. Sharda, D. Delen, e E. Turban, Analytics, data science, & artificial intelligence, Eleventh edition. Hoboken, NJ: Pearson, 2020.
J. Gama, A. P. de L. Carvalho, K. Faceli, A. C. Lorena, e M. Oliveira, Extração de Conhecimento de Dados, 3aEdição. Edições Sílabo, 2017.
V. Kotu e B. Deshpande, Predictive analytics and data mining: concepts and practice with RapidMiner. Amsterdam: Elsevier/Morgan Kaufmann, 2015.
M. Hofmann e R. Klinkenberg, Eds., RapidMiner: Data Mining Use Cases and Business Analytics Applications, 0 ed. Chapman and Hall/CRC, 2016. doi: 10.1201/b16023.
M. Sànchez-Marrè, Intelligent Decision Support Systems. Cham: Springer International Publishing, 2022.
T. J. Ross, Fuzzy Logic with Engineering Applications, 4th Edition. Wiley, 2017.
Teaching method
Theoretical-practical classes with a duration of 2h. Oral presentation of concepts, supported by multimedia teaching materials and accompanied by application to concrete cases where students take part individually or in groups.
Evaluation method
The evaluation process has the following components:
- 2 practical project assignments (TP1 and TP2), with oral discussion and with a written technical report (35%)
- 1 mid-term test during the course (T) (30%)
The formula for the calculation of the final grade:
- Final Grade = 30%T + 30%TP1 + 40%TP2
To succeed students must obtain:
(TP1,TP2 >=9.5 V) AND T >= 9.5 V)
Students must do 2 project assignments (TP) to be eligible to perform a test and or exam.
1 Exam (for students without approval in the written test).
Subject matter
1.Introduction to Artificial Intelligence
1.1. AI paradigms
1.2. AI in decision support
2. Decision Support Systems (DSSs) and Intelligent Decision Support Systems (IDSSs)
2.1. Decision theories and frameworks
2.2. Evolution of DSSs and IDSSs
2.3. Types of IDSSs
2.4. DSS and IDSS architectures
3. Expert Systems (ES)
3.1. ES Architecture and Components
3.2. Knowledge Management Frameworks
3.3. Knowledge Engineering Process
3.4. ES Programming using ES Shells
4. Knowledge Discovery from Data
4.1. Learning methods
4.2. Hypothesis induction, inductive bias and representation bias
4.3. Supervised and unsupervised algorithms
4.4. Decision Trees (ID3 and ID4.5 algorithms)
4.5. Rule Induction and tree-to-rules algorithms
4.6. Association Rules
4.7. Text Mining (TF-IDF, text processing, document classification)
4.8. Performance measurement
4.9. Ensemble methods
5. Approximate Reasoning with Fuzzy Logic
5.1. Fuzzy Logic fundamentals
5.2. Fuzzy Sets and membership functions
5.3. Fuzzy Operators and Rule-based reasoning
5.4. Fuzzy Inference – Mamdani and Sugeno methods
5.5. Designing Fuzzy Systems for decision support
6. Industrial Engineering applications