Table 3.3j: Summary of information on MITM613
1. / Name of Course: Intelligent Systems2. / Course Code: MITM613
3. / Name(s) of Academic Staff: Dr. Abdul Rahim Ahmad
4. / Rationale for the inclusions of the course in the programme:
1.To provide understanding of intelligent systems, the methods and the tools for implementing Intelligent Systems.
2.To enable students to compare the pros and cons of each method of Intelligent Systems.
3.To enable students to design Intelligent system based on methods learned.
4.To develop the ability to implement an intelligent system based on methods learned.
5. / Semester and Year offered: Semester 2
6. / Total Students Learning Time (SLT)
182 hours / Face to Face / Total
L= Lecture
T= Tutorial
P= Practical
O= Others / L
12
X
14 / T
0 / P
14 / O
0 / 182
7. / Credit value: 3
8. / Prerequisite (if any): N/A
9. / Objectives:
Upon completion of programme, students should be able to:
- Explain the various methods of implementing Intelligent systems
- Describe the issues involved in each method of implementing an Intelligent System.
- Describe the tools that can be used.
- Develop a particular intelligent system of choice in a class project environment.
10. / Learning Outcomes:
- Define the terminologies commonly used in Artificial Intelligence (AI) and Intelligent Systems
- Describe the different methods of AI and Intelligent Systems namely the knowledge base system and the computational learning systems.
- Analyzeexisting knowledge based system and computational learning system.
- Design knowledge based system and / or learning system such as expert system and prediction system.
- Use various tools for implementation and development of knowledge based system and / or learning system.
- Implement an expert system by building the knowledge base and the inferencing engine using Prolog programming language and implement a prediction system using methods such as neural network or Support vector machine.
11. / Transferable skills:
- Decision making skill
- Synthesis skills
- Effective communication skill
- Critical and analytical skills
- Qualitative and Quantitative skills
12. / Teaching-learning and assessment strategy
Overall in the course, students will be exposed to various aspects of artificial intelligent system. As Artificial Intelligent (AI) itself meant differently to different people, depending on their field of expertise and study, students will be introduced to all these different ideas and opinions. Generally, most people in AI agreed to the division of AI into knowledge based (where intelligence are entered or built into the system by gathering the information from experts) and the computational intelligent system (where intelligence are computed into a model based on a lot of past data available). Students will be given papers to read and compare the methods that have been used so far and then write up reports for the assignments. Emphasis is put on experiential learning and interactive discussions where students need to present their findings in class. The course is intended to be theoretical as well as practical. To gain some practical knowledge, students are required to produce prototype systems for knowledge based and computational based AI.
In completing the course assignment and tasks, students are required to work individually and/or as a group to be involved in problem-solving and making decisions. Students’ knowledge and ability are also tested in case studies, projects, interactive discussions, mid-term examination and final examination.
13. / Synopsis
This course emphasises on the methods and tools that can be used to develop intelligent systems. The tools can be divided into knowledge-based tools, computational intelligence tools and a hybrid of both. Knowledge based systems include expert and rule-based system, object-oriented and frame-based systems and intelligent agents. Computational intelligence includes neural networks, genetic algorithms and further optimization algorithms. Fuzzy logic, a technique which can handle uncertainties is a hybrid of both. Intelligent systems enabled a range of problems to be tackled more effectively.
14. / Mode of delivery:
Lectures, interactive discussions and system development, presentation.
15. / Assessment Methods and Types
Assignments / 15
Project / 15
Mid Semester exam / 30
Final examination / 40
100
Assessment methods / CO
1 / CO
2 / CO
3 / CO
4 / CO5 / CO
6 / CO
7 / CO
8
Final examination / X / X / X / X / X / X / X / X
MidSemester / X / X / X / X
Assignment / X / X / X / X / X / X / X / X
Project / X / X / X / X / X / X / X / X
16. / Mapping of the course to the Programme Outcomes (PO)*
1- Slightly 2- Moderately 3- Substantive
Course Outcomes (CO) / PO1 / PO2 / PO3 / PO4 / PO5 / PO6 / PO7 / PO8
- Define the terminology commonly used in Artificial Intelligence (AI) and Intelligent Systems
- Describe the different methods of AI and Intelligent Systems namely the knowledge base system and the computational learning systems.
- Analyze existing knowledge based system and computational learning system.
- Design knowledge based system and / or learning system such as expert system and prediction system.
- Use various tools for implementation and development of knowledge based system and / or learning system.
- Implement an expert system by building the knowledge base and the inferencing engine using Prolog programming language
- and implement a prediction system using methods such as neural network or Support vector machine.
*Please refer to:
Appendix I – Programme Outcomes 1 – 10
Appendix II – Program Educational Outcomes 1 – 4
Appendix III – CO-PO Matrix
17. / Mapping of the course to the Programme Educational Outcomes (PEO)*
1- Slightly 2- Moderately 3- Substantive
Course Outcomes / PEO 1 / PEO 2 / PEO 3 / PEO 4 / PEO 5 / PEO 6
- Define the terminology commonly used in Artificial Intelligence (AI) and Intelligent Systems
- Describe the different methods of AI and Intelligent Systems namely the knowledge base system and the computational learning systems.
- Analyze existing knowledge based system and computational learning system.
- Design knowledge based system and / or learning system such as expert system and prediction system.
- Use various tools for implementation and development of knowledge based system and / or learning system.
- Implement an expert system by building the knowledge base and the inferencingengine using Prolog programming language
- Implement a prediction system using methods such as neural network or Support vector machine.
*Please refer to:
Appendix I – Programme Outcomes 1 – 10
Appendix II – Program Educational Outcomes 1 – 4
Appendix III – CO-PO Matrix
18. / Content outline of the course and the SLT per topic
Week / Topics / Notes/References
1 / 1.IntroductiontoIntelligentSystems
·Knowledge-based systems and computational intelligence
· Expert and rule-based systems
· Intelligent agents
·Neural networks, genetic algorithms
· Further optimization algorithms
· Fuzzy logic / Refer Hopgood
2.Rule-basedSystems
· Rules and facts, rule examination and rule firing
· Consistency and assumptions
· Forward chaining
· Conflict resolution
· Backward chaining / Refer Hopgood
3.Uncertainty
· Bayesian updating
· Certainty theory
· Possibility theory: fuzzy sets and fuzzy logic / Refer Hopgood
4.IntelligentAgents
· Agents and objects
· Agent architectures
· Multi-agent system / Refer Hopgood
5.SymbolicLearning
· Learning by induction
· Case based reasoning / Refer Hopgood
6.SoftComputing
· Neural Network
· Support Vector Machine
· Other soft computing methods / Refer Hopgood
7.HybridSystems
· Genetic-fuzzy systems
·Neuro-fuzzy systems
· Genetic neural systems / Refer Hopgood
8.Toolsandlanguages
· Expert System shell
· Toolkit and libraries
· AI Languages / Refer Hopgood
9.CurrentTrendsandIssuesinIntelligentSystems
·Discussion on local and international researches on Intelligent Systems based on Journal papers
· Application areas
· Technologies used
· Problems faced
· Proposed solutions
10. CaseStudy/Project
·Proposal and report writing or Project on simulation model of a simple intelligent system
19. / Main references supporting the course
- Adrian A. Hopgood, Intelligent Systems for Engineers and Scientists, 2nd Edition, CRC Publication (2000).
- Michael Negnevitsky, Artificial Intelligence: A Guide to Intelligent Systems, 2nd Edition, Addison Wesley (2004).
- Selected papers and journal articles used for assignment, analysis, classroom discussion and case study purposes.
20. / Other Additional Information