Subject Description Form

Subject Code EIE557

Subject Title Computational Intelligence and Its Applications

Credit Value 3

Level 5

Pre-requisite/ Nil
Co-requisite/
Exclusion
Objectives The subject aims to introduce students to
(i) fundamentals of key intelligent systems technologies including knowledge-based
systems, neural networks, fuzzy systems, and evolutionary computation, and
(ii) practice in integration of intelligent systems technologies for engineering
applications.
Intended Learning Upon completion of the subject, students shall be able to
Outcomes a. Gain a working knowledge of knowledge-based systems, neural networks, fuzzy
systems, and evolutionary computation;
b. Apply intelligent systems technologies in a variety of engineering applications;
c. Implement typical computational intelligence algorithms in MATLAB;
d. Present ideas and findings effectively; and
e. Think critically and learn independently.

Subject Synopsis/ 1. Introduction to Computational Intelligence

Indicative Syllabus 1.1. Intelligence machines
1.2. Computational intelligence paradigms
1.3. Short history
2. Rule-Based Expert Systems and Fuzzy Expert Systems
2.1 Rule-based expert systems
2.2 Uncertainty management
2.3 Fuzzy sets and operations of fuzzy sets
2.4 Fuzzy rules and fuzzy inference
2.5 Fuzzy expert systems
2.6 Case Studies
3 Artificial Neural Networks
3.1 Fundamental neurocomputing concepts: artificial neurons, activation
functions, neural network architectures, learning rules
3.2 Supervised learning neural networks: multi-layer feedforward neural
networks, simple recurrent neural networks, time-delay neural networks,
supervised learning algorithms
3.3 Unsupervised learning neural networks: self-organizing feature maps
3.4 Radial basis function networks
3.5 Deep neural networks and learning algorithms
3.6 Case studies
4 Evolutionary computation
4.1 Chromosomes, fitness functions, and selection mechanisms
4.2 Genetic algorithms: crossover and mutation
4.3 Genetic programming
4.4 Evolution strategies
 4.6 Case studies
5 Hybrid Intelligent Systems
5.1 Neural expert systems
5.2 Neuro-fuzzy systems
5.3 Evolutionary neural networks

Teaching/Learning Lecture/case studies (leaning outcomes a and b)

Methodology • fundamental principles and key concepts of the subject are delivered to
students;
• guidance on further readings, applications and implementation is given.

The formal lectures will be accompanied by case studies of successful real-world

engineering applications of intelligent systems technologies.

Tutorial (learning outcomes a and b)

• students will be able to clarify concepts and to have a deeper understanding of
the lecture material;
• problems and application examples are given and discussed.

Laboratory exercises (learning outcomes a - e)

Students will make use of the software tools and MATLAB to develop simple
computational intelligence systems.

Teaching/Learning Intended Subject Learning Outcomes

Methodology
a b c d e
Lectures  
Tutorials   
Laboratories     
Assignments    

Assessment
Methods in Specific assessment % Intended subject learning outcomes to be
Alignment with methods/tasks weighting assessed (Please tick as appropriate)
Intended Learning
a b c d e
Outcomes
1. Test 30%    

2. Final examination 50%    

3. Laboratories 20%
(including report   
writing)

Total 100%
 Student Study Class contact:
Effort Expected
 Lecture 26 Hrs.

 Tutorial 7 Hrs.

 Laboratory 6 Hrs.

Other study efforts:

 Self-learning 36 Hrs.

 Assignments, laboratory report writing 18 Hrs.

Total student study effort 93 Hrs.

Reading List and 1. M. Negnevitsky, Artificial Intelligence: A Guide to Intelligent Systems, 3rd
References Edition, Pearson/Addison Wesley, 2011.
2. A.P. Engelbrecht, Computational Intelligence: An Introduction, 2nd Edition, John
Wiley & Sons, 2012.
3. H.K. Lam, S.S.H. Ling, and H.T. Nguyen, Computational Intelligence and Its
Applications: Evolutionary Computation, Fuzzy Logic, Neural Network and
Support Vector Machine, Imperial College Press, 2011.
4. E. Turban, J. E. Aronson, T.-P. Liang, Decision Support Systems and Intelligent
Systems, 8th Ed., Pearson Prentice Hall, 2012.
5. E. Cox, The Fuzzy Systems Handbook, Boston: AP Professional, 1998.
6. S. Russell and P. Norvig. Artificial Intelligence – A Modern Approach, Prentice
Hall, 2010.
7. S. Haykin, Neural Networks – A Comprehensive Foundation, Prentice Hall, 1999.
8. N. Baba and L.C. Jain, Computational Intelligence in Games, Heidelberg; New
York: Physica-Verlag, 2001.
9. F.F. Soulie and P. Gallinari (Editors), Industrial Applications of Neural Networks,
Singapore; River Edge, NJ: World Scientific, 1998.
10. S. Chen (editor), Evolutionary computation in economics and finance, Heidelberg;
New York: Physica-Verlag, 2002.
11. R.J. Jr., Bauer, Genetic Algorithms and Investment Strategies, John Wiley & Sons,
1994.
12. H.J. Zimmermann et al (Editors), Advances in Computational Intelligence and
Learning: Methods and Applications, Boston: Kluwer Academic Publishers, 2002.
13. L.C. Jain and P. de Wilde (Editors), Practical Applications of Computational
Intelligence Techniques, Boston: Kluwer Academic Publishers, 2001.

June 2016