Computational Intelligence – Intelligent Systems

Module Information

Module Semester:
3
Module Part:
Theory
Sub-Module Code:
ΜΔΕ-Γ1
Hours per Week:
3
Module ECTS Credits:
7.5
Available to ERASMUS Students:
No
Module Staff:


Module Objective

The course aims at: (a) providing a solid theoretical grounding and practical skills, along with in-depth knowledge regarding main notions of computational intelligence, (b) establishing the importance of these scientific fields in computer science, as well as the wide range of their applications in computing systems. The course’s objectives include introducing concepts, models, algorithms, and tools for development of intelligent systems. Emphasis is put on studying real-world applications as well as acquiring hands-on experience and becoming familiar with dedicated software packages (MATLAB, WEKA).


Module Study Targets

Upon completion of the course, the postgraduate student:

  • should be able to perform full analysis and training of neural networks and neurufuzzy models, having acquired in-depth knowledge of their functionality
  • will have become familiar with evolutionary algorithms. Support vector machines and particle swarm optimization techniques
  • will have been acquainted with major applications of computational intelligence-based intelligent systems in the areas of informatics, telecommunications and biomedical engineering
  • will have studied test-case of industrial applications of intelligent systems
  • will have got hands-on experience and will have been familiarized with dedicated software packages


Module Description

  • Neural Networks (supervised and unsupervised learning)
  • Fuzzy learning and fuzzy/neurofuzzy systems
  • Support Vector Machines
  • Particle Swarm Optimization
  • Evolutionary algorithms, genetic programming
  • Intelligent methods for telecommunications fraud detection
  • Intelligent noise cancellation filters for audio signals
  • Intelligent methods for satellite image processing
  • Intelligent systems for biomedical signal processing

Module Student Evaluation

Written exam: 60%

Projects (2): 20% + 20%


Bibliography

  • R. Babuska, "Computational Intelligence in Modelling and Control", Delft University of Technology, 2009
  • W. Banzhaf, P. Nordin, R. Keller, F. Francone, "Genetic Programming – An Introduction", Morgan Kaufmann Publishers, 1998
  • E. Cox, "Fuzzy Modeling and Genetic Algorithms for Data Mining and Exploration", Morgan Kaufmann Publishers, 2005
  • A.P. Engelbrecht, "Fundamentals of Computational Swarm Intelligence", John Wiley & Sons, 2006
  • A.P. Engelbrecht, "Computational Intelligence: An Introduction", 2nd Edition, Wiley, 2007
  • Hopgood, "Intelligent Systems for Engineers and Scientists", CRC Press, 3rd edition, 2011
  • K.A. de Jong, "Evolutionary Computation", MIT Press, 2002
  • F. Karray, C. De Silva, "Soft Computing and Intelligent Systems Design", Addison Wesley, 2004
  • S. Rajasekaran, G. Vijayalakshmi, "Neural Network, Fuzzy Logic, and Genetic Algorithms: Synthesis and Applications", PHI Editions, 2013
  • T. Ross, "Fuzzy Logic with Engineering Applications", John Wiley & Sons, 2010
  • R. Schalkoff, "Intelligent Systems: Principle, Paradigms and Pragmatics", Jones & Bartlett Learning, 2009
  • B. Schuller, "Intelligent Audio Analysis", Springer, 2013
  • L. Tsoukalas, R. Uhrig, "Fuzzy and Neural Approaches in Engineering", John Wiley & Sons, 1997