Research Investigation Topics (George Magoulas)

• TOPIC 1: Knowledge-based neurocomputing in user-adaptive systems
  • Description: In neural expert systems or knowledge-based neurocomputing, as it is the name that is used now, the emphasis is on the use and representation of knowledge about an application within a neurocomputing paradigm. Despite the powerful processing capabilities of a neurocomputing system, explicit modelling of the knowledge represented by that system remains a major research topic. The aim of this project is to present this area, cover the state-of-the-art of knowledge-based neurocomputing in an accessible way, and provide examples from the literature that show how knowledge-based neural networks have been used in user modelling and adaptive web systems.
  • Search keywords: hybrid systems, neuro-fuzzy systems, knowledge-based neurocomputing, adaptive web systems, personalisation
  • Indicative literature
    • Stathacopoulou R., Magoulas G. D., Grigoriadou M. and Samarakou M., Neuro-fuzzy knowledge processing in intelligent learning environments for improved student diagnosis, Information Sciences, 170, 2, 273-307, 2005.
    • Frias-Martinez E., Magoulas G.D., Chen S., and Macredie R. Recent Soft Computing Approaches to User Modeling in Adaptive Hypermedia. In Paul De Bra, Wolfgang Nejdl (eds), Adaptive Hypermedia and adaptive web-based systems, Proceedings of 3rd Int Conf Adaptive Hypermedia-AH 2004, Eindhoven, The Netherlands, Aug. 2004, Lecture Notes in Computer Science, vol. 3137, Springer, 104-113.
    • Magoulas G. D. , Papanikolaou K. and Grigoriadou M., Towards a computationally intelligent lesson adaptation for a distance learning course, in Proceedings of the IEEE International Conference on Tools with Artificial Intelligence, 5-11, Chicago, November 1999.
    • Magoulas G.D. , Papanikolaou K.A., and Grigoriadou M. Neuro-fuzzy Synergism for Planning the Content in a Web-based Course, Informatica, vol. 25, 39-48, 2001.
    • Relevant articles in the journals IEEE Tr. Neural Networks, Neurocomputing, Neural Computing and Applications, Neural Networks, User Modeling and User-Adapted Interaction, the User Modeling COnference, the Adaptive Hypermedia Conference and in the ACM Digital Library.

• TOPIC 2: Natural computing in User-adaptive/personalised systems
  • Description: Natural computing, i.e. approaches that use genetic algorithm, evolutionary algorithms, swarm intelligence, have been recently applied to personalised systems and the adaptive web. The aim of this project is to present the state-of-the-art in this area in a comprehensive way, providing examples from the literature that show how natural computing approaches are used for user modelling and personalisation.
  • Search keywords: web search, genetic algorithms, evolutionary algorithms, web information retrieval, swarm intelligence, adaptive web systems, personalisation
  • Indicative literature
    • Zacharis N, and Panayiotopoulos T. (2001). Web search using genetic algorithms, IEEE Internet Computing, March-April, 18-26.
    • Frias-Martinez E., Magoulas G.D., Chen S., and Macredie R. Recent Soft Computing Approaches to User Modeling in Adaptive Hypermedia. In Paul De Bra, Wolfgang Nejdl (eds), Adaptive Hypermedia and adaptive web-based systems, Proceedings of 3rd Int Conf Adaptive Hypermedia-AH 2004, Eindhoven, The Netherlands, Aug. 2004, Lecture Notes in Computer Science, vol. 3137, Springer, 104-113.
    • http://wwwis.win.tue.nl/ah/
    • Relevant articles in the journals IEEE Tr. Neural Networks, IEEE Tr. Evolutionary Computation, Neurocomputing, Neural Computing and Applications, Neural Networks, Natural Computing, IEEE Intelligent Systems, IEEE Internet Computing, User Modeling and User-Adapted Interaction, the User Modeling COnference, the Adaptive Hypermedia Conference and in the ACM Digital Library.

• TOPIC 3: Algorithms for Training Neural Networks
  • Description: Learning from data using neural networks is considered as one of the most popular approaches to adaptive modelling. The project will review recent approaches to learning for neural networks from 1999 onwards. The review would be based on articles published in the top five neural networks journals (IEEE Tr. Neural Networks, Neural Networks, Neural Computation, Neurocomputing, Neural Computing and Applications) and conference articles.
  • Search keywords: learning algorithms, training algorithms, neural networks, multilayer perceptrons, backpropagation, feedforward neural networks, self-organising maps, recurrent networks