Publications (3)0 Total impact
Conference Proceeding: Student Representation Assisting Cognitive Analysis.[show abstract] [hide abstract]
ABSTRACT: A central concern when developing intelligent tutoring systems is student representation. This paper introduces work-in-progress on producing a scheme that describes various imprecision in student knowledge. The scheme is based on domain representation through multiple generalized constraints. The adopted approach to domain and student representation will facilitate cognitive analysis performed as propagation of generalized constraints. Qualitative reasoning provides the basis for the approach and Zadeh’s computational theory of perception complements the technique with the ability to process perception-based information.Intelligent Tutoring Systems, 7th International Conference, ITS 2004, Maceiò, Alagoas, Brazil, August 30 - September 3, 2004, Proceedings; 01/2004
Conference Proceeding: Domain Representation Assisting Cognitive Analysis.Proceedings of the 16th Eureopean Conference on Artificial Intelligence, ECAI'2004, including Prestigious Applicants of Intelligent Systems, PAIS 2004, Valencia, Spain, August 22-27, 2004; 01/2004
- [show abstract] [hide abstract]
ABSTRACT: The proposed paper demonstrates that a hybrid fuzzy neural network can serve as a risk classifier of stock investment projects. The training algorithm for the regular part of the network is based on bidirectional incremental evolution proving more efficient than direct evolution. The approach is compared with other crisp and soft investment appraisal and trading techniques, while building a multimodel domain representation for an intelligent decision support system. Thus the advantages of each model are utilised while looking at the investment problem from different perspectives. The empirical results are based on UK companies traded on the London Stock Exchange.http://www.unipi.gr/jass/2003/2003-2.htm.