Int. J. , Vol. x, No. x, xxxx 1 Copyright © 200x Inderscience Enterprises Ltd. Using a hybrid A.I. approach for exercise difficulty level adaptation Constantinos Koutsojannis, Grigorios Beligiannis, Ioannis Hatzilygeroudis and Constantinos Papavlasopoulos Department of Computer Engineering & Informatics, School of Engineering University of Patras, Hellas (Greece) E-mails:ckoutsog@ceid.upatras.gr, beligian@ceid.upatras.gr, ihatz@ceid.upatras.gr, papavlas@ceid.upatras.gr Jim Prentzas Department of Informatics and Computer Technology Technological Educational Institute of Lamia, Hellas (Greece) E-mail:dprentzas@teilam.gr Abstract: In this paper, we present an intelligent and adaptive web-based education system that uses a hybrid AI approach for determination of the difficulty levels of the provided exercises. More specifically, a combination of the expert systems approach and a genetic algorithm approach is used. A genetic algorithm is used to extract some kind of rules from the data acquired from the interactions of the students with the system when answering to questions/exercises. Those rules are used to modify expert rules provided by the Tutor. In this way, feedback from the students is taken into account for determination of the difficulty levels of the questions/exercises. This is important because the difficulty levels of the exercises are taken into account for the evaluation of the knowledge levels of the students with regards to various concepts. Experimental results show that a significant part of questions/exercises may need to change their level of difficulty. Furthermore, the validity of the method is experimentally showed. Keywords: Intelligent Web-Based Education, Intelligent E-Learning, Exercise adaptation, Expert systems, Genetic Algorithms, Hybrid Intelligent Systems Biographical notes: Dr Constantinos Koutsojannis holds a PhD in Medical Physics and studies for a PhD in Artificial Intelligence at the Department of Computer Engineering and Informatics, University of Patras, Greece. Special areas of interest are intelligent web based educational systems and medical expert systems. Dr Koutsojannis is currently member of the teaching staff at the Health Science Department of Technological Educational Institute of Patras, Greece. Dr Grigorios Beligiannis received his PhD from the Department of Computer Engineering and Informatics, University of Patras, Greece, in 2002. Since then he is working as a post-graduate researcher at the Pattern Recognition Laboratory at the above Department. He has published several papers concerning the application of evolutionary algorithms in many real-world problems (system identification and parameter estimation of linear and nonlinear systems, text classification, user/student profile optimization, biomedical data processing and classification). His current research interests are in evolutionary and genetic programming, hybrid intelligent systems, data mining, system analysis and detection, and bioinformatics.