To build learning environments that can provide tailored assistance to learners during learning activities, a popular solution is to model the cognitive processes of learners with a cognitive model. It allows a tutoring system to closely follow the reasoning of learners to then generate tailored assistance. This is the idea originally proposed in the Cognitive Tutors by Anderson et al. (1995). However, their cognitive model can be improved in several ways.

For this reason, we have decided to build an alternative cognitive model. The model is directly inspired by the work on Cognitive Tutors. But it provides several originalities such as:

• providing a better evaluation of declarative (semantic) knowledge and spatial reasoning (see project 2) [1,2]
• and incorporating ontologies for improving reusability of knowledge and building glass-box learning objects (see project 3) [3].

This work has resulted in a knowledge representation framework [1,2,3] comprising mainly:

• knowledge structures for representing cognitive processes
• an interpreter to simulate cognitive processes described with the knowledge structures
• a model-tracer that use the interpreter for determining what a learner is actually doing according to the knowledge structures.

The current version of the framework (2006-..), described in [1,2] has been applied in the following projects:

• RomanTutor, a tutoring system for learning to operate the Canadarm2 robotic arm (figure 1) [1].
• the latest version of an authoring tool for the knowledge structures (figure 2) (P. Fournier-Viger, 2007)
• Redbool, a tutoring system for learning to reduce boolean expressions (figure 3) ([1], 2005-2006)

Fig 1. The RomanTutor Tutoring System

Fig 2. The Latest Version of the Authoring Tool

Fig 3. The Redbool Tutoring System

Earlier versions (2003-2006) of the knowledge structures and interpreter have been designed with André Mayers and have been described in my M.Sc. Dissertation (P. Fournier-Viger, 2005). They have been used in several projects including:

• an early version of the GNT tutoring system (figure 4) for learning to perform restriction, digestion and reconstructing DNA in a genetic lab (X. Zhao, M.Sc. 2004)
• an early version of Redbool tutoring system (figure 5) (M. Najjar, P. Fournier-Viger, A. Mayers et al., 2003-2004)
• an early version of the authoring tool for the knowledge structures (M. Najjar, P. Fournier-Viger et al., 2005)
• TiramisuSimulation, a cognitive simulation of a person cooking a tiramisu that is being interrupted during the task (figure 6) (M. Najjar, P. Fournier-Viger, J.F. Lebeau et al., 2006)
• an early version of the ACCC tutoring system for DC Circuit Analysis (figure 7) (A. Abdessemed, J.F. Lebeau et al., 2006).

Fig 4. An Early Version of the GNT Tutoring System

Fig 5. An Early Version of the Redbool Tutoring System

Fig 6. A Cognitive Simulation of the Realisation of a Tiramisu Cake

Fig 7. An Early Version of a Tutoring System for DC Circuit Analysis

Main publications

[1] Fournier-Viger, P., Nkambou, R. & Mayers, A. (2008). Evaluating Spatial Representations and Skills in a Simulator-Based Tutoring System. IEEE Transactions on Learning Technologies, vol. 1, no. 1, pp. 63-74, Jan-Mar, 2008.

[2] Fournier-Viger, P., Nkambou, R. & Mayers, A. (2008), A Framework for Evaluating Semantic Knowledge in Problem-Solving-Based Intelligent Tutoring Systems. Proceedings of the 21th International Florida Artificial Intelligence Research Society Conference (FLAIRS 2008). AAAI press, pp. 409-414.

[3] Fournier-Viger P., Najjar, M., Mayers, A. & Nkambou, R. (2006). A Cognitive and Logic based Model for Building Glass-box Learning Objects. Interdisciplinary Journal of Knowledge and Learning Objects, Vol. 2. pp: 77-94.

The RomanTutor is a software program developped by the GDAC and PLANIART research team with the logistic and financial support of the Canadian Space Agency, FQRNT and the NSERC.

Copyright © 2005-2010 Philippe Fournier-Viger. All rights reserved.