AN ADAPTIVE STUDENT CENTERED CURRICULUM FOR AN INTELLIGENT TRAINING SYSTEM

An intelligent tutoring system customizes its presentation of knowledg e to the individual needs of each student based on a model of the stud ent. Student models are more complex than other user models because th e student is likely to have misconceptions. We have addressed several difficult issues in reasoning about a student's knowledge and skills w ithin a real-time simulation-based training system. Our conceptual fra mework enables important aspects of the tutor's reasoning to be based upon simple, comprehensible representations that are the basis for a S tudent Centered Curriculum. We have built a system for teaching cardia c resuscitation techniques in which the decisions about how to teach a re separated from the decisions about what to teach. The training cont ext (i.e., choice of topics) is changed based on a tight interaction b etween student modeling techniques and simulation management. Although complex student models are still required to support detailed reasoni ng about how to teach, we argue that the decision about what to teach can be adequately supported by qualitatively simpler techniques, such as overlay models. This system was evaluated in formative studies invo lving medical school faculty and students. Construction of the student model involves monitoring student actions during a simulation and eva luating these actions in comparison with an expert model encoded as a multi-agent plan. The plan recognition techniques used in this system are novel and allow the expert knowledge to be expressed in a form tha t is natural for domain experts.