Teaching operational expertise to 'trained novices': The case-based intelligent tutoring system

Today, and for the foreseeable future, rapid change is a nearly ubiquitous characteristic of complex-dynamic systems. Widespread use of digital technology greatly increases the rate at which systems change and the complexity of systems. Changes in the work environment can degrade even the most skilled practitioner's expertise, creating gaps or misunderstandings in practitioner knowledge. Moreover, such gaps or misunderstanding can significantly affect performance. Under such circumstances, these practitioners, although highly skilled, can sometimes be thought of as trained novices.; This research has two primary goals. The first goal is to address the growing training demands of maintaining practitioner expertise by using computer-based training that merges intelligent tutoring systems (ITS) and case-based teaching. The second goal is to implement this new approach in such a way that facilitates the ease and decreases the cost of incorporating new cases as training needs evolve. To address these goals, several components comprise this research. The key component is a conceptual architecture, the Case-Based Intelligent Tutoring System (CBITS). CBITS builds upon the experience and research in both ITS and case-based teaching. The ITS provides a control structure for monitoring individual students and addressing their individual needs. Within that structure, cases provide a method of teaching, using memorable experiences to create focused instruction. Cases also allow tutor content to evolve as the operational environment evolves. Another component of the research, the Georgia Tech Intelligent Tutoring Architecture (GT-ITACS), is a computational implementation of CBITS that separates training and domain knowledge from tutor software. GT-ITACS thus enables rapid and lower cost adoption of new cases into training.; Training system implementations of CBITS are relevant in a range of domains in which practitioners interact with complex, technological, and evolving system. Examples include airline maintenance, electronic manufacturing, and telecommunications.; In this research, CBITS is implemented as a proof-of-concept tutor for MD-11 pilots. The CBITS case in this implementation is a newly licensed capability of the MD-11 aircraft. This capability introduces a new technique that improves safety but is unfamiliar to experienced pilots. An empirical evaluation of the system with active airline pilots showed that the system provides significantly effective training.