Showing papers on "Intelligent tutoring system published in 1987"

Methodology for building an intelligent tutoring system

Abstract: Over the past 6 years we have been developing a computer program to teach medical diagnosis. Our research synthesizes and extends results in artlficlal intelligence (Al), medicine, and cognitive psychology. This paper describes the progression of the research, and explalns how theories from these fields are combined in a computational model. The general problem has been to develop an "intelligent tutoring system" by adapting the MYCIN "expert system." Thls conversion requires a deeper understanding of the nature of expertise and explanatlon than origlnally requlred for developlng MYCIN, and a concomitant shift in perspective from slmple performance goals to attaining psychologlcal validity in the program''s reasoning process. Others have written extensively about the relatlon of artificlal intelligence to cognltive sclence (e.g., [Pylyshyn, 1978] [Boden, 1977]). Our purpose here is not to repeat those arguments, but to present a case study which will provide a common point for further dlscusslon. To this end, to help evaluate the state of cognitive science, we will outline our methodology and survey what resources and viewpoints have helped our research. We will also discuss pitfalls that other Al-oriented cognitive scientists may encounter. Finally, we will present some questions coming out of our work whlch might suggest possible collaboration with other fields of research.

The Role of Cognitive Simulation Models in the Development of Advanced Training and Testing Systems.

Abstract: : To be most efficient, an intelligent tutoring system must be based on a thorough analysis of the task that is being trained, and the knowledge, both declarative and procedural, that the learner must acquire in order to perform the task. This paper explores the thesis that constructing a cognitive simulation model of the task is an efficient approach to characterizing this content. Because the simulation model must be explicitly stated in order to carry out the task properly, the model acts as a specification of (1) the exact nature of the user's task in terms of goals and subgoals; (2) the exact procedural knowledge required to accomplish the goals in the task setting; (3) the exact declarative knowledge required to support the procedural knowledge in carrying out the task. Such specifications could be used to both specify the content of instruction and the content of diagnostic tests. Two examples of the applications of this approach are presented, both assuming that the procedural knowledge is represented in the form of production rules. In the first example, by determining what production rules were actually stated by the training materials for a word processing system, it became clear that certain procedures were not correctly stated. The second example concerned the training and testing materials used in experiments in which subjects learned the fictitious inner workings of a simple control panel system, and then had to infer how to operate the control panel to accomplish a simple goal under different situations.

Building a community memory for intelligent tutoring systems

Abstract: This article discusses the need for multiple experts to work together to develop knowledge representation systems for intelligent tutors. Three case studies are examined in which the need for a pragmatic approach to the problem of knowledge acquisition has become apparent. Example methodologies for building tools for the knowledge acquisition phase are described including specific tasks and criteria that might be used to transfer expertise from several experts to an intelligent tutoring system.

Artificial intelligence applications to high-technology training

Abstract: Recent advances in artificial intelligence (AI) could be used to improve occupational instruction in complex subjects with sophisticated performance goals, such as those required for high-technology jobs. Educational devices incorporating AI would “understand”what, whom, andhow they were teaching and could therefore tailor content and method to the needs of an individual learner without being limited to a repertoire of prespecified responses. Intelligent Computer Assisted Instruction (ICAI) encompasses a spectrum of approaches, including Socratic tutoring systems, simulation environments with embedded coaches, and “empowering environments” which aid workers in using intelligent tools in complementary cognitive partnerships. This article focuses on (a) depicting how present training methods might change if intelligent instructional devices were incorporated, (b) delineating the current state of the art in the areas of research needed to produce such systems, and (c) indicating in which types of adult educational settings ICAI might be productive and cost effective.

Research on Computer Aided Design for Maintainability

Abstract: : The objective of this research was to investigate methods for measuring and predicting equipment maintainability as a consequence of internal structure and the design of the man-machine interface. A computer-based technique has been developed for projecting maintenance workload which is sensitive to design characteristics such as selection for test points and from panel indicators, modularization, internal system architecture and circuitry, and physical packaging of the hardware. The report summarizes the operation of the performance model which generates projected diagnostic sequences for sample failures; it presents a complete example of a maintainability analysis of a system; and it discusses the current application of the technique within an intelligent tutoring system. Keywords: PROFILE Expert System; Intelligent Maintenance Training System; Troubleshooting.

An intelligent tutoring system for interpreting ground tracks

Abstract: This paper describes an intelligent tutoring system for the space domain. The system was developed on a Xerox 1108 using LOOPS and provides an environment for discovering principles of ground tracks as a direct function of the orbital elements. The system was designed to teach students how to "deduce" a sateliite's orbital elements by looking at a graphic display of a satellite's ground track. The system also teaches students how to use more systematic behaviors to explore this domain. Since the system is equipped with a number of online tools that were specially designed to help students better understand facts, principles and relationships, the student is free to investigate different options and learn at his own pace.

Design of an intelligent tutoring system for aircraft recognition

Abstract: A microcomputer-based intelligent tutoring system for teaching aircraft recognition in support of air defense training is described. An overview of the conceptual design is presented, and the main components are described. The system presents realistic images to the student, dynamically assesses student knowledge, provides individualized feedback, and allows limited student control of the educational path. The design methodology is referenced to standard practice in computer-assisted instruction.

Portable, Intelligent Simulation for ASW Training

Abstract: The purpose of this paper is twofold: first, we would like to discuss some Navy-sponsored research and development work in Computer-based Instruction (CBI) where the aim is to add “intelligence” to the CBI, and second, to describe one such system. The military services have to train large numbers of people to perform a wide variety of somewhat specialized jobs, and to this process, they devote considerable resources and personnel. It is little wonder that technical developments that offer to make instruction better or more efficient have generated a great deal of interest.

The desktop interface in intelligent tutoring systems

Abstract: The interface between an Intelligent Tutoring System (ITS) and the person being tutored is critical to the success of the learning process. If the interface to the ITS is confusing or non-supportive of the tutored domain, the effectiveness of the instruction will be diminished or lost entirely. Consequently, the interface to an ITS should be highly integrated with the domain to provide a robust and semantically rich learning environment. In building an ITS for ZetaLISP on a LISP Machine, a Desktop Interface was designed to support a programming learning environment. Using the bitmapped display, windows, and mouse, three desktops were designed to support self-study and tutoring of ZetaLISP. Through organization, well-defined boundaries, and domain support facilities, the desktops provide substantial flexibility and power for the student and facilitate learning ZetaLISP programming while screening the student from the complex LISP Machine environment. The student can concentrate on learning ZetaLISP programming and not on how to operate the interface or a LISP Machine.

The Conversion of an Expert System to an Intelligent CAI System

Abstract: The process of building the knowledge base associated with an expert system is long and complex, and the information it contains very valuable. Most expert systems are designed to be used in a consultative manner by a non-expert in order to perform a task requiring expertise. The idea of using the same knowledge base in a tutoring role is very attractive.

An intelligent tutor for the space domain

Abstract: An intelligent tutoring system for the space domain is described. This system was developed on a Xerox 1108 using LOOPS and provides an environment for discovering principles of ground tracks as a direct function of the orbital elements. Some of the more practical design and implementation issues associated with the development of intelligent tutoring systems are examined. Some solutions to the problems and some suggestions for future research are offered.