Showing papers on "Intelligent tutoring system published in 1995"

Using the operator function model and OFMspert as the basis for an intelligent tutoring system: towards a tutor/aid paradigm for operators of supervisory control systems

Abstract: Training is a critical issue for operators responsible for the safe and efficient operation of large-scale complex dynamic systems. This paper proposes and articulates a set of requirements for an intelligent tutoring system. The requirements specify what (instructional content) and how (instructional strategies) to teach a novice operator to supervise and control a complex dynamic system. The instructional content teaches system structure and behavior (i.e., declarative knowledge), system procedures (i.e., procedural knowledge), and how to use this declarative and procedural knowledge to manage a complex dynamic system in real time (i.e., operational skill). Using the underlying representations of the operator function model (OFM) and OFMspert, the OFM's computational implementation. GT-VITA (Georgia Tech Visual and Inspectable Tutor and Assistant) realizes these requirements. As a proof-of-concept demonstration, an instance of the generic GT-VITA tutoring architecture was implemented for satellite ground controllers. The empirical evaluation, utilizing NASA satellite ground control personnel, showed that GT-VITA was a flexible and useful training system. In fact, NASA has adopted VITA as the foundation for required training for all satellite ground control personnel. In addition to an intelligent tutoring system architecture, by using and extending the operator function model and OFMspert, GT-VITA demonstrates a robust methodology for conceptualizing the tutor-aid paradigm. The tutor-aid paradigm defines a conceptual framework in which learning with a intelligent tutor gradually becomes collaboration with an intelligent associate. Using the same structures (i.e., OFM and OFMspert) and the same domain knowledge, GT-VITA specifies a tutor and GT-MOCA (Jones and Mitchell, 1995) specifies an aid. >

The Role of Probability-Based Inference in an Intelligent Tutoring System.

Abstract: Probability-based inference in complex networks of interdependent variables is an active topic in statistical research, spurred by such diverse applications as forecasting, pedigree analysis, troubleshooting, and medical diagnosis. This paper concerns the role of Bayesian inference networks for updating student models in intelligent tutoring systems (ITSs). Basic concepts of the approach are briefly reviewed, but the emphasis is on the considerations that arise when one attempts to operationalize the abstract framework of probability-based reasoning in a practical ITS context. The discussion revolves around HYDRIVE, an ITS for learning to troubleshoot an aircraft hydraulics system. HYDRIVE supports generalized claims about aspects of student proficiency through probabilitybased combination of rule-based evaluations of specific actions. The paper highlights the interplay among inferential issues, the psychology of learning in the domain, and the instructional approach upon which the ITS is based.

Knowledge organization in intelligent tutoring systems for diagnostic problem solving in complex dynamic domains

Abstract: Turbinia-Vyasa is a computer-based instructional system that trains operators to troubleshoot and diagnose faults in marine power plants. The simulator, Turbinia, is based on a hierarchical representation of subsystems, components, and primitives. Vyasa is the computer-based tutor that teaches the troubleshooting task using Turbinia. The simulator, an interactive, direct manipulation interface, and the tutor (with its expert, student, and instructional modules) comprise the instructional system. To be effective, knowledge about the system and the troubleshooting task, together with the knowledge to infer student's misconceptions from observed actions and pedagogical knowledge, must be suitably organized and presented to the student. System knowledge is organized in terms of schematics, subsystems, and fluid paths, which are further decomposed into structure, function, and behavior. Information about failures and failure schemas complement the system knowledge. In the paper, the authors discuss the details of knowledge organization and show how they support the functions of the intelligent tutoring system. >

Modeling student knowledge with self-organizing feature maps

Abstract: The paper describes a novel application of neural networks to model the behavior of students in the context of an intelligent tutoring system. Self-organizing feature maps are used to capture the possible states of student knowledge from an existing test database. The trained network implements a universal student knowledge model that is compatible with knowledge space theory approaches to student assessment and computer aided instruction. The student model can be applied to rapidly assess the knowledge of any given student, and chart a path from lower to higher states of expertise. The authors illustrate the concept on an aircraft fuel management domain, demonstrating its noise-tolerance and insensitivity to feature map parameter values. An approach to determining the correct feature map size is also described. >

Designing Human-Computer Collaborative Learning

Abstract: In this paper we describe the design of a system to support collaboration between a human learner and an artificial learner. The focus is on promoting the learner’s metacognitive skills by making strategic decisions explicit, by inducing reflection through criticism, and by fostering an active mode of learning. We outline the design of a system with which students can learn about electoral biases through designing electoral simulations. The implications for the machine learning component of the system, and for intelligent tutoring system architectures generally, are discussed.

Tutoring Transfer of Technical Competence.

Abstract: : We report partial results of the evaluation of an intelligent tutoring system (Sherlock 2) that fosters the transfer of complex technical skills. The tutor's learning environment is concordant with views from the acquired skill through coached apprenticeship activities. Instructional content consists of authentic problem solving scenarios that situate trainees in realistic contexts where they can practice and hone complex diagnostic skills. Moreover, results show that their acquired expertise is generalizable to a novel equipment system. Similar general a ability was not demonstrated by a matched control group. (AN)

An adaptive Student Centered Curriculum for an intelligent training system

Abstract: An intelligent tutoring system customizes its presentation of knowledge to the individual needs of each student based on a model of the student. Student models are more complex than other user models because the student is likely to have misconceptions. We have addressed several difficult issues in reasoning about a student's knowledge and skills within a real-time simulation-based training system. Our conceptual framework enables important aspects of the tutor's reasoning to be based upon simple, comprehensible representations that are the basis for a Student Centered Curriculum. We have built a system for teaching cardiac resuscitation techniques in which the decisions abouthow to teach are separated from the decisions aboutwhat to teach. The training context (i.e., choice of topics) is changed based on a tight interaction between student modeling techniques and simulation management. Although complex student models are still required to support detailed reasoning 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 involving medical school faculty and students. Construction of the student model involves monitoring student actions during a simulation and evaluating 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 that is natural for domain experts.

Multiple multimodal mentors: delivering computer-based instruction via specialized anthropomorphic advisors

Abstract: We describe the Smalltalk Gurus, components of the MoleHill intelligent tutoring system for Smalltalk programming. The Gurus offer help on plans for achieving goals in the Smalltalk environment, as well as remediation for students' incorrect and less-than-optimal plans. The Gurus' assistance is provided via the multimodal media of animation and voice-over audio. MoleHill employs multiple Gurus to deliver advice and instruction concerning disparate information domains, thus facilitating learners' cognitive organization and assimilation of new knowledge and information. We have labelled the approach instantiated by the Smalltalk Gurus the guru instructional model, one which is generally applicable to computer-based advisory systems.

Implementing multiple tutoring strategies in an intelligent tutoring system for music learning

Abstract: Variation in tutoring strategies plays an important part in intelligent tutoring systems. The potential for providing an adaptive intelligent tutoring system depends on having a range of tutoring strategies to select from. In order to react effectively to the student's needs, an intelligent tutoring system has to be able to choose intelligently among the strategies and determine which strategy is best for an individual student at a particular moment. This paper describes, through the discussion pertaining to the implementation of SONATA, a music theory tutoring system, how an intelligent tutoring system can be developed to support multiple tutoring strategies during the course of interaction. SONATA has been implemented using a hypertext tool, HyperCard II. 1.

A model of tutoring: facilitating knowledge integration using multiple models of the domain

Abstract: This thesis describes a model of tutoring. This model is intended for CIRCSIM-Tutor (v.3)--an Intelligent Tutoring System (ITS)--that teaches the functioning of the baroreceptor reflex to the first year medical students. This model is based on the behavior of human tutors in the keyboard-to-keyboard sessions. The major theme of this model is that, in a problem-solving environment, it helps the student integrate his/her knowledge into a coherent qualitative causal model of the domain and solve problems in the domain. The key feature of this model is that it uses multiple qualitative models of the domain in the process of facilitating knowledge integration. The development of this model of tutoring has been approached by using an ITS development framework that views the development of an ITS as a modeling activity. There are three major phases of this methodology. These are the conceptual phase, the system phase, and physical phase. At each phase a different model of an ITS results. The conceptual model, resulting out of the conceptual phase, deals in this research only with the domain and the pedagogy aspects of tutoring. The domain knowledge here consists of multiple qualitative models that are used to support decision making. This decision making process considers three major functions: what to teach, when to teach, and how to teach. The system model, resulting out of the system phase, provides a generic framework to represent three different types of knowledge. These are the planning knowledge, the curriculum knowledge, and the domain knowledge. The system model can also be viewed as consisting of a set of tutoring spaces. Each space is responsible for performing one type of major decision of the tutor while interacting with the student. The second model resulting out of the system phase is the architecture of the system. Here an object-oriented methodology is used to develop some of the major components of this architecture. These architectural components are coded using the Common Lisp Object System on the Apple Macintosh.

An intelligent tutoring system for simulator-based helicopter flight training

Abstract: The development of an intelligent tutoring system for helicopter flight training is described. The Intelligent Flight Trainer (IFT) is a simulator-based system designed to assist students in developing proficiency on a suite of initial entry rotary wing maneuvers. It encapsulates instructor pilot domain knowledge in an expert system shell that provides tutorial and performance monitoring functions through a synthetic voice generator. The expert system shell works in concert with a variable stability augmentation control law that makes it easier for a neophyte student to control the motion of the simulated vehicle. Experimental verification of the IFT is currently under way at the UH-1 Training Research Simulator at Fort Rucker. NOMENCLATURE airborne flight training, and they have been used widely for both civilian and military training. Simulators operate indoors and are not affected by weather, and they are not subject to the problems and accidents that may occur in real flight (Gonzales and Ingraham, 1994). They do, however, require intensive supervision by instructors or check pilots, which can limit availability and increase expenses. Intelligent Tutoring Systems (ITSs) offer the potential to reduce this dependence on instructor pilots by automating the instructional process. The objective of this work is to hybridize flight simulation and ITS technologies to develop a system capable of teaching Army flight students how to perform basic helicopter flight maneuvers. E(.) Expected value h Altitude, ft p Roll rate, rad/sec q Pitch rate, rad/sec r Yaw rate, rad/sec t Time, sec x Distance along x-axis, ft/sec x State vector u Body x-axis velocity, ft/sec u Control vector v Body y-axis velocity , ft/sec V Airspeed, ft/sec or knots w Body z-axis velocity, ft/sec Intelligent tutoring systems are designed to train and instruct a user in a computerized environment. They are generally developed to take the place of a human instructor. They draw upon a body of domain knowledge that is embedded in the system as an expert system of rules (Farr and Psotka, 1992). ITSs present this expertise to a learner under the control of some appropriate pedagogical strategy tailored to his or her changing states of knowledge and understanding. Ideally, the ITS monitors and diagnoses the student’s progress to improved expertise in the form of an evolving student model. y Distance along y-axis, ft y Output vector z Distance along z-axis, ft col Collective input, inches lon Longitudinal cyclic input, inches lat Lateral cyclic input, inches ped Antitorque pedal input, inches Roll attitude, rad Much of the ITS work to date has concentrated on conventional curriculum areas, such as elementary subtraction (Ohlsson, 1990), fractions (Gutstein, 1992), basic Newtonian mechanics (Teodoro, 1990), and the like. They have also been used for teaching electronic troubleshooting (Brown, Burton, and deKleer, 1982). In these applications, the focus has been on building up the student’s knowledge base and on teaching the skills for manipulating that knowledge. Pitch attitude, rad

Designing Navigational Support for Educational Software

Abstract: From a user-centered point of view, learning with hypermedia educational software is mainly a matter of navigation in a corpus of knowledge. However, although navigating obviously requires minimal competences in both computer interaction skills and domain knowledge, yet most current models of navigational support rely on a presupposed degree of proficiency in both domains. We suggest that every learner using a new navigational based learning system needs to be supported by an initial phase of orientation and initiation in both spaces of interface and domain contents. Activity metaphors seem to be a convenient way of supporting learner's cognitive transfer from familiar to unfamiliar domain in particular to help them structure their dynamic progress through the different phases of learning. We will refer to activity theory as a framework to structure both the support of the user navigation and the description of the learning process. As an overall navigational metaphor we will draw on a travel metaphor interpreted as a quest of objects by subjects (Greimas' semio-narrative theory). Considering that navigational issues in learning must evolve from a focus on navigation in the interface to navigation in the domain contents, we propose a three-phases navigational model specific for educational software. Each of the three phases call for different navigational support with Adaptive Hypermedia Systems (AHS) as one of them.

Using student modelling to determine when and how to hint in an intelligent tutoring system

Abstract: CIRCSIM-Tutor (CST) is an Intelligent Tutoring System (ITS) designed to assist first year medical students in reasoning about disturbances to blood pressure. Specifically, they must be able to predict the qualitative changes that occur in the human body when it encounters a perturbation. Many of the physiological concepts used to accurately make predictions are counter intuitive and, therefore, this domain is ideal for studying the dynamics of tutoring. A study of human tutoring sessions is the basis for the design of CST. The student model is the tutor's (ITS or human) assessment of the student's cognitive state. After interviews with CST's two expert human tutors and an analysis their human tutoring transcripts, I have concluded that an ITS's student model can provide answers to two important questions: what should be tutored and how should it be tutored. In CST, the tutor selects an error pattern, a set of student prediction errors that violate a physiological concept. Then, through natural language dialogue, CST attempts to guide the student into an understanding of that physiological concept. A study of these two expert human tutors reveals that, while they employ many tactics to achieve this end, they virtually always try hinting first. A hint is an utterance that is intended to assist the student without providing the answer. Hints are occasionally mentioned in the ITS literature but there has been no systematic study of this phenomenon. I have identified two major categories of hints: (1) hints that convey information (CI-Hints) and (2) hints that point to information (PT-Hints). An analysis of the use of hints by these two tutor's and of the corresponding student responses reveals consistent patterns regarding when and how to hint. The tutor maintains a global assessment (how well is the student's total performance?) and a local assessment (how is the student doing on this topic?). The behavior of these two tutors is the basis for the rules that determine when and how CST hints.

Rethinking and Reinventing Artificial Intelligence from the Perspective of Human-Centered Computational Artifacts

Abstract: Many research efforts in Artificial Intelligence (AI) have focused on replacing rather than augmenting and empowering human beings. We have developed human-computer collaboration environments to demonstrate the power and the possibilities of Intelligence Augmentation (IA) with human-centered computational artifacts.

Developing hybrid intelligent tutoring and hypertext systems

Abstract: The objective of this paper is to present an alternative paradigm to the traditional Knowledge Based Expert Systems Paradigm for developing a full-scale Intelligent Tutoring System that has dominated for years Intelligent Tutoring Systems development. This alternative paradigm which integrates Minsky's Frames with hypertext has been successfully deployed so far in the development of PEDRO, an Intelligent Tutoring System for foreign language learning, SONATA, an Intelligent Tutoring System for music theory learning and INTUITION, an Intelligent Tutoring System for Gaming-Simulation.

Towards New Learning Strategies in Intelligent Tutoring Systems

Abstract: Co-operative tutoring systems replace the prescriptive approach developed by traditional intelligent tutoring systems with a constructive one based on the use of the computer as a way to exchange, control and build knowledge. This paper proposes two new learning strategies, learning by disturbing and learning by co-teaching, that extend the spectrum of possibilities in terms of co-operation and place the learner into a higher degree of abstraction. Learning by disturbing method allows to check the ability of the learner to distinguish between wrong and correct solutions. Learning by co-teaching provides an example of discussions between the teacher and the co-teacher that is useful for inducing correct solutions presented in a pedagogical form. Co-operation can be improved using elicitation techniques that can serve to extract learner's knowledge which can be further compared with the expert solution in order to identify his knowledge level. These techniques strengthen the efficiency of the learning strategies and serve as a basis for developing tutoring systems or learning environments including their co-operative aspects. We show how these strategies can be dynamically selected in an architecture of an intelligent tutoring system in which the knowledge level of the learner is frequently evaluated. We give an example of eliciting dialogues in a medical environment.

Addressing the trained novice/expert performance gap in complex dynamic systems: a case-based intelligent tutoring system

Abstract: Training operators for complex dynamic systems is an essential, but costly, endeavor. New operators need to learn declarative and procedural knowledge, and operational skill in order to safely and effectively perform functions required in complex work domains, e.g., nuclear power generation or aviation. Economic pressures, however, necessitate the adoption of training approaches and programs that produce competent performance in limited time. These approaches often lead to gaps between the level of performance of the newly trained operator (the trained novice) and the expert operator. This paper discusses the genesis of this gap and some of its effects on operation. A design for a case-based intelligent tutoring system is proposed for addressing this performance gap.

An intelligent tutoring system for the Dijkstra-Gries methodology

Abstract: The paper describes the design and implementation of an intelligent tutoring system for the Dijkstra-Gries programming methodology as defined by Gries (1981) in "The Science of Programming". The first part of the paper identifies the requirements of intelligent tutoring systems in general and those of the methodology in particular. It shows the suitability of the Smalltalk environment for developing expandable intelligent systems and the compatibility of Smalltalk's object-oriented paradigm with the Gries methodology's goal/plan approach to programming. We then describe how these requirements are met: an overview of the system's support of the methodology and the modules that enable the system to respond intelligently. As an example, a reusable tutorial part is presented, first from a student's perspective, then from an author's perspective. Finally the results of an evaluation of the system drawn from actual student experience are presented. >

An object-oriented tutoring system for teaching sets

Abstract: Over the recent years several prototypes of intelligent tutoring systems for scientific subjects have been developed. Meanwhile, the object-oriented paradigm has become popular in the software engineering and artificial intelligence communities. The objective of the research presented in this paper is an application of the object-oriented paradigm to the design and implementation of an intelligent tutoring system. The domain of the system is the set theory at the secondary school level. It is shown that the inheritance hierarchy of the object-oriented paradigm is very useful in defining and organizing the components of the set theory, and in the generation of examples and questions. The issues raised in the object-oriented design of an intelligent tutoring system are discussed.

ITS-Engineering: providing adaptive teaching in the engineering tutor

Abstract: The successful learning of an engineering student depends substantially on the instructor's ability to adapt instruction, both the content and the various teaching styles, to individual differences among students. The emergence of computer applications in education and training, such as intelligent tutoring systems, provides a viable alternative to achieve these teaching tasks. Computerized instruction is a significant tool for the effective application of adaptive teaching. ITS-Engineering is a tutoring system shell intended to provide a developing framework for applications in the engineering domains with less time and cost. Based on R.M. Gagne's (1985) instructional design and the multiple teaching style paradigm, the application is able to deliver instruction that adapts in both content and teaching styles. The available teaching styles in ITS-Engineering include instructor oriented, guided discovery, user initiated and exploratory styles. The instructor oriented and the guided discovery style represents the teacher control paradigm. In contrast, the user initiated and the exploratory style represent the learner control paradigm. The application of these teaching styles and their adapting capabilities are demonstrated in ITS-CPM (Intelligent Tutoring System for Construction and Project Management); an ITS application developed within the framework of ITS-Engineering.

Modelling the student in Pitagora 2.0

Abstract: With the aim to individualise human-computer interaction, an Intelligent Tutoring System (ITS) has to keep track of what and how the student has learned. Hence, it is necessary to maintain a Student Model (SM) dealing with complex knowledge representation, such as incomplete and inconsistent knowledge and belief revision. With this in view, the main objective of this paper is to present and discuss the student modelling approach we have adopted to implement Pitagora 2.0, an ITS based on a co-operative learning model, and designed to support teaching-learning activities in a Euclidean Geometry context. In particular, this approach has led us to develop two distinct modules that cooperate to implement the SM of Pitagora 2.0. The first module resembles a “classical” student model, in the sense that it maintains a representation of the current student knowledge level, which can be used by the teacher in order to tune its teaching strategies to the specific student needs. In addition, our system contains a second module that implements a virtual partner, called companion. This module consists of a computational model of an “average student” which cooperates with the student during the learning process. The above mentioned module calls for the use of machine learning algorithms that allow the companion to improve in parallel with the real student. Computational results obtained when testing this module in simulation experiments are also presented.

A proposed student model algorithm for an intelligent tutoring system

Abstract: Tutoring is a linguistic exchange whose goal is to clarify a body of knowledge to which the student has already been exposed. Tutoring also involves directly a dialog so that the responses remain appropriate even when facing errors. This paper presents a proposed algorithm for the student model which can be considered as one of the main modules existing in an intelligent tutoring system. The proposed algorithm takes care of transferring knowledge to the student, pointing out the student errors, and understanding the student belief. This can be done by keeping track of the student status. The student model will also monitor the student behaviour. The monitoring process can be done by analyzing the student answers, comparing them with the correct system generated answers. This comparison will predict the student level of understanding or to recognize the student particular learning style. The student model is supported by a powerful structured knowledge base (KB) which contains a large number of facts and rules of the selected domain. The KB contains diagnostic hypotheses which are able to explain the student behaviour. The student model using that KB can perform logical inference operations to detect the student exploration direction, the student weak points, the student belief, and others.

Cognitive Technology Extends the Work Environment and Accelerates Learning in Complex Jobs.

Abstract: : Instructional technology that is grounded in cognitive theory is used as the medium to accelerate the acquisition ot complex problem solving skills The use of an intelligent tutoring system to teach troubleshooting literally expands the learning environment by providing a simulated representation of the actual work environment where trainees work a graded series of troubleshooting scenarios Scenarios are sequenced t9 promote successive approximations of mature practice as trainees work more and more difficult problems in the 'forgiving' tutor environment, where they learn by doing and reflecting on their own solution vis-a-vis an exemplar master solution In a controlled experiment, experimental apprentice subjects outperformed their control counterpart on the two Verbal Troubleshooting Posttests (t39= -404, p = 000; t39 = -372, p = 001) and on the paper and pencil posflest (r39 = -277, p = 009) After tutoring, scores obtained by apprentice subjects (having about 3 years' AF experience) rivaled those of Master technicians having over 10 years' experience in F 15 avionics maintenance The dramatic results are attributed to (a) cognitive models as input to instruction; (b) the sequence of instructional events; (c) situated learning in a constructivist instructional environment, and (d) the sociology surrounding the learning system Topics (c) and (d) are discussed with special attention (AN)

The learn, explore, and practice (leap) intelligent tutoring system: a demonstration project incorporating instructional design theory in a practical tutor

Abstract: The Learn, Explore, and Practice (LEAP) Intelligent Tutoring System: A Demonstration Project Incorporating Instructional Design Theory in a Practical Tutor