Showing papers on "Intelligent tutoring system published in 1997"

User Modeling and Adaptive Navigation Support in WWW-Based Tutoring Systems

Abstract: Most learning systems and electronic textbooks accessible via the WWW up to now lack the capabilities of individualized help and adapted learning support that are the emergent features of on-site intelligent tutoring systems. This paper discusses the problems of developing interactive and adaptive learning systems on the WWW. We introduce ELM-ART II, an intelligent interactive textbook to support learning programming in LISP. ELM-ART II demonstrates how interactivity and adaptivity can be implemented in WWW-based tutoring systems. The knowledge-based component of the system uses a combination of an overlay model and an episodic user model. It also supports adaptive navigation as individualized diagnosis and help on problem solving tasks. Adaptive navigation support is achieved by annotating links. Additionally, the system selects the next best step in the curriculum on demand. Results of an empirical study show different effects of these techniques on different types of users during the first lessons of the programming course.

On-Line Student Modeling for Coached Problem Solving Using Bayesian Networks

Abstract: This paper describes the student modeling component of ANDES, an Intelligent Tutoring System for Newtonian physics. ANDES' student model uses a Bayesian network to do long-term knowledge assessment, plan recognition and prediction of students' actions during problem solving. The network is updated in real time, using an approximate anytime algorithm based on stochastic sampling, as a student solves problems with ANDES. The information in the student model is used by ANDES' Help system to tailor its support when the student reaches impasses in the problem solving process. In this paper, we describe the knowledge structures represented in the student model and discuss the implementation of the Bayesian network assessor. We also present a preliminary evaluation of the time performance of stochastic sampling algorithms to update the network.

Chapter 37 – Intelligent Tutoring Systems

Abstract: Publisher Summary The goal of intelligent tutoring systems (ITSs) would be to engage the students in sustained reasoning activity and to interact with the student based on a deep understanding of the students' behavior. This chapter begins by providing an overview of intelligent tutoring systems. The chapter comments on competing research goals in the field, followed by descriptions of two successful systems: (1) the Pittsburgh urban math project algebra tutor project and (2) the SHERLOCK project. These two systems are being deployed in real-world educational environments with substantial success. This chapter briefly describes the underlying theory and implementation of each system, to motivate later discussions. A description of the standard components in an intelligent tutoring system is also presented along with a discussion of human-computer interaction assessment issues unique to educational software. This chapter also provides a prescription for ITS design and development methods. Several issues concerning ITS design principles are also addressed in the chapter.

CIRCSIM-Tutor: An Intelligent Tutoring System Using Natural Language Dialogue

Abstract: CIRCSIM-Tutor version 2, a dialogue-based intelligent tutoring system (ITS), is nearly five years old. It conducts a conversation with a student to help the student learn to solve a class of problems in cardiovascular physiology dealing with the regulation of blood pressure. It uses natural language for both input and output, and can handle a variety of syntactic constructions and lexical items, including sentence fragments and misspelled words.

An intelligent tutoring system for introductory C language course

Abstract: In this paper, we describe a system called C-Tutor, an intelligent tutoring system (ITS) for novice C programmers. A program analyzer is the most important part of the ITS for programming. Our program analyzer is a compound of a reverse engineering system and a didactic system. Since a novice program usually contains many bugs, information about the intentions of the programmer is inevitable to recognize a buggy program. In our approach, the intentions of a programmer are automatically extracted as a problem description from a sample program by a reverse engineering system called GOES (GOal Extraction System). Based on the problem description, students' programs are recognized by a didactic system called ExBug (Execution-guided deBugger). As a learning environment. Curriculum Network constructs the knowledge base as genetic graphs to teach programming. C-Tutor is a complete ITS which provides both a program analyzer and a learning environment. Tested with real students' programs, program analyzer gives acceptable recognition results. Program analyzer and learning environment are closely related so that students can learn C language during programming. New problems can be easily set because GOES automatically generates problem descriptions for program analyzers. This makes C-Tutor a more practical tutoring system for a real C language course.

Developing a Design System into an Intelligent Tutoring System

Abstract: As the techniques of artificial intelligence become more widely used, an increasing number of knowledge-based design systems has been developed to handle problems that cannot be solved by traditional computational-based systems. Knowledge-based design systems are embedded with a wealth of design rules and heuristics. In addition, the architecture of knowledge-based system has features such as symbolic and structured programming, objects, rules manipulation, and ruletracing and explanation. Therefore, they are ideal candidates for development into intelligent tutoring systems (ITS). This paper explains how a knowledge-based design prototype system for progressive die design is developed into an ITS that can be used to teach authentic design activities both in the classroom and on-the-job. It illustrates how the flexibility offered in the trainee-system interaction facilitates the exploration of design alternatives and case studies to tackle open-ended design problems. The ITS uses a computer-aided design and drafting (CADD) system as the frontend and automates many of the tedious drafting, measurement, shape recognition and manipulation tasks associated with progressive die planning and design. Therefore, it promises to be a more effective training aid which can help shorten the traditionally long period of apprenticeship training program which a trainee has to follow.

Degrees of Mixed-Initiative Interaction in an Intelligent Tutoring System

Abstract: We are currently implementing CIRCSlM-Tutor v. 3, a conversation-based intelligent tutoring system (ITS) which tutors medical students on the baroreceptor reflex, a topic in cardiovascular physiology. In order to provide the most natural conversational experience possible, we would like to let the student take the initiative where possible. On the other hand, because of the increased complexity of the required infrastructure, the difficulty of understanding full free-text input, and the tutor’s desire to accomplish the tutoring agenda, we must restrict the types of initiatives which the system will attempt to respond to. We classify initiatives according to the nature of the student’s utterance and according to the type of processing required by the tutor to handle them. We describe how we encourage the student to give responses we can handle. We explain wily we believe that these methods do not restrict the student’s ability to communicate with the system or to learn the material. We illustrate the phenomena described with examples from human-to-human tutoring sessions.

Intelligent tutoring system as multiagent system

Abstract: Intelligent tutoring systems are important educational tools. They can be built using different methodologies and tools. In this paper a generic architecture for intelligent tutoring system as a multiagent system is presented. The agents in the architecture are programmed with AGLess-a specialized agent-oriented environment, This approach has been compared to an object-oriented approach based on object-oriented language, Less.

Challenges for a Mixed Initiative Spoken Dialog System for Oral Reading Tutoring

Abstract: Deciding when a task is complete and deciding when to intervene and provide assistance are two basic challenges for an intelligent tutoring system. This paper describes these decisions in the context of Project LISTEN, an oral reading tutor that listens to children read aloud and helps them. We present theoretical analysis and experimental results demonstrating that supporting mixed initiative interaction produces better decisions on the task completeness decision than either system-only or useronly initiative. We describe some desired characteristics of a solution to the intervention decision, and specify possible evaluation criteria for such a solution.

OBOA model of explanation module in intelligent tutoring shell

Abstract: The important characteristics of any intelligent systems are the possibilities of explanation. So, any software product which intend to be intelligent must provide some kind of explanation, i.e., explanation of some conclusions, explanation of new knowledge (theorem), etc. As Intelligent Tutoring Systems (ITSs) intend to be intelligent software, the explanation feature must be provided in ITSs. In this paper, we will briefly survey how we realized the explanation properties and features in Intelligent Tutoring System (ITS) shell called EduSof. The OBOA (OBject - Oriented Abstraction) model for representing the knowledge, interaction within that knowledge and actions on that knowledge is used for the model of explanation, the transitions and the interactions features in EduSof shell.

ADIS-an Animated Data Structure Intelligent Tutoring System on the WWW

Abstract: In today's information technology (IT) age, the traditional role of teachers and learners is being changed by multimedia courseware. Hypermedia offers much to learners in terms of providing an environment that engages the learner, allowing the construction of knowledge in a meaningful way. However, these packages lack intelligent tutors. Intelligent multimedia tutoring systems (IMTS) can offer some solutions by providing students multimedia interface features with the added ability to monitor the student's performance and to provide guidance towards the correct solution using methods of inquiry teaching. Current ITS suffer from expensive artificial intelligence (AI) inference engines, the inability for the expert to learn and handle radical strategy variability, and large empirical search spaces. Although a myriad of ITS exists, no one single topology provides a perfect solution. The main objective of this project was to provide an optimal solution to implementing an ITS component for the hypermedia IMTS, to coach in the domain of data structures. The pre-requisites for the topology chosen were low cost, high efficiency, platform independence, and the ability to be used on the World Wide Web (WWW). ADIS was successfully implemented and integrated with a graphical user interface (GUI) to interact with students The current framework contains the linked list, stack, and queue microworlds.

The Five Families of Cognitive Learning: A Context in Which To Conduct Cognitive Demands Analyses of Innovative Technologies

Abstract: A cognitive demands analysis of a learning technology, a term that includes the hardware and the computer software products that form learning environments, attempts to describe the types of cognitive learning expected of the individual by the technology. This paper explores the context of cognitive learning, suggesting five families of cognitive learning. These families are: (1) content understanding; (2) collaboration; (3) communication; (4) problem solving; and (5) metacognition. Three technologies are analyzed with reference to these types of learning. The first technology, Algebra Tutor, is an intelligent tutoring system to help students learn algebra skills. "Hands-On Universe" is an astronomical research environment for high school students. "Function Machines" is an application for a visual programming language designed for mathematics and science education. Analyses of the types of learning expected for each of these technologies have resulted in the development of a suite of performance tasks (an integrated simulation) that includes individual and collaborative concept mapping tasks, a problem-solving search task, an explanation task, and a metacognitive questionnaire. This assessment environment is integrated across grade levels and within content areas to blend real-world tasks with a project-based scenario that captures many types of cognitive learning. (Contains 1 table and 79 references.) (SLD) ******************************************************************************** Reproductions supplied by EDRS are the best that can be made from the original document. ******************************************************************************** THE FIVE FAMILIES OF COGNITIVE LEARNING: A CONTEXT IN WHICH TO CONDUCT COGNITIVE DEMANDS ANALYSES OF INNOVATIVE TECHNOLOGIES U.S. DEPARTMENT OF EDUCATION Office of Educational Research and Improvement EDUCATIONAL RESOURCES INFORMATION CENTER (ERIC) /This document has been reproduced as received from the person or organization originating it. Minor changes have been made to improve reproduction quality. Points of view or opinions stated in this document do not necessarily represent official OERI position or policy. Davina C. D. Klein National Center for Research on Evaluation, Standards. and Student Testing (CRESST) Graduate School of Education & Information Studies University of California, Los Angeles Harold F. O'Neil, Jr. University of Southern California/ National Center for Research on Evaluation. Standards, and Student Testing (CRESST) Robert A. Dennis National Center for Research on Evaluation, Standards. and Student Testing (CRESST) Graduate School of Education & Information Studies University of California, Los Angeles Eva L. Baker National Center for Research on Evaluation, Standards, and Student Testing (CRESST) Graduate School of Education & Information Studies University of California, Los Angeles BEST COP Y. AVIALABLE 2 RUNNING HEAD: FAMILIES OF COGNITIVE LEARNING

Using Multi-agent Approach for the Design of an Intelligent Learning Environment

Abstract: This paper presents FILIP, a multi-agent framework for the design of Intelligent Simulation-based Learning Environment (ISLE). Such a learning environment assesses the learner and provides adaptive instruction when the learner is developing his/her operational skill in dynamic and highly risky domains. The FILIP framework offers a great hope as a means of helping learners develop the skill necessary for effective performance. It is geared towards skill development and acquisition in order to develop and support operators performance. FILIP is designed as a multi agent architecture, which includes the seven agents: a simulator; a user interface; a domain expert agent; a learner agent; an instructor agent, a curriculum agent and a skill development agent. FILIP framework is distinguished from other traditional ISLE by its skill development agent and the curriculum agent. The skill development agent is to advise the instructor on issues related to the skill development of the learner so that it can be taken into account in the planning of the instruction. The curriculum agent is made of a Curriculum Formalism for Operational Skill Training (CFOST). It provides information for skill development agent to assess skill development and for the instructor agent to provide adaptive instruction.

Using fuzzy logic in ITS-course generation

Abstract: Shows how fuzzy logic has been used in the course building process. This process is based on the curriculum modeling approach that we have proposed, and exploits several knowledge sources, such as target-public knowledge and training requirements. By using these parameters, a fuzzy algorithm generates a course which is adapted to the given target public that can produce the required knowledge. The obtained course can be edited by the designer through graphical interfaces and can be delivered by an object-oriented intelligent tutoring system (ITS).

SimTutor: a multimedia intelligent tutoring system for simulation modeling

Abstract: SimTutor is a multimedia intelligent tutoring system (ITS) for simulation modeling. Multimedia systems are now de facto standard on personal computers and increasing number of intelligent tutoring systems incorporate multimedia systems to enhance interaction with students. SimTutor provides a graphical environment in which the student can practice conceptual model development and interact direct with different simulation modeling software. We used multimedia systems to enhance the pedagogy and for incorporating different strategy into the courseware design. ITS components are accessed through the graphical user interface, allowing them to be developed independently. The modular architecture allows for interoperability of applications with the same event changing protocol. An object-oriented approach is adapted to allow the system to evolve and to flexibly change the data.

The case-based intelligent tutoring system: an architecture for developing and maintaining operator expertise

Abstract: The case-based intelligent tutoring system (CB-ITS) is a proposed architecture for a computer-based training system for operators of complex dynamic systems. Intended for individuals who have already completed formal training, the goal of the CB-ITS is to help operators enhance and maintain expertise. The CB-ITS provides experience with prototypical and unusual operational situations (cases). The CB-ITS includes a simulator that allows a student to experience and practice the cases under the guidance of a computer-based tutor. The architecture uses the operator function model and OFMspert to provide intelligence and instructional control. This paper describes the CB-ITS architecture and enhancements to the operator function model and OFMspert to support an intelligent tutor that uses cases as pedagogy.

Designing an interface on the Web for an intelligent tutoring system

Abstract: The fundamental aim of computer-aided learning (CAL) is to communicate with the student The most important design feature is the user interface In our system, this involves the use of a keyboard and mouse for inputting mathematical expressions and controlling the behaviour of the software This article describes a software tool designed as an input tool (EqEditor) for an intelligent tutoring system (ITS) With respect to the benefits of graphical user interface (GUI) design, the principles of good design have been considered as a guideline for designing the interface The system was designed for the World Wide Web using an applet written in Java, and could be used as a distance learning tool for learning and teaching mathematics

An ITS Authoring Tool: Experimental Advanced Instructional Design Advisor

Abstract: The experimental Advanced Instructional Design Advisor (XAIDA) is one of the intelligent tutoring system (ITS) authoring tools presented at the AAAI 1997 Fall Symposium. This paper briefly describes the system including the Deliver (student mode) and Develop (authoring mode) components. Four shells are described although some exist only in a preliminary prototype. XAIDA is best used for creating tutors to teach maintenance of physical devices. Maintenance training is split into teaching the physical characteristics of the device, the theory of operation of the device, the procedural operations of the device, and troubleshooting problems with the device. Each of these shells is discussed below.

Automatic Problem Description from Model Program for Knowledge-based Programming Tutor

Abstract: Knowledge-based programming tutors are supposed to analyze the students‘ programs using knowledge of the concepts of programming language, skills to build programs, misconceptions of novice programmers, and information about the programs to be analyzed. The last one provides the programming tutor with the intentions of programmers, and this allows the tutor to do an intention-based diagnosis (Johnson, 1996). This is given to the system in the form of a problem description by human instructors. However, it is very hard for instructors to write a problem description. For instructors, the simplest way to describe a problem may be to write a model program of that problem. This paper describes the system named GOES, a GOal Extraction System, which extracts the purposes (Goals) of a model program automatically. GOES is a susbsystem of C-Tutor, a knowledge-based C Programing Tutor (Hahn et al., 1996). GOES extracts implemented plans from a model program, and then extract goals from the plans according to goal/plan hierarchies. The efficiency of GOES depends on the process of plan extraction. In GOES, only pairs of labels and variables of each statement are used to extract candidate plans. Exact matching is followed only for theses candidate plans. In addition, to extract plans more efficiently, we introduce the concept of necessary and sufficient conditions of a plan to the model program. Using this method, plan candidates can be extracted efficiently and successfully.

An ITS (Intelligent Tutoring System) on the WWW (World Wide Web)

Abstract: In this paper, we integrate an Intelligent Tutoring System (ITS) with World Wide Web (WWW) technology, investigate the benefits and limits of the WWW-based ITS, and study technical problems in system development and their solutions.

Conversation rebuilding: from the foreign language classroom to implementation in an intelligent tutoring system

Abstract: This paper shows how an innovative “communicative” technique in teaching foreign languages—Conversation Rebuilding (CR)—readily lends itself to implementation in an Intelligent Tutoring System (ITS). Classroom language teachers using CR get students to formulate acceptable utterances in a foreign idiom by starting from rough approximations (using words the students know) and gradually zeroing in on the utterance which a native speaker of that idiom might produce in a similar setting. The ITS presented here helps students do the “zeroing in” optimally. It lets them express themselves temporarily in an “interlingua” (i.e., in their own kind of French or English or whatever they are studying), as long as they make something of their communicative intent clear, that is, as long as the System can find a semantic starting point on which to build. The ITS then prods the students to express themselves more intelligibly, starting from the “key” elements (determined by a heuristic based on how expert classroom teachers proceed) and taking into consideration the students' past successful or unsuccessful attempts at communication. To simplify system design and programming, however, conversations are “constrained”: students playact characters in set dialogs and aim at coming up with what the characters actually say (not what they could possibly say). While most Intelligent Computer Assisted Language Learning (ICALL) focuses the attention of students on norms to acquire, the ICALL implementation of CR presented in this paper focuses the attention of students on saying something—indeed, almost anything—to keep the conversation going and get some kind of meaning across to the other party. It sees successful language acquisition primarily as the association of forms with intent, not simply as the conditioning of appropriate reflexes or the elaboration/recall of conceptualized rules (which are the by-products of successful communication). Thus, in espousing this hard-line communicative approach, the present paper makes a first, non-trivial point: ICALL researchers might usefully begin by investigating what the more able teachers are doing in the classroom, rather than by building elaborate computer simulations of out-dated practices, as happens all too often. The paper then goes on to describe the architecture of a prototype ITS based on CR—one that the authors have actually implemented and tested—for the acquisition of English as a foreign language. A sample learning session is transcribed to illustrate the man-machine interaction. Concluding remarks show how the present-day limits of ICALL (and Artificial Intelligence in general) can be partially circumvented by the strategy implemented in the program, i.e. by making the students feel they are creatively piloting an interaction rather than being tested by an unimaginative machine.

Intelligent tutoring system: an expert-system trainer for herring roe grading

Abstract: Describes an expert system developed to train humans to grade herring roe. The design features of the system are given. The system provides a user with some general information about the herring roe industry, how roe is processed and graded in an industrial plant, and an intelligent tutoring module. The knowledge was extracted from a human expert who is highly experienced in grading herring roe. The system runs under a convenient tool used to develop the expert system. An important criterion in the design of the grading trainer was user-friendliness, since most users are unlikely to be highly educated. To assess the progress of each user, an evaluation module is provided. A module to evaluate the reaction of a user to the system itself automatically validates the goal of the system. Based on the outcome of these modules, final comments are given to the user about his/her progress with the knowledge domain. In designing the training tutorial, different methods of associating information were used: exclusive sets, multi-choice sets, and fuzzy sets. Various types of questions are considered in training the user as well as simulating the realistic condition of grading in an industrial plant where each decision must be made in a fraction of a second. An example is given to illustrate the effectiveness of the system, by evaluating the grading capability of an inexperienced human grader before and after using the intelligent tutoring system.

TEx-Sys: an authoring tool for an intelligent tutoring system with hypermedia

Abstract: The integration of hypermedia and an intelligent tutoring system in a newly developed authoring tool TEx-Sys (Tutor-Expert System) is presented. The student explores cyberspace which is defined as domain knowledge like a cybernaut and acquires skills and knowledge. The TEx-Sys system is modularly structured and consists of a logic model, a tutor shell, a communication module in quasi-natural language, a questioning module and an evaluation module. Knowledge is represented by semantic networks with frame and production rules. Semantic networks apply different semantic entities and relations: nodes, links, properties, frames, property inheritance with inference engine, as well as multimedia and hypertext. The hypermedia with a rich attribute structure made by integration of multimedia and hypertext is associated with the objects in the knowledge-base. TEx-Sys is structured in a way which enables "guided free play" in accordance with the Piagetian paradigm of learning, student modelling and efficient control of the learning process.

CALAT: An intelligent CAI system using the World Wide Web

Abstract: This paper describes an intelligent CAI system, called CALAT, which provides an individual adaptation capability on the World Wide Web (WWW). CALAT consists of an intelligent tutoring system (ITS) on a WWW server. A newly developed user identification mechanism makes the system capable of adapting to individuals over the stateless protocol of the WWW. A viewer control mechanism using control script has also been developed in order to improve response speed and to implement viewer control capability from the server. An evaluation experiment shows that the individual adaptation capability works well and that the response speed is sufficient for practical use. CALAT is now in operation on the Internet. © 1997 Scripta Technica, Inc. Syst Comp Jpn, 28(9): 17–25, 1997