Computer-assisted Instruction System Research Articles

Intelligent CAI in engineering: Knowledge representation strategies to facilitate model-based reasoning

This article describes an architecture for an intelligent computer-assisted instruction (ICAI) system for use in engineering domains. A qualitative model is utilized for representing the physical characteristics and operating methodologies of the systems tutored; planning techniques are employed for instruction using a text-based tutor; reasoning about the engineering model and about the student behavior during instruction is accomplished using a production system. Examples are drawn from two specific implementations: tutorials about (1) a hot water heater and (2) a power distribution system. Specific recommendations are given for implementing ICAI systems in engineering domains.

A framework for ICAI systems based on inductive inference and logic programming

The main components of an Intelligent Computer-Assisted Instruction (ICAI) system are the expertise, the student model and tutoring strategies. The student model manages what the student dose and dose not understand, and the performance of an ICAI system depends largely on how well the student model approximates the human student. We propose a new framework for ICAI systems which uses the inductive inference for constructing the student model from the student’s behavior. In the framework, both the expertise and the student model are represented as Prolog programs, which enables to express the meta-knowledge that is the knowledge of how to use the knowledge. Since the construction of the student models is performed independently of the expertise, the framework is domain-independent. Therefore, an ICAI system for any subject area can be built with the framework. As an example, the ICAI system teaching chemical reaction is presented together with a sample performance. The authors believe that the new framework for ICAI systems based on logic programming and inductive inference could be a breakthrough of the future ICAI systems.

Computer assisted instruction for therapy of heart failure based on simulation of cardiovascular system

Adequate treatment of cardiac failure should reflect both clinical rules and quantitative evaluation of hemodynamics. For the latter we assumed an extensive model of heart and vessels: For the left and right ventricles the EMAX models were assumed with the parameters of contractilities and diastolic compliances. The model of the vessels was composed of systemic and pulmonary vascular networks with arterial, capillary and venous segments. Heart failure of various types was simulated by the model and the optimal therapeutic regimen was formulated. The cardiovasular parameters of patients with heart failure could be esimated from the hemodynamic measurements through the model and the optimal therapy was computed with the technique of nonlinear programming.The simulation thechnique was incorporated in the computer assisted instruction system based on the clinical emirical rules. The program was written with TURBO PASCAL for a microcomputer with CPU 80286. The response time was within a tolerable range for use in the clinical practice.

A Study of a Computer-Assisted Instructional System Using Causal Modeling

A causal model was developed to test the effects of scholastic ability, computing attitudes, and computing background on the use of a computer-assisted instruction (CAI) system called PLATO-LDEC, on attitudes about PLATO-LDEC, on computing attitudes after student's PLATO-LDEC experience, and on course grade. In general, the greater a student's ability as measured by the SAT, the less time the student spent using the PLATO-LDEC courseware. Students' prior attitudes about computers had an effect on how they perceived PLATO-LDEC and how they perceived computers after their CAI experience. Neither prior computing attitudes nor computing background had any effect on PLATO-LDEC usage, and only computing background had a small effect on course grade.

Development of computer-assisted instruction systems with intelligent capabilities

The primitive answer analyzers in the existing CAI systems are usually designed to compare the incoming word sequence with the reference answers provided by the author of the course (AUTHOR in what follows), and the data base in these systems reflects the subject area on the level of links between the instruction pages. This imposes certain constraints on the allowed answers, creating difficulties in knowledge monitoring and design and modification of the course material; it essentially complicates the natural interaction of the user with the system.

Computer-assisted instruction. An overview.

The development of computer-assisted instruction (CAI) is discussed and definition of major concepts is presented. The three major types of CAI (drill and practice, tutorials, and simulations) are defined and examples given for each. The impact of CAI in nursing is discussed and several CAI systems are described.

Intelligent tutoring systems survey

Simple computer assisted instruction (CAI) systems suffer from the fact that in general they do not know the subject matter they are teaching. Intelligent tutoring systems (ITS) use artificial intelligence (AI) formalisms to represent knowledge in order to improve on CAI systems. We survey a number of systems developed, and the emerging architecture for ITS development.

Using planning techniques in intelligent tutoring systems

This paper proposes an architecture for building better Computer-Assisted Instruction (CAI) programs by applying and extending Artificial Intelligence (AI) techniques which were developed for planning and controlling the actions of robots. A detailed example shows how programs built according to this architecture are able to plan global teaching strategies using local information. Since the student's behavior can never be accurately predicted, the pre-planned teaching strategies may be foiled by sudden surprises and obstacles. In such cases, the planning component of the program is dynamically reinvoked to revise the unsuccessful strategy, often by recognizing student misconceptions and planning a means to correct them. This plan-based teaching strategy scheme makes use of global course knowledge in a flexible way that avoids the rigidity of earlier CAI systems. It also allows larger courses to be built than has been possible in most AI-based “intelligent tutoring systems” (ITSs), which seldom address the problem of global teaching strategies.

Applications of artificial intelligence within education

Computers have been employed within the field of education for many years, often with disappointing results. However, recent and current research within the field of artificial intelligence (AI) is having a positive impact on educational applications. For example, there now exist ICAI (intelligent computer-assisted instruction) systems to teach or tutor many different subjects; several such systems are discussed herein. In addition to CAI (computer-assisted instruction) systems, we discuss the development of learning environments that are designed to facilitate student-initiated learning. A third major application is the use of expert systems to assist with educational diagnosis and assessment. During the course of our discussion of these three major application areas, we indicate where AI has already played a major role in the development of such systems and where further research is required in order to overcome current limitations.

The Use of Interactive Video and Videodisc for Preservice and Inservice Education

This article describes the concept of interactive video. Emphasis is placed on the use of the video disc in connection with microcomputers. The different types of videodisc systems are described and the levels of interactivity are presented. The advantages of a video disc storage system for computer-assisted instruction (CAI) are compared to video tape. Some examples of contemporary software utilizing interactive video and the laser videodisc are presented. Applications for the specialist in communication disorders in the area of faculty and staff development, student educational programming and clinical praeticum are put forth.

Interactive Video Authoring of Instruction for the Mentally Handicapped

The article describes the development and field testing of a Microcomputer/Videodisc computer assisted instruction system for mentally handicapped students with primary emphasis on the authoring system, which is a set of computer programs designed to allow noncomputer programmers to write instructional programs for use with the Microcomputer/Videodisc system. The objectives of the authoring system were evaluated as part of the overall field tests. Evaluation results are reported along with details on the operational aspects of the authoring system.

Classroom use of personal computers in medical education: a practical approach.

Classroom lectures in medical schools have traditionally employed a blackboard and slides. We have developed a compact, durable, and relatively low-priced system for computer-assisted instruction which introduces audiovisual material in a random-access manner. When this system was used in the classroom to provide flexible, clinical simulations, it promoted a high level of audience-instructor interaction and facilitated problem-based learning. The system has been used successfully in lectures in our medical school, at other medical schools, at community hospitals and at national scientific meetings.

Computer-Assisted Instruction and Its Use in Occupational Therapy Education

Abstract A computer-assisted instruction system is described in this paper, and the rationale for integrating this system into an occupational therapy course is discussed. Student performance in this course is apparently enhanced by using computer-assisted instruction. Attitudes of both students and faculty concerning the use of a computer for instruction are also discussed.

CAI: Goals and perspectives: Computer users’ group panel discussion

This report of the users’ group meeting contains a condensed version of a panel discussion of general issues involving computer-assisted instruction (CAI) systems. The discussants were asked to comment on the goals of the CAI efforts and the past accomplishments and future of computer systems in education.

ARIS: A computer-assisted instruction system

The automated real-time instructional system (ARIS) is a small computer-assisted instructional system written to run under the UNIX operating system on a PDP-11/34A machine. ARIS is a tool used to provide highly individualized instruction and, at the same time, to study the process of learning by keeping detailed records of students’ actions. Currently, the system is used to teach logic and set theory. This paper describes the general philosophy, operation, and implementation of ARIS.

Computer-Assisted Instruction in Word-Decoding for Educationally-Handicapped Children

A computer-assisted instruction system for drilling educationally-handicapped children in word-decoding skills is described. The system allows a teacher to design a word-decoding exercise tailored to the need of an individual learner. The computer then generates, presents and monitors the exercise. A theoretical rationale for the objectives and design of the system, based on research from the psychology-of-reading literature, is discussed. In addition, certain system design constraints, applied in order to accommodate the possibility of future conversion of the system to an inexpensive, hand-held device, are discussed. Results of a controlled field test of the system with educationally-handicapped children are presented.

An evaluation of the costs of computer-assisted instruction

The purpose of this paper is to estimate the costs and cost feasibility of utilizing computer-assisted instruction (CAI) for compensatory education. Cost data were collected from an experiment on the effectiveness of CAI that had been established in Los Angeles and sponsored by the National Institute of Education. Based upon the resource ingredients approach to measuring costs, it was found that up to three daily 10-minute sessions of drill and practice could be provided for each disadvantaged child within the 1977–1978 allocation of funds from Title I of the Elementary and Secondary Education Act of 1965. If the computer system were shared between two schools, the higher costs would permit only two daily sessions. Costs were also estimated for a more advanced CAI system, and somewhat surprisingly the costs were in the same range. This finding reflects the very heavy costs of “software” that do not seem to decline with more advanced technologies. Also, it is possible that the latter technology will be found to be more effective at the same cost level. However, because comparative effectiveness data between the CAI approach and other instructional strategies are not readily available, such cost-effectiveness comparisons will have to be deferred until some future date.

Use of Adaptive Information for Advisement in Learning Concepts and Rules Using Computer-assisted Instruction

Findings from two experiments showed that students can effectively manage their learning needs in a computer-assisted instructional system when provided continuous, updated advisement information about their achievement (diagnosis) and instructional needs (prescription) in relation to the objective. In Experiment 1, high school students receiving instruction (learning four physics concepts) via a learner-adaptive-control management strategy that included advisement performed better on the posttest than students in a learner-control strategy (p > .001) and needed less instructional time than students in a program-managed, adaptive-control strategy (p > .001). Experiment 2 replicated the effectiveness of the learner-adaptive-control strategy by showing that students were able to make increasingly better self-assessments and management decisions during three separate instructional units (learning nine punctuation rules) than either a learner-partial-control strategy (p > .001) or a learner-control strategy (p > .001).

Using a Computer Game to Reinforce Skills in Addition Basic Facts in Second Grade

Early work in computer-assisted instruction (CAI) involved using the computer to present drill-and-practice exercises to the student (e.g., Suppes, Jerman, & Brian, 1968; Suppes & Morningstar, 1972). Since the computer can provide immediate feedback to the student and can control the sequence in which the exercises are presented, such CAI has generally proven to be effective, although the cost-effectiveness of such systems of programmed instruction has been questioned (Vinsonhaler & Bass, 1972). Two large CAI systems, PLATO and TICCIT, have incorporated games, simulation, and the use of graphics. Although evaluations of the affective and cognitive effects of these systems have produced mixed results, they have established that such systems do have a place in the curriculum (Alderman, Oppel, & Murphy, 1978). In recent years there has been an increasing interest in research on the effects of instructional games (Reiser & Gerlach, 1976; Bright, Harvey, & Wheeler, Note 1). Two studies in grades 4, 5, and 6 conducted by Bright, Harvey, and Wheeler (1979, 1980) have shown that games can be effective at the post-instructional level in retraining and maintaining skill in multiplication basic facts. This study is an extension of the Bright, Harvey, and Wheeler games research to addition basic facts in a primary grade and to the implementation of the game on a microcomputer. The question addressed was Can a computer game be used to increase proficiency at the post-instructional level in addition basic facts in the second grade?

Use of Adaptive Information for Advisement in Learning Concepts and Rules Using Computer-Assisted Instruction

Findings from two experiments showed that students can effectively manage their learning needs in a computer-assisted instructional system when provided continuous, updated advisement information about their achievement (diagnosis) and instructional needs (prescription) in relation to the objective. In Experiment 1, high school students receiving instruction (learning four physics concepts) via a learner-adaptive-control management strategy that included advisement performed better on the posttest than students in a learner-control strategy (p > .001) and needed less instructional time than students in a program-managed, adaptive-control strategy (p > .001). Experiment 2 replicated the effectiveness of the learner-adaptive-control strategy by showing that students were able to make increasingly better self-assessments and management decisions during three separate instructional units (learning nine punctuation rules) than either a learner-partial-control strategy (p > .001) or a learner-control strategy (p > .001).