08 Nov 2019


Task analysis (TA) practice is used across a wide range of human-performed as well as automated skills and tasks in the design and development of procedures, training, and evaluations. Education environments for Virtual Reality (VR) have been shown to be useful objective evaluation methods for testing skills for laparoscopic surgery as well as providing effective means of education in such complex skills. VR simulation settings for laparoscopic surgery vary from basic so-called mobile phone or tablet box trainers to high-fidelity surgical simulators with sophisticated motion tracking metrics.

It has been shown that intelligent tutoring systems (ITS) are particularly valuable in teaching cognitive tasks such as troubleshooting, problem-solving, and critical situations. As a human teacher does, an ITS constantly tracks and reviews the behaviour of the individual student, infers the state of knowledge of the student, and decides on the next educational step to optimize the learning of the student based on an embedded student model, project model, and instructional model. As a recent meta-analysis has shown, ITS research and development have shown the technical feasibility and relative efficacy of computer-based adaptive learning compared to the classroom and small group teaching. The design of ITS has been extended across several areas, including military applications such as ship handling and tactical decision-making. In addition, previous development efforts have demonstrated the ability to easily adapt standard ITS components to specific military environments, such as authoring tools.

Intelligent tutoring systems (ITS) have two objectives: to provide advanced, one-on-one instructional guidance that is better than conventional computer-aided instruction and equivalent to that of a good human tutor; and to build and test models on the cognitive processes involved in instruction. ITS intelligence stems from the implementation of artificial intelligence techniques used in four components which interact: The knowledge base includes the domain knowledge, the student model reflects the current state of knowledge of the student, the pedagogical module contains relevant instructional steps based on the student model’s content, and the user interface allows an active dialogue between ITS and the student. The knowledge base is typically the central part of the instructional system, but there are a number of strategies that also rely on the other components. Although many fascinating theoretical insights have been provided by research on ITS, there are very few ITS that are currently used and very few that are routinely used in schools.

A student learns mainly by solving problems from an intelligent system–problems that are carefully chosen or tailor-made, and that serve as learning experiences for that student. The program will start by reviewing what the student already knows. Student information is kept in what is called the student template, which is modified during the learning process. The program must then decide what needs to be known to the student. In the domain-expert model, this knowledge is expressed. Eventually, the program must determine which unit of content should be addressed first (e.g. assessment function or instructional element) and how to present it. The pedagogical method (or tutor) does this. The process selects or creates a problem from all of these criteria, either figure out a solution to the problem (through the domain-expert model) or seeks a ready-made solution. The smart device compares its approach to the one prepared by the student and conducts a diagnosis based on differences between the two as well as other available information in the student model. The system provides feedback based on factors such as how long it has been since the last feedback was given, whether the student has already provided any specific advice, and so on.

The software will then update the student model and restart the entire cycle, beginning with selecting or creating a new issue. Despite the great promises of smart systems, they are not currently commonly used in schools, partly due to their expense, and also due to limitations in measurement. We are now focused more closely on the latter, explaining how evaluations vary from conventional smart systems to newer, improved smart systems. This is intended to provide the framework on which to explore in intelligent systems a new view of academic measurement.

Leave a Reply

Notify of