Alenka Kavcic

Fuzzy user modeling for adaptation in educational hypermedia

Education is a dominating application area for adaptive hypermedia. Web-based adaptive educational systems incorporate complex intelligent tutoring techniques, which enable the system to recognize an individual user and their needs, and consequently adapt the instructional sequence. The personalization is done through the user model, which collects information about the user. Since the description of user knowledge and features also involves imprecision and vagueness, a user model has to be designed that is able to deal with this uncertainty. This paper presents a way of describing the uncertainty of user knowledge, which is used for user knowledge modeling in an adaptive educational system. The system builds on the concept domain model. A fuzzy user model is proposed to deal with vagueness in the users knowledge description. The model uses fuzzy sets for knowledge representation and linguistic rules for model updating. The data from the fuzzy user model form the basis for the system adaptation, which implements various navigation support techniques. The evaluation of the presented educational system has shown that the system and its adaptation techniques provide a valuable, easy-to-use tool, which positively affects user knowledge acquisition and, therefore, leads to better learning results.

The role of user models in adaptive hypermedia systems

Computers have been used in education from the beginning. Educational systems have developed first from computer assisted learning systems to more complex intelligent tutoring systems and hypermedia systems. Intelligent tutoring systems are knowledge centred and are able to adapt the instructional sequence to the particular user. On the other hand, hypermedia systems are based on hypermedia and the user can freely browse the learning material. The last two technologies have merged into so called adaptive hypermedia systems. They are actually hypermedia systems, which incorporate some intelligent tutoring techniques. Therefore, they offer the freedom of exploratory learning, yet dynamically adapt to the individual users knowledge level and learning goals, provide intelligent guidance, and support the user in acquiring knowledge. In intelligent tutoring systems, the adaptation is based on user modelling. Since adaptive hypermedia systems take the adaptation principles from intelligent tutoring systems, they also use user models for adapting the system to a particular user. Hence, the user model is one of the most important components for adaptation. Although the adaptation itself can be realised through different techniques, it is always based on the user model. In the paper, adaptive hypermedia systems and their general structure are described first. Then the role of a user model is presented together with the various approaches to user modelling in adaptive hypermedia systems. Finally, we investigate user modelling in different educational adaptive hypermedia systems.

Student modeling based on fuzzy inference mechanisms

The paper presents a competence-based instructional design system and a way to provide a personalization of navigation in the course content. The navigation aid tool builds on the competence graph and the student model, which includes the elements of uncertainty in the assessment of students. An individualized navigation graph is constructed for each student, suggesting the competences the student is more prepared to study. We use fuzzy set theory for dealing with uncertainty. The marks of the assessment tests are transformed into linguistic terms and used for assigning values to linguistic variables. For each competence, the level of difficulty and the level of knowing its prerequisites are calculated based on the assessment marks. Using these linguistic variables and approximate reasoning (fuzzy IF-THEN rules), a crisp category is assigned to each competence regarding its level of recommendation.

Evaluating Comparisons and Evaluations of Learning Management Systems

In the last years, numerous papers were published comparing different learning management systems (LMS). Some of them dealt with only few comparison criteria, while others included almost every imaginable feature. When faced to do a comparison ourselves, we came across many of such papers and did a research of what authors considered relevant in an LMS. By comparing papers written in different years, we tried to find out if there is a pattern of features linked to a certain time period, how a demand for new features was evolving through time, and how did LMS developers respond to this demand. We also tried to figure out the present demands and which new features will be included in future versions of LMSs.

On detecting note onsets in piano music

This paper presents an overview of our researches in the use of connectionist systems for transcription of polyphonic piano music and concentrates on the issue of onset detection in musical signals. We propose a new technique for detecting onsets in a piano performance. The technique is based on a combination of a bank of auditory filters, a network of integrate-and-fire neurons and a multilayer perceptron. Such a structure introduces several advantages over the standard peak-picking onset detection approach and we present its performance on several synthesized and real piano recordings. Results show that our approach represents a viable alternative to existing onset detection algorithms.

Educational hypermedia: an evaluation study

The role of computers in education has changed significantly in the last years. Educational systems have exceeded passive teaming systems and now actively participate in the teaming process. Web-based educational systems, for example, supported by incorporated intelligent tutoring techniques, are able to adapt information and its presentation to each individual user, and dynamically support navigation through the hypermedia material. This paper deals with the evaluation of educational hypermedia. An adaptive hypermedia system was developed and implemented for this purposes. The system is based on a concept domain model and also considers the elements of knowledge uncertainty in the process of user modelling. Both models are used for system adaptation, which builds on adaptive link insertion in addition to traditional adaptive navigation support technologies, like annotation and direct guidance. The system has been evaluated in a real environment and the results of the experiments are discussed here. In the paper, adaptive hypermedia systems in general are described first. Then our system is described, which was used in the evaluation study. In the end, the experiments are described and the results analysed in details.

Software Accessibility: Recommendations and Guidelines

The paper deals with problems that people with special needs have when using information technology products. Many software developers are not even aware of the problem, although people with disabilities nowadays represent a considerably market share. In recent times, more accessible software design is encouraged also by the national laws. The aim of this paper is to point out the difficulties and obstacles that most software applications pose to the disabled people and to seek for the guidelines on accessible software design

Fuzzy student model in InterMediActor platform

The paper deals with personalization of navigation in the educational content, introduced in a competence-based instructional design system InterMediActor. The system constructs an individualized navigation graph for each student and thus suggests the learning objectives the student is most prepared to attain. The navigation tools rely on the graph of dependencies between competences, and the student model. We use fuzzy set theory for dealing with uncertainty in the assessment of students: the marks of assessment tests are transformed into linguistic terms, which are assigned to linguistic variables. Fuzzy IF-THEN rules are applied to obtain the appropriate categories of competences in the navigation graph

Implementing content packaging standards

The paper deals with the issue of standards and specifications applied to educational digital content. Content packaging has to comply to standards to assure its interoperability and portability, as well as facilitate search and discovery, accessibility, and (re)use. Two most common packaging standards for educational content are described in the paper: already recognized and widely used ADL SCORM, and a newcomer in the field, IMS Common Cartridge, which successfully overcomes some problems of using modern Web technologies in education. We also describe our experience in implementing these standards, the problems, and advantages of using such packaged content.

A platform for supporting learning process of visually impaired children

Although ICT supported tools and e-learning material are widely available in schools to support teaching and learning, there is still a lack of specific tools and material designated for children with impairments. The costs of adapting and preparing such material is often economically not justifiable due to a small number of such children, and commonly, for the best leaning outcome the material has to be adapted for each individual child and their deficits and level of impairments. Our solution to this problem is a web platform for delivering customized exercises intended for visually impaired children. There are two sorts of exercises already prepared: a tutorial for learning and practicing Braille and ten-finger typing, and various exercises for practicing vision, memory, and motor skills. For each individual impaired learner, the teacher can select appropriate type of exercise and customize it by adjusting visual aspects of the exercise, setting the specific content (e.g., words for typing, or items to sort), or selecting the level of difficulty (e.g., set timing, complexity levels, or number of shown images). A set of such customized exercises is given to a learner for practicing and their progress is constantly monitored and saved for later inspection.