No abstract

This article describes the evolution and current state of the domainindependent Siette assessment environment. Siette supports different assessment methods-including classical test theory, item response theory, and computer adaptive testing-and integrates them with multidimensional student models used by intelligent educational systems. Teachers can use an authoring tool to create large item pools of different types of questions, including multiple choice, open answer, generative questions, and complex tasks. Siette can be used for formative and summative assessment and incorporates different learning elements, including scaffolding features, such as hints, feedback, and misconceptions. It includes numerous other features covering different educational needs and techniques, such as spaced repetition, collaborative testing, or pervasive learning. Siette is designed as a web-based assessment component that can be semantically integrated with intelligent systems or with large LMSs, such as Moodle. This article reviews the evolution of the Siette system, presents information on its use, and analyses this information from a broader and critical perspective on the use of intelligent systems in education.

Abstract. Most of the information of the WWW is not adaptive, rather it is dispersed and disorganized. Another difficulty is to find tools that help to create adaptive courses. SIGUE is an author tool that makes it possible to build adaptive courses using web pages that already exist. This means that if there is a lot of information on the web about the same topic the author doesn't have to design the content of a specific course, he can reuse these pages to build his own course, taking the best pages for the concepts he wants to explain. The author can also construct adaptive courses reusing previously non-adaptive ones. SIGUE provides an enhanced interface for the student, controls his interaction, and annotates the visited links in a student model.

No abstract

No abstract

No abstract

This paper describes the development of statistical classifiers to help diagnose meningococcal meningitis, i.e. the most sever, infectious and deadliest type of this disease. The goal is to find a mechanism able to determine whether a patient has this type of meningitis from a set of symptoms that can be directly observed in the earliest stages of this pathology. Currently, in Brazil, a country that is heavily affected by meningitis, all suspected cases require immediate hospitalization and the beginning of a treatment with invasive tests and medicines. This procedure, therefore, entails expensive treatments unaffordable in less developed regions. For this purpose, we have gathered together a dataset of 22,602 records of suspected meningitis cases from the Brazilian state of Bahia. Seven classification techniques have been applied from input data of nine symptoms and other information about the patient such as age, sex and the area they live in, and a 10 cross-fold validation has been performed. Results show that the techniques applied are suitable for diagnosing the meningococcal meningitis. Several indexes, such as precision, recall or ROC area, have been computed to show the accuracy of the models. All of them provide good results, but the best corresponds to the J48 classifier with a precision of 0.942 and a ROC area over 0.95. These results indicate that our model can indeed help lead to a non-invasive and early diagnosis of this pathology. This is especially useful in less developed areas, where the epidemiologic risk is usually high and medical expenses, sometimes, unaffordable.

No abstract