RESUMO Após 64 anos de seu surgimento, a Inteligência Artificial (IA) enfrenta o complexo e o incerto dos nossos dias. Nesse período de sua existência, podem-se destacar dois “invernos” (1980 e 1993) em que as aplicações eram interessantes, mas a IA não conseguiu dar respostas adequadas: na compreensão da linguagem e no diagnóstico médico. Por outro lado, a IA apresentou duas décadas de progressos (2000 e 2010), em que as aplicações se mantiveram, mas as respostas da IA apresentaram avanços na tradução automática (Google), no reconhecimento de imagens (a primeira a utilizar a tecnologia foi a Apple, no iPhone 10), diagnóstico do câncer (IBM Watson) e carros autônomos (dentre outras, a Tesla). Este texto é fruto da revisão sistemática da literatura e da experiência da autora na área.

ABSTRACT Sixty-four years after its emergence, Artificial Intelligence (AI) faces the complexity and uncertainty of our day. During this period, two “winters” (1980 and 1993) can be highlighted where applications were interesting, but AI was not able to provide adequate responses, for example, in understanding language and in medical diagnosis. On the other hand, AI enjoyed two decades of progress (2000 and 2010), where the applications remained, but AI responses advanced in automatic translation (Google), image recognition (Apple was the first to use the technology, on its iPhone X), cancer diagnosis (IBM’s Watson) and autonomous cars (among others, Tesla). This text is the result of a systematic review of the literature and of the author’s experience in the area.

Adaptation is a desirable feature in on-line courses which allows for the consideration of students particular characteristics and needs. However, it is not common for teachers to embrace technologies related to this feature. This phenomenon may be mainly attributed to: a) unawareness of appropriate authoring tools, and/or b) resistance to their use. Regarding this panorama, this research has two purposes. The first purpose is to present a web platform to create adaptive on-line courses that considers three adaptive functionalities: curriculum sequencing, content presentation and assessment. The second purpose is to present a validation for such platform with real users, more specifically, 51 teachers of K-12. The obtained results show that even if there was general distrust while using the platform, there was also an overall interest in rely on a tool that grants teachers in providing an individualized learning experience.

La adaptación es una funcionalidad deseable de los cursos en línea pues, permite la consideración de las necesidades y características propias de cada estudiante. Pese a esto, no es común que los profesores adopten tecnologías relacionadas con esta funcionalidad, lo cual se debe principalmente a: a) el desconocimiento de herramientas de autor apropiadas; y b) la resistencia frente a su uso. El presente estudio tiene dos propósitos. El primero es presentar una herramienta de autor para crear cursos en línea adaptativos considerando tres funcionalidades particulares: secuenciación del currículo, presentación de contenido, y evaluación. El segundo es presentar una validación de dicha herramienta con usuarios reales, más específicamente 51 profesores de básica primaria y secundaria. Los resultados obtenidos muestran que pese a existir desconfianza por parte de los profesores a la hora de utilizar la herramienta, existe un interés general por contar con una alternativa que les permita brindar una experiencia de enseñanza/aprendizaje individualizada.

Los recursos educativos almacenados en repositorios digitales requieren de metadatos que los describan adecuadamente y son fundamentales en procesos de búsqueda y recuperación. El objetivo de este artículo es realizar una aproximación al cálculo y evaluación de métricas que permitan determinar el nivel de calidad del etiquetado de recursos digitales, específicamente de Objetos de Aprendizaje (OAs). El enfoque adoptado establece cómo evaluar los recursos teniendo en cuenta tres dimensiones: completitud, consistencia y coherencia, con base en el estándar IEEE LOM. Con el fin de validar los resultados obtenidos al aplicar las métricas se realizaron pruebas experimentales con OAs sintéticos y reales, concluyendo que las mismas permiten evaluar la calidad de los metadatos involucrados. De esta manera, la propuesta presentada se convierte en un insumo relevante para procesos de evaluación automática de metadatos, así como para la administración de repositorios y procesos de recomendación de OAs..

Educational digital resources stored in repositories require metadata in order to describe them properly, and are fundamental for searching and retrieval processes. The aim of this paper is to present an approach for the calculation of metrics that determine the quality level of labeling digital resources, specifically Learning Objects (LOs). We describe how to evaluate resources considering three dimensions such as completeness, consistency and coherence, based on the standard IEEE LOM. In order to validate the results that such metrics exhibit, some experimental tests were performed with synthetic and real OAs, concluding that they allows evaluating the quality of the metadata involved. This way, the proposal presented turns to be a plausible and relevant input for the automatic evaluation of metadata, as well as for the LOs repository management and recommendation processes.

En este artículo se presenta la evaluación de la eficiencia de las búsquedas sobre una federación de repositorios de objetos de aprendizaje, en particular la Federação de Repositórios Educa Brasil - FEB, respecto a la velocidad de respuesta y cantidad de registros recuperados. El objetivo es determinar las bondades de esta arquitectura en las búsquedas centralizadas sobre recursos distribuidos, pensando en un futuro cercano en realizar una implementación similar para Colombia. Tal evaluación se llevó a cabo mediante un experimento, usando 10 términos de búsqueda del campo de la salud, y se hizo una comparación entre FEB y dos repositorios reconocidos: MERLOT y The Gateway. Para no tener sesgos respecto a los momentos y orígenes de las búsquedas, estas se realizaron 30 veces, cada una desde 3 ubicaciones diferentes: Brasil, Colombia y España. Los resultados obtenidos demostraron un menor tiempo promedio de respuesta estadísticamente significante comparado con MERLOT (valor P < 0,001), pero mayor comparado con The Gateway (valor P < 0,001). Finalmente, se evidenció un crecimiento constante de la cantidad de objetos de aprendizaje registrados en FEB durante los últimos dos años.

In this paper, it is presented the assessment of the searching performance over a federation of learning objects repositories, in particular the Federação de Repositórios Educa Brasil - FEB, with regard to the response speed and quantity of retrieved records. The aim is to determine the benefits of this structure in the centralized searches over distributed resources, thinking in a near future to build a similar implementation for Colombia. Such an evaluation was done throughout an experiment with 10 search terms in the health field and a comparison was made between FEB and two well-known repositories: MERLOT and The Gateway. In order to avoid biases regarding the searching times and locations, such searches were done 30 times from 3 different locations each: Brazil, Colombia and Spain. The results obtained showed a lower mean response time which was statistically significant compared to MERLOT (P value < 0,001), but a larger time compared to The Gateway (P value < 0,001). Finally, a continuous grow was evident in the amount of learning objects registered in FEB during the last two years.

This article introduces an open-source module responsible for the presentation of verbal (speech) and corporal (animation) behaviors of animated pedagogical agents. This module can be inserted into any learning environment regardless of application domain and platform, being executable under different operating systems. It was implemented in Java as a reactive agent (named Body agent) that communicates with the agent's Mind through a language known as FIPA-ACL. Therefore, it may be inserted into any intelligent learning environment that is also capable to communicate using FIPA-ACL. Persistence of information is ensured by XML files, increasing the agent's portability. The agent also includes a mechanism for automatically updating new behaviors and characters once available in the server. A simulation environment was conceived to test the proposed agent.

The goal of this paper is to describe a system-aided performance and composition tool that aims to expand guitarist capacities by providing innovative ways in which the user can interact with the system. In order to achieve that, we decided to use an agent-based approach, independently modeling the active elements involved in a guitar performance as autonomous agents - named Left-Hand, Right-Hand, and Speaker (the guitar itself). These agents are able to communicate to each other in order to make some musical decisions, specially related to the chord's shape choice. The musical elements (harmony and rhythm) are independently defined respectively by the Left-Hand and Right-Hand agents. The most relevant aspects of this work, however, are the algorithms and strategies to process both harmonic and rhythmic data. Finally, we perform an evaluation of the system and discuss the results of the implemented techniques.

Este artigo apresenta os resultados obtidos no projeto conjunto entre o Instituto de Informática da UFRGS (II-UFRGS) e o Departamento de Informática da UCS (DEIN/UCS), cujo propósito foi a proposição e o desenvolvimento de um ambiente educacional multiagentes, baseado na web. O foco principal da pesquisa está no desenvolvimento de um modelo de representação do conhecimento para a construção de agentes inteligentes, capazes de atuar em situações reais de ensino e aprendizagem. Em particular, o foco está no uso de métodos probabilísticos de representação do conhecimento, para a realização de diagnósticos clínicos.

This paper presents some results about a join Project between Instituto de Informática da UFRGS (II-UFRGS) and Departamento de Informática da UCS (DEIN/UCS), that proposed and implemented an educational multi-agent environment based at web. The research focus is on the knowledge representation applied to the construction of intelligent agents able to act in educational real environments. More specifically, the work aims at applying probabilistic knowledge representation in the aid to medical diagnostic in educational applications.