No abstract

The integration of interaction and simulation in elearning systems represents a milestone in educational research and supports the student's learning process in innumerable ways. Nevertheless, current standards do not provide appropriate mechanisms to obtain a significant assessment about the student's performance while interacting with a simulation neither to influence on the teaching-learning process. This work proposes a SCORM-compliant architecture which includes a Tutoring Module for Simulations (TMS). The main objective consists in providing mechanisms to track and "observe" the student's performance (while interacting with a simulation), thus enabling the TMS to take decisions or intervene when necessary, and/or to modify the course of the simulation.

ResumenEl objetivo de este documento es presentar una propuesta de un Sistema Inteligente de Tutoría para entrenamiento procedimental en un entorno virtual 2D/3D, capaz de mantener un diálogo en lenguaje natural basado en el contexto. De esta manera, cada alumno será capacitado por medio de un diálogo en lenguaje natural que tome en cuenta sus características específicas, su progreso en el desarrollo de la tarea y el entorno donde se realiza la tarea. Por lo tanto, la retroalimentación de tutoría será el resultado de un diálogo adaptado al contexto. Para dar soporte al diálogo, se utilizará un gestor de diálogo, construido sobre alguna de las plataformas conocidas para la creación de gestores de diálogo actualmente disponibles. Palabras Clave: Sistema Inteligente de Tutoría, Procesamiento de Lenguaje Natural, Diálogo adaptado al Contexto. AbstractIn order to provide support environments for education, the aim of this paper is to present a proposal for an Intelligent Tutoring System for procedural training in a 2D / 3D virtual environment, capable of maintaining a dialogue in natural language based on the context. In this way, each student will be trained through a dialogue in natural language that takes into account the students' specific characteristics, their progress in the development of the task and the environment where the task is performed. Therefore, the tutoring feedback will be the result of a dialogue adapted to the context. To support the dialogue, a dialogue manager will be used, built on one of the currently available

A priority objective in knowledge-based systems (KBS) engineering is quality assurance. Within the knowledge engineering, there is a discipline, usually referred to as Verification & Validation (V&V), whose goal is to ensure the quality of a KBS. One area of research in V&V is related to establishing whether the KBS meets a series of formal properties. Indeed, a lot of work has been done on verifying KBS consistency. As a result of these research efforts, some computerize methods for identifying anomalies in the KBS structure that could potentially produce incorrect outputs have been proposed. This thesis takes a step forward in the area of V&V methods. It presents a method, called MECORI, for detecting semantic inconsistencies in hybrid KBS using production rules and frame hierarchies. A semantic inconsistency occurs whenever the KBS is able to deduce a set of facts that are incompatible with the KBS application domain. Semantic inconsistencies can be specified by Integrity Constraints (IC). It will be shown what improvements MECORI offers over its predecessors and how it overcomes many of their limitations. MECORI is a method for verifying knowledge bases (KBs) expressed in a knowledge representation formalism called CCR-2, which can be used to represent non-monotonic and uncertain reasoning. The rules expressed in the CCR-2 formalism can include variables that can be instantiated as frames, propositions or relationships, and it can, therefore, be used to represent some classes of formulas expressed in second-order logic. Furthermore, MECORI can handle inequations defined in the rational domain within the antecedents of rules that express constraints on the values of attributes or certainty factors. AgradecimientosSon muchas las personas a las que, de una manera o de otra, estoy agradecido por su apoyo moral o sus aportaciones a este trabajo. Seguramente me dejaré algún nombre en el tintero fruto de mi mala memoria, mas no por ello deberán sentirse ajenos a mi gratitud.Debo empezar mencionando a mi directora de tesis, Angélica de Antonio, sin cuya intervención este trabajo no habría podido ser realizado. Ella es la persona que más ha creído en la relevancia de este trabajo, y más confianza ha depositado en la capacidad de un servidor para llevarlo a cabo. Su calidad humana y profesional han sido siempre una fuente de sugerencias y consejos. Por otro lado, su capacidad analítica y su claridad de ideas han sido esenciales para que este trabajo tomara cuerpo y ofreciera los frutos deseados. Ante todo, me gustaría destacar que trabajar con ella ha sido divertido e intelectualmente estimulante. Para mí, la investigación tiene un carácter eminentemente lúdico y debe ser practicada con ilusión y honradez, porque si no se convierte en una pieza más de un engranaje pervertido por las codicias y las vanidades. Trabajar con Angélica me ha ayudado a reforzar estas convicciones. En el futuro deseo poder seguir disfrutando de su amistad y del privilegio de trabajar con ella.No me puedo olvidar de las chicas que han trabajado...

The integration of interaction and simulation in elearning systems represents a milestone in educational research and supports the student's learning process in innumerable ways. Nevertheless, current standards do not provide appropriate mechanisms to treat simulations as learning objects, which makes their integration into e-learning systems a hard task. This work proposes an architecture as extension to SCORM which includes a Tutoring Module for Simulations (TMS). The main objective consists in providing mechanisms to track and "observe" the student's actions while interacting with a simulation, thus enabling the TMS to take decisions or intervene when necessary, and/or to modify the simulation course.