Evolutionary Multiobjective Clustering
Clustering techniques group data according to their similarities, it means, the elements belonging to a group (cluster) are similar to each other but different from those in other groups. Thus, the approach provides to the experts a possible classification or categorization of elements based on criteria such as for example a distance metric. In some problems these criteria are difficult to define due to the data typology, and it is necessary to combine several criteria to group the data. Multiobjective clustering uses a set of criteria (objectives) to promote the definition of clusters, returning a set of possible solutions with different trade-offs between all the analyzed criteria. The research focuses on evolutionary multiobjective clustering algorithms.
Case-based reasoning (CBR) systems solve new problems through an analogical procedure based on experiences represented by a set of cases stored in a case memory. As the case memory feeds this process, its size and organization plays an important role in the CBR performance in terms of computational time, accuracy and maintenance. The research focuses on analyzing how to improve the case memory organization to improve the case retrieval (time vs accuracy) and also the knowledge maintenance. Nowadays this issue is tackled from the point of view of evolutionary multiobjective clustering algorithm
Intelligent Tutoring Systems based on competences
Nowadays the educational methodologies are being reconsidered to allow the successful achievement of the skills of the future computer engineer. The issue is based on adapting these methodologies from the point of view of the competences provided by the subjects. The research focuses on the design and development of an intelligent tutoring framework to guarantee the acquisition of the competences specified in a degree.