WAI: Volume Visualization and Artificial Intelligence research group

Some links
About us

WAI research group was created in 2004. Afterwards, from 2005 to 2008 it was recognised a "Grup de recerca emergent" by the SGR of the Generalitat de Catalunya.Subsequently, the group was recognised as "Grup de Recerca Singular" (group code 2009 SGR 362). Currently, the group is within the CLiC Centre de Llenguatge i Computació 2014 (SGR 623).

Its main activities are devoted to:

- Teaching at the University of Barcelona: lecturing courses in the EHEA bachelor's degree in Computer Engineering (grau d'Enginyeria Informàtica) and interuniversitary master on Artificial Intelligence (UPC-UB-URV: Master interuniversitari en Intel.ligència Artificial ) offered at UB by the Departament de Matemàtica Aplicada i Analisi (MAiA) at the Facultat de Matemàtiques.

- Educational Innovation: our members belong to the Consolidated Educational Innovation Group INDOMAIN at UB (code GIDCUB-13/138). Within its activities, we can highlight the educational innovation project: Mòdul Pedagògic en un Sistema Tutor Intel.ligent per a predir l'evolució de l'alumnat. Finançament:Vicerectorat de Políca Docent, Universitat de Barcelona. Download code here.

- Research in the areas of Volume Visualization of medical data, 3D graphics, Virtual Worlds and serious games, and different areas of Artificial Intelligence such as Machine Learning, Multi-Agent Systems (including Normative Multi-Agent Systems) or Group Recommenders. We are also interested in educational issues.

As previous picture shows, our research faces problems related to the gathering, managing and understanding of large volumes of data:

  • Wireless sensor networks (together with other scenarios such as Internet or medical applications) represent alternatives for the gathering of large volumes of data. Sensors, and other involved elements, can be characterised as autonomous agents. Therefore, we study their organization, adaptation and decision making within the Multi-Agent Systems research area.
  • Once the data have been gathered, we can apply machine learning and recommenders in order to manage and extract knowledge from this large volume of information. More concretely, we are specialists in Probabilistic Graphical Models and Group Recommenders.
  • Finally, we emphasize the need for appropriate information visualization (in 3D). This will allow an advanced user interaction that will allow the user to understand and take advantage of the information contained within the data.