Computational Intelligence Group (CIG)

The Computational Intelligence Group (CIG) was created in 2008 and is lead by professors Pedro Larrañaga and Concha Bielza. Research of CIG members, both theoretical and practical, is devoted to modelization (from a statistical and machine learning perspectives) and heuristic optimization, with different application areas. The main research area is machine learning, whose current main issues include: data streams, multi-dimensional supervised classification, multi-label classification, clustering in high-dimensional spaces, feature subset selection using Bayesian networks and regularization. In heuristic optimization we investigate improvements of state-of-the-art methods and their extension to complex problems (multi-objective functions, non-continuous objective functions), with special emphasis on estimation of distribution algorithms. Neuroscience is an important field of application. Some problems that we face include: (a) neuroanatomy issues, like modeling and simulation of dendritic trees and classification of neuron types based on morphological features; (b) neurodegenerative diseases, like predicting health-related quality of life in Parkinson's disease and searching for genetic biomarkers in Alzheimer's disease. The second main field of application is Industry 4.0 where we develop machine learning solutions for cyber-physical systems. The third application field is sports, where we develop intelligent systems for coach assistance, injury prediction, football player performance prediction and their potential transfer to other clubs. CIG has been involved in more than 100 research projects, mostly in public competitive calls but also for private companies. Current public projects include Human Brain Project, Cajal Blue Brain and several national projects from the Spanish Ministry of Science, Innovation and Universities. CIG has collaborated with companies as Telefónica I+D, Abbott, Arthur Andersen, Progenika Biopharma, Bank of Santander, Repsol, Etxe-Tar...