SOCO works on data and knowledge visualization as a problem that involves artificial pattern recognition as a complement to the natural pattern recognition involved in human visual system. As such, this is a key element of exploratory data mining. Our work focuses on latent variable models, probabilisitic self-organizing systems and Gaussian Processes.
The first five describe methodologies with a similar goal: the resolution of complex problems that cannot be efficiently solved by means of traditional computational methods (hard computing). Feature Selection and Extraction deals with problems of data dimensionality reduction that are present in all the previous lines. Finally, Pattern Recognition and Computer Vision copes with a huge application field where the performance of AI systems is usually worse than the human one, and where the soft computing techniques have great potential. Related to it, Data and Knowledge Visualization concerns ways in which Soft Computing complements human vision in problems of exploratory Data Mining.
Please follow the links for further description.
SOCO's current main line of research is in the areas of biomedicine and bioinformatics. Our work involves the development of robust Computational Intelligence techniques and their application to data-based medical diagnosis and prognosis, mainly in the area of neuro-oncology, and to protein sequence analysis for pharmaco-proteomics. In the former problem, SOCO collaborates with the Neural Computation Research Group [go] at Liverpool John Moores University [go] in U.K., and with the Grup d'Aplicacions Biomèdiques de la Ressonància Magnètica Nuclear (GABRMN) [go] at Universitat Autònoma de Barcelona (UAB) [go]. In the latter problem, SOCO is currently leading a MINECO R+D project (TIN2012-31377), titled "KAPPA AIM: Knowledge Acquisition in Pharmacoproteomics using Advanced Artificial Intelligence Methods", in collaboration with the Systems Pharmacology and Bioinformatics group [go] at UAB. SOCO also collaborates in the SHOCKOMICS European project [go] providing data science in a multiscale approach to the identification of molecular biomakers in acute heart failure induced by shock. We also investigate major depressive disorders. The prevalence of depression, its social and personal costs and its recurrent characteristics, put heavy constraints on the ability of public healthcare systems to provide sufficient support for patients with depression. Current research at SOCO includes the design and development of a remote intelligent monitoring and prediction system that performs an automatic assessment on the progress of the patient in a short-term basis, carrying out prediction of possible reoccurrence or relapses.
SOCO also collaborated with the Servei de Medicina Interna de l'Hospital General de la Vall d'Hebron [go] in a study of the relevance of several clinical and immunological variables for the prediction of cancer in patients with idiopathic inflammatory myopathies.
Until 2008, SOCO focused much of its applied research to problems of failure detection in Waste Water Treatment Plants (WWTPs) and exploration of the ecological status of European streams, in collaboration with several partners, including the Laboratori d'Enginyeria Química i Ambiental (LEQUIA) at Universitat de Girona and the and Centre d'Estudis Avançats de Blanes-CSIC at Girona. A Long-term collaboration with the Water Microbiology Group - MARS, Dept. of Microbiology of the University of Barcelona (UB), was started in 2001 within the European project TOFPSW ("Tracking the origin of faecal pollution in surface water", EVK1-CT-2000-00080). It was continued within the MICINN projects "Determinación del origen de la contaminación fecal en el agua" (CGL2004-04702-C02), from 2004 to 2007, and "Procedimientos para la discriminación de origen de la contaminación fecal animal en el agua" (CGL2007-65980-C02-01/HID), from 2008 to 2011. Currently we undertake external assessment to the European project Aquavalens (go) "Protecting the health of Europeans by improving methods for the detection of pathogens in drinking water and water used in food preparation", from 2013 to 2018. In seismic data analysis, achieving integrated risk modeling is a difficult undertaking because interconnections between the assumed risk-related variables are still not completely understood. Current research of SOCO in this area involves the development of a holistic seismic risk fuzzy inference system.