A main research line at SOCO concerns Fuzzy Inductive Reasoning (FIR): a model-based qualitative methodology, derived from Systems General Theory, which is quite attractive for dynamic systems modelling and prediction. Among its advantages, it is worth mentioning that inductive reasoning allows dealing with time in qualitative models as a continuous variable. The technique can be applied to any system amenable to observation and experimentation. Furthermore, the methodology∆s simulation engine has an inherent evaluation mechanism that prevents it from reaching to conclusions that cannot be justified by evidence. This methodology has been designed in collaboration with the University of Arizona [go]. FIR has been applied to the development of a Fault Monitoring System.
Support Vector Machines (SVM) is a rather novel automatic learning paradigm, as well as a hot research issue due to its excellent theoretical foundations and practical results, especially in classification problems. SVMs can be adapted to specific problems through the design of their kernels. SOCO works on kernel design with a focus on methods to deal with incomplete or missing data, as well as on hybridization of Supervised Neural Networks (SNNs) and SVMs, with the design of margin maximization algorithms for SNNs.
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.