This area includes the distributed diagnosis and classification, large-scale semantic search, social networking analysis, and analysis of emotions and feelings.
Early research on machine learning in artificial systems date back to the 1950's. From the 80 start to develop practical applications of algorithms called "subsymbolic"(mainly Bayesian neural networks and systems) to problems of pattern recognitionand classification and the "symbolic" (induction of trees and rules) to knowledge acquisition for expert systems. In the 90 off with force what has been called 'data mining' application of learning algorithms and visualization for knowledge extractionin large databases. Our contributions in this field have also followed this path:
- Application of Bayesian techniques for the assessment of risk in bank credit(ExpertBao project, 1986-1988).
- Genetic algorithms and fuzzy logic to control power plants (ANOTHER project, 1989-1991) and in general for adaptive control of complex processes (projects courage andMITA).
- Solving real engineering problems, providing technical tools integrating symbolic andsubsymbolic (MIX project, 1994-1997).
- Data mining of urban transport (SEIC Project, 1995) and CCTV (AzVigia project, 2005-2007). Tools for data mining process (project M2D2).
- Application of Bayesian techniques for diagnosis in telecommunication networks (in cooperation with Telefonica from Spain and Czech Republic)
- Application of marchine learning techiques based on Big Data to Sentiment Analysis (Financial Twitter Tracker and EuroSentiment)