The world of artificial cognitive systems and machine learning is advancing rapidly and is becoming one of the major challenges of international research. We are developing new techniques in this field that will transform many aspects of our work and private life. The project Simbad ("Beyond features: Similarity-based pattern analysis and recognition"), supported by EU funding of 1.65 million, is considering some ways in which this research can be exploited.
Simbad aims to develop fully the new technology that is emerging in the fields of pattern recognition and machine learning, and is investigating the use of "similar information" instead of the standard "based on common characteristics" , said Professor Marcello Pelillo University Ca 'Foscari Venezia (Italy).
The company is developing increasingly complex machines (like robots) to fulfill many of our daily needs, he said. The artificial cognitive systems (ACS) are now becoming a main priority of the international research and in accordance with this priority, the European Commission made this area one of the seven key research areas that Europe must develop in order to become a leader in the field of information and communication technologies (ICTs) to the next generation.
A fruitful research in this field will lead to the development of many tools that will have a strong social and economic impact in the EU, he added. The control of vehicles, communications networks, medical diagnostics and human-machine interaction are just some of the areas that will benefit. There are also many economic benefits that will boost European competitiveness.
"We are devoting much effort to the completion of two biomedical imaging applications on a large scale. We contribute to the effective delivery of advanced techniques to assist in the diagnosis of renal cell carcinoma and diagnosis of most of psychosis such as schizophrenia and bipolar disorder, "explained Professor Pelillo." Such problems are not liable to be addressed through the use of traditional machine learning techniques, because of the difficulty of deriving appropriate descriptions on the basis of common characteristics.
A successful outcome of these applications of research shows that the approach Simbad is highly qualified to be used in biomedicine, and this would be a good starting point for further research to be carried out in this area, he said. Use techniques of pattern recognition in medicine and health services would lead to major improvements in the field of public health across the EU and open up many avenues of health technology industry.
"A positive result of our experiments provide evidence regarding the applicability of our approach in biomedicine, thus promoting the search along the path defined by Simbad, both methodological and practical level," said Professor Pelillo. "This would provide potential new opportunities in health and disease, and lead to huge improvements in the quality and efficiency of our health systems," he noted. "The field of recognition pattern is responsible for the automatic discovery of the regularities of the data through the use of computer algorithms, and through the use of these regularities take actions such as the classification of data into different categories, with a view to provide artificial systems able to improve their performance the light of new external stimuli. "
A Simbad involved six partners from five European countries (Italy, Netherlands, Portugal, Switzerland and United Kingdom): an international consortium that reflects a range of international research.
" The skills needed to achieve our objectives can not be found locally or nationally. The European dimension of the project provides a critical mass of researchers with experience and complementary skills, thus stimulating the chance of success, "said Professor Pelillo." Furthermore, the potential impact of this research goes beyond the national level and the EU will benefit from the fact that present themselves as an active participant on world stage of artificial cognitive systems, which is largely dominated by the USA.
http://www.giornaletecnologico.it/hitech/200812/11/49353b0404132/ 
