COMPUTATIONAL KNOWLEDGE DISCOVERY IN SCIENTIFIC APPLICATIONS

 

Program summary


Enormous quantities of information are available today. Effective and intelligent handling of information and knowledge is needed from manufacturing to banking, from health care to transportation. Knowledge based society of the future is impossible without computers able to practically realize complex tasks like knowledge representation, knowledge discovery and decision support. Although today practical implementation of these tasks may seem as a science fiction, from our previous experience in data analyses, data modeling, and artificial intelligence applications we have learnt that they, regardless how intellectually complex they may seem, consist of some computational parts that may be automated and actually better executed by machines than by humans.

The aim of the program is development, evaluation, implementation, and integration of complex computational methods representing fundamentals of the knowledge technologies. Having in mind that general goal, we will mainly concentrate on practical scientific applications. We suppose that in interdisciplinary collaboration of computer scientists and scientists working on very specific scientific problems, we have the best chance to recognize the problems, to learn how to solve them, and finally, if possible, to generalize the solutions. The work will be strongly multidisciplinary on very concrete scientific applications. The results should be relevant for application domains like medicine, bioinformatics, chemistry, and physics, as new and significant scientific results in the form of relations, models, or decision systems. At the same time, the results should be relevant for computer sciences, as novel theoretical and practical methodological achievements in the field of artificial intelligence.

The work consists of developing the most appropriate methodologies for the target problems. The quality of the resulting methodology is evaluated by the success in achieving the requested, domain specific results. The importance of the methodological results depends on the relevance of practical problems that have to be solved, and the ability to generalize the methodology to other similar tasks. Ultimate goal is detection of universal principles representing novel methodological breakthroughs. The significance of the research is in the fact that knowledge discovery technologies present technical fundamentals for supporting creativity of the information society and knowledge-based economy.

International cooperation:
EU FP7 STREP project e-LICO
EU FP6 STREP project HEARTFAID
COST Action IC0604: Telepathology Network in Europe: EURO-TELEPATH
Books:
Recent Advances in Multimedia Signal Processing and Communications, Springer 2009
Recent Advances in Face Recognition, IN-TECH 2008
Services:
Web portal Thiotemplate Modular Systems Studies
Quantum Random Bit Generator Service

Papers:
Maric, I., Ivek, I. Self-Organizing Polynomial Networks for Time-Constrained Applications, IEEE Transactions on Industrial Electronics, 2011; 58(5):2019-2029
Maric, I., Ivek, I. Compensation for Joule-Thomson effect in flow rate measurements by GMDH polynomial, Flow Measurement and Instrumentation, 2010; 21:134-142
Delac, K., Grgic, M., Grgic, S. Face Recognition in JPEG and JPEG2000 Compressed Domain. Image and Vision Computing, 2009; 27(8):1108-1120
Gamberger, D., Lavrac, N., Krstacic, A., Krstacic, G. Clinical data analysis based on iterative subgroup discovery: Experiments in brain ischaemia data analysis. Applied Intelligence, 2007;27:205-217
Starcevic, A., Zucko, J., Simunkovic, J., Long, P.F., Cullum, J., Hranueli, D. ClustScan: An integrated program package for the semi-automatic annotation of modular biosynthetic gene clusters and in silico prediction of novel chemical structures. Nucleic Acids Res., 2008;36:6882-6892
Stipcevic, M., Medved Rogina, B. Quantum random number generator based on photonic emission in semiconductors.Review of Scientific Instruments 2007;78(4):045104
Maric, I. A procedure for the calculation of the natural gas molar heat capacity, the isentropic exponent, and the Joule-Thomson coefficient Flow Measurement and Instrumentation 2007;18(1):18-26
Sonicki, Z., Cvitkovic, A., Edwards, K.L., Miletic-Medved, M., Cvoriscec, D.; Babus, V., Jelakovic, B. Visual Assessment of Endemic Nephropathy Markers Relationship. In Proc. of Medical Informatics in a United and Healthy Europe 2009 Amsterdam : IOS Press, pp.836-840.

->hrvatski

 


The program is supported by Croatian Ministry of Science Education and Sports
contract number: 0982560
starting date: July 2007


Participating projects

Intelligent image features extraction in knowledge discovery systems - University of Zagreb, Faculty of Electrical Engineering and Computing

Real life data measurement and characterization - Rudjer Boskovic Institute

Machine learning algorithms and their applications - Rudjer Boskovic Institute

Computational Intelligence Methods in Measurement Systems - Rudjer Boskovic Institute

Predictive models in health care - University of Zagreb, Medical School, Andrija Stampar School of Public Health

Generation of Potential Drugs In-silico - Faculty of Food Technology and Biotechnology, University of Zagrebu

Machine learning of predictive models in computational biology - Rudjer Boskovic Institute


Documents

Scientific hypothesis
Collaboration plan

[NEW] Workshop "Computational knowledge discovery in scientific applications", Zagreb, RBI 12/11/2009

First program meeting - IRB 03/09/2007 presentation

Workshop "Computational knowledge discovery in scientific applications", Porec 17-19/10/2008

[NEW] Mammographic Image Analysis Homepage