MACHINE LEARNING ALGORITHMS AND THEIR APPLICATION

The project is supported by Croatian Ministry of Science Education and Sports
contract number: 098-0982560-2563
starting date: January 1st 2007
part of the program: Computational Knowledge Discovery in Scientific Applications

International Workshop e-Cardiology and European Society of Cardiology working group meeting organizer: dr. G.Krstačić

Handbook: Data Mining for Knowledge Discovery (in Croatian) by D.Gamberger

Book: Foundations of Rule Learnig by J.Fuernkranz, D.Gamberger, and N.Lavrac

Comparison of two methods for protein function annotation

Example of medical plan for the case of pulmanory oedema

Decision support based on the ontological knowledge representation

Procedural knowledge integrated into OWL ontology

Project summary

Effective knowledge handling is the limiting factor of computational intelligence. And although the project purpose is practical implementation of knowledge technology tasks, our main research topic is actually machine learning. Our previous work gives us good reasons to believe that machine learning algorithms are not only powerful tools for intelligent data analysis and knowledge discovery tasks, but also that they can help us to structure existing expert knowledge and that they can be the driving force for decision support procedures.

The topic is both theoretical and practical research related to machine learning algorithms. Special attention is devoted to feature construction in general, and specifically for inductive learning from different complex data forms including temporal signals, two-dimensional images, text, and relational databases. Theoretically and practically we try to prove usefulness of the saturation-based concept of inductive learning. We will work on noise handling and overfitting prevention techniques.

The goal is development of algorithms that can be effectively used in intelligent data analysis and knowledge handling tasks. Applications are in very different fields including but not restricted to medicine, chemistry, biology, and social sciences. In each of these domains, we strongly cooperate with respective domain experts trying to obtain novel results that cannot be obtained by other methods. The aim of this interdisciplinary work is to achieve results that are significant for the development of the target domain as well as for the computer science as an illustration of the quality and significance of applied algorithms.

Among others, the importance of the proposed project is in the fact that it presents necessary support for EU projects in which we are involved. The first has been HEARTFAID in the period from February 2006 to April 2009. In cooperation with ten other European partners within three years we realized a platform of services able to improve medical-clinical management related to heart failure disease. Within this project, we used our machine learning expertise for knowledge discovery tasks and for the development of effective knowledge representation and decision support services. Although the project used and developed modern computer science techniques, it has been strongly an interdisciplinary work with the result potentially very relevant also for medicine.

Currently we work on EU FP7 project e-LICO: An e-Laboratory for Interdisciplinary Collaborative Research in Data Mining and Data-Intensive Sciences. In the frames of the project we cooperate with a few leading European centers in the field of machine learning, workflow planning, and application of recommender systems. Besides that we started the work on the FP7 project Forecasting Financial Crisis (FOC).

Members

• Dragan Gamberger, PhD. - www
- head
• prof. Nikola Bogunović, Ph.D. - www
• prof. Bojana Dalbelo Bašić, PhD. - www
• Goran Krstačić, MD, PhD, FESC - www
• Nives Škunca, B.Sc. - www PhD student
• Marin Prcela, B.Sc. - PhD student (till September 2009)

Members on HEARTFAID project

• Matko Bošnjak, B.Sc. - (till July 2009)

Technical support

• Rajko Horvat - www

Activities

• [new] In November 2013 started work on EU FP7 project MULTIPLEX: Foundational Research on Multilevel Complex Networks and Systems.
• [new] Workshop "Rule learning algorithms and their applications", Rudjer Boskovic Institute, February 15, 2013. Speakers: Johannes Fuernkranz, Nada Lavrac, and Dragan Gamberger.
• Published book Foundations of Rule Learning , Johannes Fuernkranz, Dragan Gamberger, Nada Lavrac.
• Eighth Workshop on Knowledge Tehnologies organized in Masun by Ilirska Bistrica , October 27-29, 2012.
• Published paper: Skunca, N., Altenhoff, A., Dessimoz, C. (2012) Quality of Computationally Inferred Gene Ontology Annotations. PLoS Comput Biol 8(5)
• Organized International workshop e-Cardiology and nucleus meeting of the working group of European Society of Cardiology , Osijek, March 15-17, 2012.
• Seventh Workshop on Knowledge Tehnologies organized in Poreč , October 19-21, 2011.
• In September we started the work on FP7 FET project Forecasting Financial Crisis (FOC).
• The Gene Ontology (GO) project is the largest resource for cataloging gene function. Nonetheless, its use is not yet ubiquitous and is still fraught with pitfalls. In our review, we provide a short primer to the GO for bioinformaticians. We summarize important aspects of the structure of the ontology, describe sources and types of functional annotations, survey measures of GO annotation similarity, review typical uses of GO, and discuss other important considerations pertaining to the use of GO in bioinformatics applications.
• Handbook "Data Mining for Knowledge Discovery (in Croatian)" presents machine learning methods and systems and their usage in data mining aimed at knowledge discovery tasks. Although the majority of the examples and illustrations are from the medical domain, all approaches may be used in other scientific applications: from natural and technical sciences to business and sociology.
• Proposed EU FP7-ICT-2011-7 project: "Citizen oriented e-health environment supporting an innovative health management model for enhancing risk assessment and handover process - CHEERS". In the consortium is 11 EU partners. Institut R. Bošković is leading a Workpackage titled "Knowledge management and decision support services".
• FP7 STREP project "e-LICO: e-Laboratory for Interdisciplinary Collaborative Research in Data Mining and Data-Intensive Sciences" started on June 1st, 2010. Besides 7 partners inlcuded into the original e-LICO project, the enlarged consortium includes Institut J.Stefan, Ljubljana Slovenia, Poznan University of Technology, Poland, and Rudjer Boskovic Institute.
• RandomGuy team (M.Bošnjak and D.Gamberger) first runner-up at RSCTC'2010 Discovery Challenge: basic track. Challenge has been organized by The Seventh International Conference on Rough Sets and Current Trends in Computing (RSCTC 2010), it participated more than 80 teams, and the task has been class prediction in gene expression domains.
• Marin Prcela PhD Thesis Knowledge representation based on integration of ontologies and Bayesian networks in Croatian
• Informatic project GORBI: A web application for protein function prediction
• Public web service: Saturation filter for detection and elimination of noise in datasets
• HEARTFAID results: Ontology of concepts for the heart failure domain , -- Decision support for hospital care , -- Alarm system for home care
• Workshop "Computational knowledge discovery in scientific applications" Porec 17.-18. October 2008.
• joint slovenian-croatian project "Intelligent subgroup discovery"
• joint slovenian-croatian project "Inductive rule learning"
• internal pages

Published papers in year 2013

• Gamberger, D. Smuc, T. (2013) Good Governance Problems and Recent Financial Crises in Some EU Countries. Economics: The Open-Access, Open-Assessment E- Journal, 7:2013-41.
• Gamberger, D., Krstacic, G., Jovic, A. (2013) A novel way of integrating rule based knowledge into a web ontology language framework. In Proc. of Thirteenth EFMI Special Topic Conference "Data and Knowledge for Medical Decision Support", IOS Press, pp. 51-55.
• Rios-Morales, R., Gamberger, D., Schweizer, M. Brennan, L. (2013) Institutional Environment Features and Swiss Foreign Direct Investment. Global Business and Economics Review, 15(2-3):196-209.

Published papers in year 2012

• Fuernkranz, J., Gamberger, D., Lavrac, N. (2012) Foundations of rule learning. Springer Verlag 2012.
• Gamberger, D., Lucanin, D., Smuc, T. (2012) Descriptive modeling of systemic banking crisies, In Proc. of Fifteenth Internation Conference on Discovery Science (DS-2012), pp. 67-80.
• Skunca, N., Altenhoff, A., Dessimoz, C. (2012) Quality of Computationally Inferred Gene Ontology Annotations. PLoS Comput Biol 8(5): e1002533. doi:10.1371/journal.pcbi.1002533

Published papers in year 2011

• du Plessis, L., Skuca, N., Dessimoz, C. (2011) The what, where, how and way of gene ontology - a primer for bioinformaticians, Briefings in Bioinformatics.
• Jovic, A., Gamberger, D., Krstacic, G. (2011) Heart Failure ontology. Bio-Algorithms and Med-Systems, 7:101-110.
• Rios-Morales, R., Gamberger, D., Jenkins, I., Smuc, T. (2011) Modelling investment in the tourism industry using the World Bank's good governance indicators. Journal of Modelling in Management, 6(3):279-296.

Published papers in year 2010

• Prcela, M., Gamberger, D., Smuc, T., Bogunovic, N. (2010) Information gain of structured medical diagnostic tests: Integration of Bayesian networks and ontologies, In Proc. of Third International Conference on Health Informatics HEALTHINF 2010, pp. 235-240.
• Lavrac, N., Fuernkranz, J., Gamberger, D. (2010) Explicit Feature Construction and Manipulation for Covering Rule Learning. In Koronacki, J., Ras, Z., Wierzchon, S.T., Kacprzyk, J. editors: Advances in Machine Learning I - Dedicated to the Memory of Professor Ryszard S. Michalski. Springer, pp. 121-146.
• Kononowicz etal. (2009) HEARTFAID's ECRF: Lessons learnt from using a two-level data acquisition and storage system for knowledge discovery tasks within an electronic platform for managing heart failure patients. Bio-algorithms and med-systems, 5:59-69.

Published papers in year 2009

• Stajduhar, I., Dalbelo Basic, B., Bogunovic, N. (2009) Impact of censoring on learning Bayesian networks in survival modelling, Artificial Intelligence in Medicine. 47(3):199-217.
• Skunca N., Supek, F., Panov P., Dzeroski S., Smuc T. (2009) Functional annotation of orthologous groups by using hierarchical multi label classification, 17th Annual International Conference on Intelligent Systems for Molecular Biology (ISMB) & 8th European Conference on Computational Biology, Stockholm, Švedska, poster presentation .
• Jagnjic, Z., Bogunovic, N., Pizeta, I., Jovic, F., (2009) Time series classification based on qualitative space framentation , Advanced Ingenieering Informatics, 23:116-129.
• Kralj, P., Lavrac, N., Gamberger, D. and Krstacic, A. (2009) CSM-SD: Methodology for contrast set mining through subgroup discovery, Journal of Biomedical Informatics, 42:113-122.
• Rios-Morales, R., Gamberger, D., Smuc, T., Azuje, F. (2009) Innovative methods in assessing political risk for business internationalization, Research in International Business and Finance, 23:144-156.

Published papers in year 2008

• Gamberger, D., Lavrac, N., Fuernkranz, J. (2008) Handling Unknown and Imprecise Attribute Values in Propositional Rule Learning: A Feature-Based Approach In Proc. of 10th Pacific Rim International Conference on Artificiel Intelligence, PRICAI 2008, pp.636-645. (pdf)
• Skunca N., Supek F., Repar J., Smuc T. (2008) Evaluation of intergene distances across bacterial species. ECCB08 - European Conference on Computational Biology, extended abstract.
• Gamberger, D., Prcela, M., Bosnjak M. (2008) Attribute ranking for intelligent data analysis in medical applications. In Proc. of ITI 2008 30th International Conference on Information Technology Interfaces, pp.323-328.
• Prcela, M., Gamberger, D., Jovic, A. (2008) Semantic web ontology utilization for heart failure expert system design. In Proc. of 21st International Congress of the European Federation for Medical Informatics, MIE 2008, pp.851-856. (doc)
• Malenica, M., Smuc, T., Snajder, J., Dalbelo Basic, B. (2008) Language Morphology Offset: Text Classification on a Croatian-English Parallel Corpus , Information Processing and Management, 44:325-339.
• Gamberger, D., Prcela, M., Jovic, A., Smuc, T., Parati, G., Valentini, M., Kawecka-Jaszcz, K., Styczkiewicz, K., Kononowicz, A., Candelieri, A., Conforti, D., Guido, R. (2008) Medical knowledge representation within Heartfaid platform , Proceedings of BIOSTEC 2008, 307-314.
• Lambach, D., Gamberger, D. (2008) Temporal Analysis of Political Instability Through Descriptive Subgroup Discovery , Conflict Management and Peace Science, 25:19-32.

Published papers in year 2007

• Jovic, A., Bogunovic, N. (2007) Feature Extraction for ECG Time-Series Mining Based on Chaos Theory , In Proc. of ITI 2007 29th International Conference on Information Technology Interfaces, pp. 63-68.
• Silic, A., Chauchat, J-H., Dalbelo Basic, B., Morin, A. (2007) N-Grams and Morphological Normalization in Text Classification: A Comparison on a Croatian-English Parallel Corpus , Lecture Notes in Artificial Intelligence, Progress in Artificial Intelligence: 13th International Conference EPIA 2007; Proceedings ed. Neves, J., Santos, M.F., Machado, J.M.; Berlin, Heidelberg, Springer-Verlag, 2007. 671-682.
• Prcela, M., Gamberger, D., Bogunovic, N. (2007) Developing factual knowledge from medical data by composing ontology structures , In Proc. of 30th International Covention MIPRO 2007, part III, pp.145-150. (pdf)
• Kralj, P., Lavrac, N., Gamberger, D. (2007) Contrast set mining through subgroup discovery applied to brain ischaemia data , In Proc. of 11th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining (PAKDD 2007), pp.579-586.
• Jovic, A., Prcela, M., Gamberger, D. (2007) Ontologies in medical knowledge representation, In Proc. of ITI 2007 29th International Conference on Information Technology Interfaces, pp.535-540. (pdf)
• Lavrac, N., Kralj, P., Gamberger, D., Krstacic, A. (2007) Supporting factors to improve the explanatory potential of contrast set mining: Analyzing brain ischaemia data, In Proc. of 11th Mediterranean Conference on Medical and Biological Engineering (MEDICON 2007), pp.157-161.
• Jovic, A., Prcela, M., Krstacic, G. (2007) Medical Plans as a Middle Step in Building Heart Failure Expert System , In Proc. of 11th Mediterranean Conference on Medical and Biological Engineering (MEDICON 2007), pp.549-553. (pdf)
• Gamberger, D., Lavrac, N. (2007) Supporting factors in descriptive analysis of brain ischaemia, In Proc. of 11th Conference on Artificial Intelligence in Medicine (AIME 2007), pp.155-159.
• Kralj, P., Lavrac, N., Gamberger, D., Krstacic, A. (2007) Contrast Set Mining for Distinguishing between Similar Diseases , In Proc. of 11th Conference on Artificial Intelligence in Medicine (AIME 2007), pp.109-118.
• Gamberger, D., Lavrac, N., Krstacic, A., Krstacic, G. (2007) Clinical data analysis based on iterative subgroup discovery: Experiments in brain ischaemia data analysis, Applied Intelligence, 27:205-217.