© 2007

Freund/OncoLab

The group

The Department of Knowledge Technologies at the Jožef Stefan Institute (http://kt.ijs.si) is involved in basic and applied research in the fields of data mining, machine learning, decision support, language technologies, knowledge management, and other information technologies that support the acquisition, management, modeling, and use of knowledge and data. One of the major research topics is the development of machine learning and data mining techniques, and their applications to problems in the areas of environmental and life sciences. In addition, the group is very active in relational data mining, and the emerging area of inductive databases and queries. The group has previously participated and is currently participating in several other EU funded projects and networks of excellence concerned with the development of novel data mining techniques, as well as their application to practical problems in the area of bioinformatics.

Our role in EET-Pipeline

Within the EET-Pipeline, the JSI group will contribute their extensive expertise in mainstream data mining methods, as well as cutting-edge methods such as multi-relational data mining and predictive clustering. The data available within the project includes patient's clinical information, DNA, mRNA and miRNA arrays, protein arrays and SELDI-MS profiles. This presents a unique opportunity to find connections between the different facets describing the patient through data analysis. Multi-relational data mining techniques allow for the analysis of such structured data, and also have the capacity to include background information such as gene ontologies, gene interactions or pathway information.

Staff Member

People in Photograph:
Left to right:
Benard Zenko, Dragi Kocev, Valentin Gjorgjioski, Marko Debeljak, Aneta Ivanovska, Aleksandar Pečkov, Saso Dzeroski, Panče Panov, Ivica Slavkov and Katerina Taškova

Top 5 publications

1. S. Dzeroski, and N. Lavrac, editors. Relational Data Mining. Springer, Berlin (2001)

2. S. Dzeroski, and B. Zenko. Is combining classifiers better than selecting the best one? Machine Learning, 54: 255-273 (2004)

3. S. Dzeroski, D. Hristovski, and B. Peterlin. Using data mining and OLAP to discover patterns in a database of patients with Ychromosome deletions. Journal of the American Medical Informatics Association, pages 215-219 (2000)

4. J. Struyf, S. Dzeroski, H. Blockeel, and A. Clare. Hierarchical Multi-classification with Predictive Clustering Trees in Functional Genomics. In Proc. EPIA/CMB, Springer (2005) In press.

5. S. Dzeroski, L. Todorovski, and P. Ljubic. Inductive Queries on Polynomial Equations. In J.-F. Boulicaut, L. De Raedt, and H. Mannila, editors, Constraint-Based Data Mining and Inductive Databases. Springer (2005) In press.