Projects / Programmes
Inteligentna analiza podatkov, računalniška logika in jezikoslovje (Slovene)
January 1, 1999
- December 31, 2003
Code |
Science |
Field |
Subfield |
2.07.00 |
Engineering sciences and technologies |
Computer science and informatics |
|
2.06.00 |
Engineering sciences and technologies |
Systems and cybernetics |
|
Code |
Science |
Field |
P176 |
Natural sciences and mathematics |
Artificial intelligence |
B110 |
Biomedical sciences |
Bioinformatics, medical informatics, biomathematics biometrics |
H350 |
Humanities |
Linguistics |
B003 |
Biomedical sciences |
Ecology |
P175 |
Natural sciences and mathematics |
Informatics, systems theory |
P110 |
Natural sciences and mathematics |
Mathematical logic, set theory, combinatories |
Researchers (7)
no. |
Code |
Name and surname |
Research area |
Role |
Period |
No. of publicationsNo. of publications |
1. |
05806 |
PhD Bojan Cestnik |
Computer science and informatics |
Researcher |
2001 - 2003 |
196 |
2. |
11130 |
PhD Sašo Džeroski |
Computer science and informatics |
Researcher |
2001 - 2003 |
1,204 |
3. |
05023 |
PhD Tomaž Erjavec |
Linguistics |
Researcher |
2001 - 2003 |
636 |
4. |
20243 |
PhD Branko Kavšek |
Computer intensive methods and applications |
Researcher |
2001 - 2003 |
134 |
5. |
08949 |
PhD Nada Lavrač |
Computer science and informatics |
Head |
2001 - 2003 |
867 |
6. |
16302 |
PhD Ljupčo Todorovski |
Computer science and informatics |
Researcher |
2001 - 2003 |
443 |
7. |
22279 |
PhD Bernard Ženko |
Computer science and informatics |
Researcher |
2002 - 2003 |
172 |
Organisations (1)
no. |
Code |
Research organisation |
City |
Registration number |
No. of publicationsNo. of publications |
1. |
0106 |
Jožef Stefan Institute |
Ljubljana |
5051606000 |
90,664 |
Abstract
The gap between the amount of data gathered and stored in electronic form and the human capability of data analysis and understanding is increasing in all fields of human activity. The goal of the research program is the development and use of methods for intelligent data analysis including Knowledge Discovery in Databases and Data Mining. These methods are being developed in close connection with the developments in the areas of Computational Logic, in particular Inductive Logic Programming, Constraint Logic Programming and Computational Linguistics. The main link between these areas is the need for extensive use of human expert knowledge in problem solving and data analysis, as well as the understandability of used and extracted knowledge, enabled by the use of logical formalisms for knowledge representation. The main developments are expected in the following areas. First, in the area of intelligent data analysis the program’s goal is the development of new and adaptation of existing machine learning and inductive logic programming methods with an emphasis on solving practical problems in the following areas: medical data analysis and synthesis of diagnostic and prognostic rules, analysis of environmental data, analysis of data on media as well as the analysis of commercial and management data. Second, for efficient problem solving and modeling of problems with Constraint Logic Programming it is necessary to incorporate into the model domain knowledge and previous experience in modeling of similar types of problems. This can be achieved in collaboration with experts, whereas the research goal of this program is the automatic synthesis of such knowledge from examples, using machine learning. Improved CLP methods will be used for solving different complex combinatorial problems, including job shop scheduling and schedule generation. Third, in the areas of Computational Linguistics and Language Technologies the main goals will be the gathering and analysis of text data, in particular the acquisition and construction of Slovenian and multi-lingual corpora and lexica, as well as development of models of the Slovenian language, mostly by use of machine learning and inductive logic programming.
Most important scientific results
Final report
Most important socioeconomically and culturally relevant results
Final report