Projects / Programmes
Computer Systems, Methodologies, and Intelligent Services
January 1, 2015
- December 31, 2019
Code |
Science |
Field |
Subfield |
2.07.00 |
Engineering sciences and technologies |
Computer science and informatics |
|
Code |
Science |
Field |
T120 |
Technological sciences |
Systems engineering, computer technology |
Code |
Science |
Field |
1.02 |
Natural Sciences |
Computer and information sciences |
algorithms, pattern recognition, data decomposition, semantic integration, mathematical morphology, latent variable analysis, evolutionary computation, domain specific languages.
Researchers (41)
no. |
Code |
Name and surname |
Research area |
Role |
Period |
No. of publicationsNo. of publications |
1. |
51049 |
Klemen Berkovič |
|
Technical associate |
2018 - 2019 |
19 |
2. |
23982 |
PhD Borko Bošković |
Computer science and informatics |
Researcher |
2015 - 2019 |
230 |
3. |
23980 |
MSc Albin Bregant |
Computer science and informatics |
Technical associate |
2015 - 2018 |
38 |
4. |
16118 |
PhD Janez Brest |
Computer science and informatics |
Researcher |
2015 - 2019 |
466 |
5. |
20206 |
PhD Boris Cigale |
Systems and cybernetics |
Researcher |
2015 |
161 |
6. |
53590 |
PhD Jernej Cukjati |
Computer science and informatics |
Junior researcher |
2019 |
6 |
7. |
22707 |
PhD Matej Črepinšek |
Computer science and informatics |
Researcher |
2015 - 2019 |
260 |
8. |
21537 |
PhD Matjaž Divjak |
Computer science and informatics |
Researcher |
2016 - 2019 |
104 |
9. |
31054 |
PhD Iztok Fister |
Computer science and informatics |
Researcher |
2015 - 2019 |
315 |
10. |
52032 |
PhD Aljaž Frančič |
Systems and cybernetics |
Junior researcher |
2018 - 2019 |
26 |
11. |
31095 |
PhD Vojko Glaser |
Systems and cybernetics |
Researcher |
2017 |
50 |
12. |
03792 |
PhD Nikola Guid |
Computer science and informatics |
Researcher |
2015 |
461 |
13. |
21301 |
PhD Aleš Holobar |
Systems and cybernetics |
Researcher |
2015 - 2019 |
501 |
14. |
36450 |
PhD Denis Horvat |
Computer science and informatics |
Researcher |
2015 - 2017 |
26 |
15. |
25672 |
Marjan Horvat |
|
Technical associate |
2015 - 2019 |
23 |
16. |
37447 |
PhD David Jesenko |
Computer science and informatics |
Researcher |
2015 - 2019 |
46 |
17. |
16259 |
PhD Simon Kolmanič |
Computer science and informatics |
Researcher |
2015 - 2019 |
191 |
18. |
23454 |
PhD Tomaž Kosar |
Computer science and informatics |
Researcher |
2015 - 2019 |
246 |
19. |
52447 |
Ivan Kovačič |
|
Technical associate |
2019 |
16 |
20. |
53589 |
PhD Matej Kramberger |
Computer science and informatics |
Junior researcher |
2019 |
25 |
21. |
52029 |
Žiga Leber |
Computer science and informatics |
Junior researcher |
2018 - 2019 |
11 |
22. |
21318 |
PhD Bogdan Lipuš |
Computer science and informatics |
Researcher |
2015 - 2019 |
54 |
23. |
33709 |
PhD Niko Lukač |
Computer science and informatics |
Researcher |
2015 - 2019 |
202 |
24. |
39271 |
Sandi Majninger |
Computer science and informatics |
Technical associate |
2016 - 2017 |
37 |
25. |
11191 |
PhD Marjan Mernik |
Computer science and informatics |
Researcher |
2015 - 2019 |
690 |
26. |
36506 |
PhD Uroš Mlakar |
Computer science and informatics |
Researcher |
2015 - 2019 |
64 |
27. |
29243 |
PhD Domen Mongus |
Computer science and informatics |
Researcher |
2015 - 2019 |
277 |
28. |
21601 |
Jurij Munda |
|
Technical associate |
2015 - 2019 |
33 |
29. |
06823 |
PhD Milan Ojsteršek |
Computer science and informatics |
Researcher |
2015 - 2019 |
526 |
30. |
15801 |
PhD Božidar Potočnik |
Systems and cybernetics |
Researcher |
2015 - 2019 |
312 |
31. |
38213 |
PhD Miha Ravber |
Computer science and informatics |
Researcher |
2015 - 2019 |
45 |
32. |
08638 |
PhD Krista Rizman Žalik |
Computer science and informatics |
Researcher |
2015 - 2019 |
185 |
33. |
18726 |
PhD Damjan Strnad |
Computer science and informatics |
Researcher |
2015 - 2019 |
230 |
34. |
26035 |
PhD Denis Špelič |
Computer science and informatics |
Researcher |
2015 - 2018 |
62 |
35. |
50649 |
PhD Filip Urh |
Computer science and informatics |
Junior researcher |
2017 - 2019 |
29 |
36. |
28880 |
PhD Aleš Zamuda |
Computer science and informatics |
Researcher |
2015 - 2019 |
226 |
37. |
08061 |
PhD Damjan Zazula |
Systems and cybernetics |
Retired researcher |
2015 - 2019 |
789 |
38. |
32189 |
PhD Eva Zupančič |
Computer science and informatics |
Beginner researcher |
2017 - 2019 |
20 |
39. |
06671 |
PhD Borut Žalik |
Computer science and informatics |
Head |
2015 - 2019 |
850 |
40. |
31475 |
Denis Žganec |
Computer science and informatics |
Technical associate |
2015 - 2019 |
18 |
41. |
33994 |
PhD Danijel Žlaus |
Computer science and informatics |
Junior researcher |
2016 - 2019 |
23 |
Organisations (1)
Abstract
The proposed research would investigate the common characteristics of unstructured and heterogeneous data streams frequently emerging in computer science (e.g. on the World Wide Web, in Earth observation systems, and biomedical systems) that pose immense challenges with their diversities, dynamics, and huge data sizes. With the common goal of unifying their processing at a high level of abstraction, the individual data sources or streams, frequently embedded within strong environmental and instrumental noise, would be decomposed into basic semantic primitives (symbols), denoised and efficiently structured for their enrichment. The supporting algorithms would be implemented as loosely-coupled services, organised into three-tier architecture, and orchestrated for achieving a broad palette of applications from various domains. The first layer would perform domain-specific data management tasks, providing the middleware services from the second layer with interoperable data access. The second layer would be dedicated to the data enrichment and assessment of basic semantic primitives out of the data streams. For this purpose, the primary research focus would be directed towards two recently proposed paradigms: algebraic formalization, of attribute filters based on mathematical morphology, and latent components analysis. The first paradigm would enable precise evaluation of geometric properties by selective and fully automatic adaptation of the investigated patterns to the input datasets, whereas the second paradigm would exploit the time-space dependencies of data symbols for separation of compound data streams into contributions of different sources. Machine learning algorithms would be used to assess the heuristic knowledge about the characteristics of obtained data primitives (symbols) and integrate them within the high-level semantic units. The last layer in this architecture would be the application layer. Here, the middleware services would be chained and integrated into diverse applications, demonstrating universality and functional interoperability of the proposed approaches. As proof of concept, we would implement the detection of irregular muscle contractions from non-invasively acquired surface electromyograms, and monitoring of the Earth’s surface alterations due to landslides or erosions caused by water or wind. Both applications would address the actual socio-economic challenges caused or emphasised by recent demographic and climate changes. The suitable information support, based on elaborated data collection and trusted data interpretation is of key importance for efficient decision-making strategies at national and European levels. The suggested research of the computer algorithms would enable more effective, reliable, and efficient processing of data regarding the addressed applications and would thus significantly contribute to numerous scientific disciplines, also.
Significance for science
The main scientific contributions would arise from the new methodologically approaches to the decompositions of heterogeneous data streams into semantic primitives, their structuring, and semantic enrichment. In order to meet these goals, advances beyond the state-of-the art in the field of computer science would be made by functionally linking domain specific languages [2], evolution computation [9], mathematical morphology [10] and signal processing [11]. Their synergies would facilitate the development of new data enrichment paradigms, building on mechanisms of biological evolution, morphological operators, and domain-specific languages for semantic discretization of biomedical signals and streams. This would provide an efficient information infrastructure for basic research throughout numerous scientific fields, also those outside the computer science arena.
In the case of environmental studies, the proposed approach would provide accurate detections of objects and events covering vast geographical areas that were, until now, impossible to monitor. Thus, its contributions would be directly recognised and valued within the fields of geography, geomorphology, archaeology, forestry, and sustainable development. In the case of biomedical signals, the described paradigms would be used for quantitative analysis of neuromuscular systems and psycho-physical condition in humans. This would facilitate advanced diagnosis of neurodegenerative diseases and objective assessment of neurorehabilitation techniques. It would also facilitate the development of information support to the elderly and persons with disabilities. The superiority of our algorithms for the separation of biomedical signals has already been demonstrated in the diagnosis of Parkinson's disease, essential tremor [5] and the tracking of neuromuscular changes due to diabetes. In the future, their use would be extended to the analysis of cerebral palsy and stroke rehabilitation. In collaboration with the Otto Bock company, we would also develop a new generation of myoelectrical control systems for prosthetic devices that utilise surface electromyograms. Our approaches have already successfully decoded the activities of skeletal muscles after nerve transplantation following the upper-limb amputations.
[9] S.-H. Liu, M. Mernik, D. Hrnčič, M. Črepinšek. A parameter control method of evolutionary algorithms using exploration and exploitation measures with a practical application for fitting Sovova's mass transfer model, Applied soft computing 13(9):3792-3805, 2013.
[10] D. Mongus, N. Lukač, B. Žalik. Ground and building extraction from LiDAR data based on differential morphological profiles and locally fitted surfaces, ISPRS Journal of Photogrammetry and Remote Sensing, in press.
[11] S. Šprager, D. Zazula. Heartbeat and respiration detection from optical interferometric signals by using a multimethod approach, IEEE transactions on bio-medical engineering, 59(10): 2922-2929, 2012.
Significance for the country
Implementation and orchestration of the proposed algorithms in the form of loosely coupled intelligent services should allow their seamless integration into end-user applications. As proof of concept, the following two applications with widespread economic and social impact for Slovenia would be developed.
First, large scale analysis of the Earth’s surface, provided by an advanced GIS, would significantly improve in-time detection and dynamics’ assessment of critical events (landslides, floods, sleet, erosions), along with the corresponding risk evaluation. According to the official reports from the Statistical office of the Republic of Slovenia, the damages caused by natural disasters exceed 100 million euros per year. Natural disasters are hard to prevent but their devastating impacts can be mitigated by periodic terrain analyses and systematic monitoring of their characteristic indicators (cracks and terrain ridges for the event of landslides and changes in positions of riverbanks in the case of flooding). In close collaboration with our research and industrial partners (Geodetic Institute of Slovenia, Surveying and mapping authority of the Republic Slovenia, and Igea d.o.o.), a new methodology for evaluating the dynamics of critical events on the Earth’s surface would be developed and built into a new generation of GIS.
As a second demonstrator, the analysis of biomedical signals is an important source of information in clinical neurology, prevention of injuries, rehabilitation, training of athletes, and in the health monitoring of users with special needs. Musculoskeletal disorders in Slovenia cause a loss of up to 2% of GDP. Medical associations recommend regular monitoring of neuromuscular systems, but the tools for its non-invasive examination are lacking. As a result, experts estimate that 30-50% of rehabilitation treatments are inefficient. The proposed tools would facilitate objective clinical investigations and help to reduce their costs. Several technical solutions proposed by our members are already patented or patent-pending and the experts in the field of neurophysiology and physiotherapy have expressed a clear interest in their exploitation. Further methodological developments are encouraged also by health insurance companies and rehabilitation centers. In Slovenia, the application of these tools is foreseen primarily in the fields of clinical neurology and rehabilitation. Our programme group has long-lasting collaboration with the University Medical Center Ljubljana and the University Rehabilitation Institute Soča,
Last but not least, new discoveries would be published in top peer-reviewed journals. The knowledge gained would also be passed to the students of computer science and information technology study programme at the University of Maribor. In 2009-2014 this programme was successfully completed by 357 undergraduate and master students and by 17 doctoral students.
Most important scientific results
Annual report
2015,
interim report,
final report
Most important socioeconomically and culturally relevant results
Annual report
2015,
interim report,
final report