Computer Systems Department has developed Open Platform for Clinical Nutrition (OPKP) that is aimed at computerization of processes of nutritional and diet planning. OPKP provides a detailed insight into the composition of foods and planning balanced meals to individuals and groups (such as kindergartens and schools) in accordance with the latest evidence-based knowledge. It also facilitates the preparation of diet plans for those with special dietary needs, such as allergies or food intolerances. OPKP is performed as a modern web and mobile application (http://opkp.si/). User data is protected in accordance with the rules to ensure the security and privacy. Currently, the application is intended for research and development needs. In collaboration with the Pediatric Clinic of the University Medical Centre Ljubljana, we have tested the usability of OPKP by comparing the analyzes performed by OPKP and a nutrition software Prodi 5 (Nutria-Science). We also compared the calculations with the values obtained by chemical analysis.
F.15 Development of a new information system/databases
COBISS.SI-ID: 1729148Numerical optimization techniques are applied to a variety of engineering problems. The objective function evaluation is an important part of the numerical optimization and is usually realized as a black-box simulator, which is often time consuming. For time efficient solving the numerical optimization problem, new shared-memory approach was proposed. The algorithm is based on an ACO metaheuristics, where indirect coordination between ants drives the search procedure towards the optimal solution. Indirect coordination offers a high degree of parallelism and therefore relatively straightforward shared-memory implementation. It was shown that speed-up strongly depends on the simulation time. Since most of engineering problems are time-consuming, it is shown that our approach can be effectively used on most problems and we are able to significantly speed up the time it takes to get high quality solution. The above algorithm and some other nature-inspired optimization methods were successfully applied in practice. We have optimized product planning and management in ETA Cerkno, d. o. o. and temperature control of a refrigerator in Gorenje, d. d.
F.14 Improvements to existing production methods and tools or processes
COBISS.SI-ID: 24770343Highly reliable applications on FPGAs employ SEU mitigation and recovery techniques at different system levels. For this, modular redundancy and runtime partial reconfiguration are commonly employed techniques. Reported solutions feature different trade-offs in the area-overhead and the fault latency. We have developed a SEU-recovery mechanism for SRAM-based FPGAs which has a low hardware overhead and supports different self-recoverable architectures. The efficiency of the proposed approach was evaluated with a specially developed fault-emulation environment. The resulting estimated reliability is superior to the other reported solutions. In the next phase we plan to conduct realistic fault injection experiments at TRIGA reactor. The results will contribute to the assessment of reliability of the developed recovery mechanism in FPGA based embedded systems in the presence of radiation.
F.10 Improvements to an existing technological process or technology
COBISS.SI-ID: 25189159