ClowdFlows is an open cloud based platform for composition, execution, and sharing of interactive data mining workflows. In this paper we extend the ClowdFlows platform with the ability to mine real-time data streams. This functionality was implemented by creating a specialized type of workflow component and a stream mining daemon that delegates the execution of workflows in real-time. In this way, we have transformed a batch data processing platform into a real-time stream mining platform with an intuitive user interface.
F.15 Development of a new information system/databases
COBISS.SI-ID: 27392039Nada Lavrač had an invited talk entitled "Advances in data mining for biomedical research" on the 13th European Conference on Computational Biology (ECCB 2014), 7.-10.9.2014 in Strasbourg, France (http://eccb.iscb.org/2014/) - the conference was attended by approximately 1200 participants. She had a similar lecture on the 34th Joint Conference on Medical Informatics JCMI 2014 & 15th Annual Conference of Japan Association for Medical Informatics, 6.-8.11. 2014 in Chiba, Japan [COBISS.SI-ID 28099879] (http://www.ho.chibau. ac.jp/jcmi2014/Program.html)- the lecture attended around 800 participants from 2.000 registered conference participants. Nada Lavrač had also an invited lecture with the same topic within the cycle "Scientific evenings" organised by the University of Nova Gorica in the castle Lanthieri on 16.4.2014. [COBISS.SI-ID 27648039]
B.04 Guest lecture
COBISS.SI-ID: 27941159Biologists have been investigating plant defence response to virus infections; however, a comprehensive mathematical model of this complex process has not been developed. One obstacle in developing a dynamic model, useful for simulation, is the lack of kinetic data from which the model parameters could be determined. In the paper we address this problem by proposing a methodology for iterative improvement of the model parameters until the simulation results come close to the expectation of biology experts. These expectations are formalized in the form of constraints to be satisfied by the model simulations. In three iterative steps the model converged to satisfy the biology experts. There are two results of our approach: individual simulations and optimized model parameters, which provide a deeper insight into the biological system. The proposed constraint-driven optimization approach allows for an efficient exploration of the dynamic behavior of biological models and, at the same time, increases their reliability.
F.11 Development of a new service
COBISS.SI-ID: 27540775Glioblastoma multiforme (GBM) is among the most aggressive cancers with short life expectancy in the range of 12 to 15 months, which is only 3 months without medical treatment. MicroRNA profiling of 734 human and human-associated viral miRNAs was performed on blood plasma samples from 16 healthy individuals and 16 patients with GBM. One of the most important results is the identification of a group of ten candidate miRNAs exhibiting diagnostic as well as prognostic potential. Among them, hsa miR 592 and hsa miR 514a 3p have not been previously described in GBM and thus represent novel candidates for selective biomarkers.
F.02 Acquisition of new scientific knowledge
COBISS.SI-ID: 3453007Nada Lavrač had an invited talk entitled "Relational and semantic data mining" on an international LPNMR 2015 conference, September 27-30 in Lexington, Ky, USA. The conference was attended by approximately 200 participants. [COBISS.SIID: 28943911]
B.04 Guest lecture
COBISS.SI-ID: 28943911