CS Forum: Vladimir Kuzmanovski, Jožef Stefan Institute "Integration of data-derived and expert knowledge into a coherent whole: Use-cases in agriculture"
CS forum is a seminar series arranged at the CS department - open to everyone free-of-charge.
Vladimir Kuzmanovski
Jožef Stefan Institute
Host: Jaakko Hollmén
Time: 14:15 (coffee at 14:00)
Venue: T3, CS building, Konemiehentie 2, Espoo
Integration of data-derived and expert knowledge into a coherent whole: Use-cases in agriculture
Abstract:
Real-world decision-making problems have a complex nature that requires the use of different sources of information, including predictions and simulations, in order to accomplish the goal of decision making and deal with uncertainty. Through the use of data mining, knowledge can be extracted from data in the form of predictive or descriptive models. This kind of knowledge complements expert knowledge obtained from domain experts through a knowledge engineering process and captured in the form of evaluation models for decision support. Their integration, combining prediction and evaluation, allows for the automation of the complete decision-making process under uncertainty.
Decision-making challenges present in the agricultural domain, and in particular sustainable food production, are of such a complex nature. I will present selected use-cases that address two challenges in the domain of sustainable food production: integrated pest management, combining conventional and biological pest management (and balancing the protection of both plants/ crops and the environment), and the simultaneous optimization of a range of soil functions. In both cases, the two kinds of knowledge are integrated to ease the implementation of a decision support system and improve its applicability.
Bio:
Dr. Vladimir Kuzmanovski is a researcher from Jožef Stefan Institute. He received his PhD degree in 2016 from Jožef Stefan International Postgraduate School, Ljubljana, Slovenia. The study has been performed under the supervision of Prof. Dr. Marko Debeljak and the thesis has been titled “Integrating decision support and data mining for risk evaluation and management: A methodological framework and a case study in agriculture”.
His research is in the field of data mining and decision support systems, and includes the study, developments and application of different data mining algorithms. The results of his research work were published in several journals and presented at several conferences.
His recent research activities include development and application of AI methods for improving the sustainable food production. Dr. Kuzmanovski is part of several H2020 and industrial projects, including LANDMARK (LAND – Management, Assessment, Research, Knowledge base), TOMRES (Novel and Integrated Approach to Increase Multiple and Combined Stress Tolerance in Plants Using Tomato as a Model) and TRUE (TRansition paths to sUstainable legume-based systems in Europe).