​​​Evelin Halling​

Ukraine has a quarter of the world’s chernozems and 41.5 million hectares of agricultural land, covering 70 percent of the country. Agriculture pollutes about 60 percent of land resources and approximately 45-48 percent of reservoirs, representing 18-24 % of global GHG emissions. SmartAGRO's goal is to develop a precision fertilization solution that will help Ukraine achieve its climate policy goals. SmartAGRO is based on capillary electrophoresis technology, which enables the determination of various macro- and microelements in the soil. The goal is to develop a precise agriculture platform with recommendations for soil fertilization for agricultural crops growing in Ukraine, taking into account the chemical profile of the soil, the type and the crops grown, helping to reduce the use of fertilizers, increase/maintain yields and reduce GHG emissions.

"EXCITE brings together the topranked ICT research groups Estonia to work jointly on a focussed, yet broad and extendable, research programme. It will capitalize on the existing expertise to create synergies on the rich but fragmented landscape of the Estonian ICT research. The consortium will advance foundational theories of model verification and data analysis. On this groundwork, it will develop methods and tools for sound practices of designing and analyzing reliable and secure ICT systems processing large data volumes, as demanded by applications to domains of high socioeconomic relevance (cyberphysical and robotic systems, ehealth and biomedical systems). We will start with 10 cooperation themes with clearly defined objectives, methodology and expected results. These themes will be refined and redefined after 3 years. EXCITE will support research sustainability and provide a development opportunity for young researchers by financing 20-30 PhD students and postdocs.

Drug Hunter is a portable analyzer for the detection of narcotics in saliva. The project's goal was to integrate machine learning methods into an expert system for substance detection to reduce the competence required of the analyzer's user to interpret the results and thereby reduce errors in substance detection. Various machine learning methods based on supervised learning - artificial neural networks - were tested during the project. In order to prepare (annotate) the data necessary for training the neural network, a cloud service was created, where the technical parameters of all analyzes and the obtained electropherograms, on which the substances to be analyzed were marked, were stored. The best results in detecting electrophoretic patterns were obtained using a convolutional neural network (CNN). The analyzer was tested in cooperation with Estonian Police at roadside drug testing raids in Estonia.