We are witnessing the so-called “Big Data revolution”, where a deluge of data is being continuously generated by the massive Internet-of-Things, satellites and other sensory platforms – UAVs, monitoring stations, mobile phones… Furthermore, every day billions of people are providing new information through various systems or by uploading their images and videos on the internet. As the new data keeps pouring in, there is a huge need for ordering it and extracting valuable information. Indeed, these vast amounts of data carry tremendous hidden knowledge about our reality and their analysis offers many exciting opportunities. The extracted knowledge has the potential to bring significant benefits to many sectors, including agriculture, logistics and healthcare, but also to improve the quality of everyday life.
To achieve this goal, research of the BioSense’s knowledge technologies group addresses crucial scientific and technological challenges, such as how to store these huge amounts of data, how to homogenize heterogeneous data types and formats, how to make efficient data queries, but most of all how to perform efficient analytics. Our particular focus is on the data analytics where we develop advanced mathematical and pattern recognition techniques to discover interdependencies and nontrivial patterns hidden within the data sets. We utilize tools from machine learning, network science and optimization to develop new models of natural, technological, and business processes, as well as to analyze, classify and predict from the Big Data. As to applications, we have developed customized solutions for several real-world agricultural use cases, including crop yield prediction based on environmental readings, soybean varieties portfolio optimization, and classification of small agricultural fields using satellite imagery.