We organized a Summer school on mining big and complex data (http://maestra-project.eu/school/). The school included lectures on predictive modelling methods for big and complex data. More specifically, the lectures presented methods handling the following complexity aspects: (a) structured data as input or output of the prediction process, (b) very large/massive datasets, with many examples and/or many input/output dimensions, where data may be streaming at high rates, (c) incompletely/partially labelled data, and (d) data placed in a spatio-temporal or network context. The applicability and the potential of the presented methods was demonstrated on showcases from environmental sciences (including agriculture), molecular biology, sensor networks, multimedia, and social networks. More specifically, on the topic of environmental applications, several studies performed within the project were presented such as modelling soil functions and predicting the quality of agricultural waters. The lectures were be given by world leading researchers and experts in machine learning and data mining, as well as experts from the application domains. The school was attended by approximately 100 participants. The lectures were recorded and are available at videolectures.net.
B.01 Organiser of a scientific meeting
COBISS.SI-ID: 30338855Our team won the competition of the European Space Agency ESA Mars Express Power Challenge with the development of the best solution for forecasting the use of electric energy on the space probe. In the spring 2016 ESA organised an open competition to develop a model for predicting the use of electric power on the space probe Mars Express. Even though the probe was launched already in 2003 and has used up most of its fuel, the probe is still operational. One of the greater challenges in prolonging its operations is the spent battery, which is why ESA wanted to obtain a model that would enable an accurate prediction of the necessary energy for heating the probe and, with this, indirectly, an estimate of the energy that is available for scientific measurements. We developed the winning solution which uses machine learning methods for generating the model, in particular ensemble methods for multi-target regression.
E.02 International awards
COBISS.SI-ID: 30018599