Empirical data on real complex systems are becoming increasingly available. Parallel to this is the need for new methods of reconstructing (inferring) the structure of networks from time-resolved observations of their node-dynamics. The methods based on physical insights often rely on strong assumptions about the properties and dynamics of the scrutinized network. Here, we use the insights from machine learning to design a new method of network reconstruction that essentially makes no such assumptions. Specifically, we interpret the available trajectories (data) as “features” and use two independent feature ranking approaches—Random Forest and RReliefF—to rank the importance of each node for predicting the value of each other node, which yields the reconstructed adjacency matrix. We show that our method is fairly robust to coupling strength, system size, trajectory length, and noise. We also find that the reconstruction quality strongly depends on the dynamical regime.

Identification of biomarkers for the Alzheimer’s disease (AD) is a challenge and a very difficult task both for medical research and data analysis. We applied a novel clustering tool with the goal to identify subpopulations of the AD patients that are homogeneous in respect of available clinical as well as in respect of biological descriptors. The main result is identification of three clusters of patients with significant problems with dementia. The evaluation of properties of these clusters demonstrates that brain atrophy is the main driving force of dementia. The unexpected result is that the largest subpopulation that has very significant problems with dementia has besides mild signs of brain atrophy also large ventricular, intracerebral and whole brain volumes. Due to the fact that ventricular enlargement may be a consequence of brain injuries and that a large majority of patients in this subpopulation are males, a potential hypothesis is that such medical status is a consequence of a combination of previous traumatic events and degenerative processes. The results may have substantial consequences for medical research and clinical trial design. The clustering methodology used in this study may be interesting also for other medical and biological domains.

In this paper, we propose a new algorithm, called FOCUSED (FOrecast Correction Using Successive prEDictions), for forecast correction of short-term wind speed predictions. We developed FOCUSED with the aim of improving the forecast of bora gusts, which frequently result in high-speed wind situations dangerous for traffic. The motivation arises from occasionally ambiguous results of the currently deployed decision support system, which aids traffic management in strong and gusty wind conditions at the coast of Croatia. The proposed correction algorithm uses characteristics of numerical weather prediction models to iteratively forecast the wind speed multiple times for the same future window. We use these iterative predictions as input features of the FOCUSED algorithm and get the corrected predictions as the output. We compared the proposed algorithm with artificial neural networks, random forests, support vector machines, and linear regression to demonstrate the superiority of the algorithm’s performance on a data set comprising five years of real data measurements at the Croatian bridge “Krk” and complementary historical forecasts by ALADIN (Aire Limitée Adaptation dynamique Développement InterNational) numerical weather prediction model.

We present six datasets containing telemetry data of the Mars Express Spacecraft (MEX), a spacecraft orbiting Mars operated by the European Space Agency. The data consisting of context data and thermal power consumption measurements, capture the status of the spacecraft over three Martian years, sampled at six different time resolutions that range from 1 min to 60 min. From a data analysis point-of-view, these data are challenging even for the more sophisticated state-of-the-art artificial intelligence methods. In particular, given the heterogeneity, complexity, and magnitude of the data, they can be employed in a variety of scenarios and analyzed through the prism of different machine learning tasks, such as multi-target regression, learning from data streams, anomaly detection, clustering, etc. Analyzing MEX’s telemetry data is critical for aiding very important decisions regarding the spacecraft’s status and operation, extracting novel knowledge, and monitoring the spacecraft’s health, but the data can also be used to benchmark artificial intelligence methods designed for a variety of tasks.