Institute of Measurement Science
Reconstruction of the causal network from time series
Name of the supervisor
RNDr. Anna Krakovská, CSc.
Fakulta matematiky, fyziky a informatiky UK
Reconstruction of the causal network from time series is an emerging topic in many scientific disciplines. The aim of the reconstruction is to distinguish between direct and indirect effects, to reveal the presence of unobserved confounders, etc. The topic brings theoretical challenges, as well as the opportunity to design new methods and test them on real measurements. Emphasis will be placed on the development of a methodology for causal detection, taking into account the nature of the investigated processes (stochastic, fractal, deterministic, or combined). From the application point of view, multichannel electroencephalographic records from the human brain, multi-lead ECG measurements, large sets of climate measurements, time evolution of a number of economic indicators and other real problems of finding causal relationships from measured time series are of particular interest. The topic is suitable for graduates interested in creative application and development of appropriate mathematical approaches. Machine learning methods could also be used. Good English skills and experience in creating and testing software in the MATLAB environment are also a necessary requirement. As part of the doctoral study, the student will expand his/her knowledge in the field of biomeasurement and get acquainted with methods from the theory of dynamical systems, including chaos and fractal theory and partly on statistics, information theory and mathematical optimization. The dissertation will be solved at the Institute of Measurement Science of the Slovak Academy of Sciences in Bratislava.