Data Science Research Group
"We focus on unified data analysis of vast, heterogeneous data."
We are researchers focused on unified data analysis of (big) heterogeneous data. We aim to develop methods and tools to enable the discovery of new findings across various datasets and different domains.
We develop a secure and powerful data processing infrastructure, allowing us to process and analyse sensitive data in the modular processing environment. We employ our research results in interdisciplinary research, including cybersecurity and crime analysis, environment data analysis, and others.
Our works strength lies in our ability to capture and process diverse, large-scale data that can then be processed and analyzed using modern methods in a unified analytical environment.
Our research interests cover a wide area of methods for secure and reliable data storage, data processing and unified analysis.
We focus on building a robust and reliable data processing infrastructure comprising hierarchical data storage with heterogeneous data indexes, workflow-based data processing on the Kubernetes container platform, and visualizations. We build and provide a data analysis solution not only for individual data analysts, but also for communities with specific data analysis interests. Besides data processing infrastructures, we also offer solutions for particular data analysis tasks, collaborating with various research groups on an interdisciplinary level.
ENVision is environmental data analysis portal for a unified analysis of (primarily) geospatial data obtained from satellite or aerial imagery.
In cooperation with Institute of Physics of Material, we developed MELASA - a tool for computing anisotropic elastic properties of coherent nano-composites using linear-elasticity methods.
CopAS is a system targeted at personal digital forensics analysis, allowing network operators to comfortably analyze and correlate large amounts of primarily network data on limited HW resources.
Multi-phase ELAStic Aggregates (MELASA) software tool for modeling anisotropic elastic properties of lamellar composites
Computer Physics Communications, year: 2020, volume: 247, edition: FEB 2020, DOI
A deterministic approach for rapid identification of the critical links in networks
PLOS ONE, year: 2019, volume: 14, edition: 7, DOI
Big Data - overview, basic concepts and practical use in research
Year: 2019, type:
Numerical and experimental investigation of three-dimensional cavitating flow around the straight NACA2412 hydrofoil
Ocean Engineering, year: 2016, volume: 123, edition: 123, DOI
Our research group collaborates closely with other research teams, finding data analysis and processing solutions for specific cases. With some research teams, we deal with particular data analyses opening new research opportunities. And with others, we collaborate in designing and building private or public data infrastructures for sharing and interactive data analysis of a specific (research, government) community.
With Police of the Czech Republic, established under the jurisdiction of the Ministry of the Interior, we collaborate in designing and building a highly-secure data processing and analysis infrastructure as well as novel data analysis methods supporting crime investigations.
CzechGlobe is a research institution investigating the ongoing global change and its impact on the atmosphere, biosphere and human society. We collaborate on designing and building a flexible infrastructure for data processing and analysis, as well as new analytical methods for analyzing various environmental phenomena over heterogeneous data.
The aim of the Institute of Physics of Materials of the Czech Academy of Sciences is to elucidate the relation between the behaviour and properties of materials and their structural and microstructural characteristics. We collaborate on analyzing structural defects and destructions of various materials using a vast amount of acoustic emission data of their mechanical stresses.
Interested in Our Research? Join Us!
We are searching for new colleagues for various positions who would work with us on exciting projects, develop unique software and solve unconventional problems. In case of interest, contact firstname.lastname@example.org.
RNDr. Tomáš Rebok, Ph.D.
Data Science Research Group Leader
Tom focuses on all topics covered by the group. He leads research activities, mentors students, and communicates with partners to identify exciting research goals and projecs. He proposes and designs the solutions developed by the group, and his primary research interests cover heterogeneous data indexes and workflow-based data processing using containers. Besides research activities, he teaches at the Faculty of Informatics at Masaryk University.
RNDr. Milan Čermák, Ph.D.
Milan researches novel techniques for a forensic analysis of network traffic data using modern approaches and technologies such as a stream or graph-based analysis frameworks. In addition to detecting attacks and anomalies in network traffic, he is also interested in various cybersecurity areas, including web penetration testing or criminal investigation. He is the manager of main group projects and teaches various lectures focused on cybersecurity at the Faculty of Informatics at Masaryk University.