About DISA

There are huge amounts of digital data all around us…

…that need to be effectively organized!

In the Laboratory of Data Intensive Systems and Applications (DISA), we study and develop modern techniques for effective and efficient data management:

  • Similarity-based indexing and searching
  • Content-based multimedia processing
  • Distributed data organization

To get a quick idea about our research, you may see our presentation (in Czech) or try some of our demo applications:


  • February 22, 2017: First lecture of the DISA seminar in Spring 2017 starts
  • January 11, 2017: New course PA212 on advanced search techniques for large-scale data analytics will be taught by Pavel Zezula and Jan Sedmidubsky in Spring 2017.
  • December 12, 2016: DSBDA 2016 in Barcelona, Spain
    Vladimir Mic is presenting a paper Designing Sketches for Similarity Filtering
  • October 20, 2016: Kiwi.com company organizes a competition on analyzing flight connections. More detailed information is available here.
  • October 24-26, 2016: SISAP 2016 in Tokyo, Japan
    Jan Sedmidubsky is presenting a paper Similarity Searching in Long Sequences of Motion Capture Data
    Vladimir Mic is presenting a short paper Speeding up Similarity Search by Sketches
  • October 24-28, 2016: CIKM 2016 in Indianapolis, USA
    David Novak is presenting a paper Off the Beaten Path: Let’s Replace Term-Based Retrieval with k-NN Search