prof. RNDr. Ing. Jiří Šťastný, CSc.

E-mail:   stastny@fme.vutbr.cz 
Dept.:   Institute of Automation and Computer Science
Dept. of Applied Computer Science
Position:   Professor
Room:   A1/0623
Phone:   +420 54114 3341

Education and academic qualification

  • 1978, Ing. (MSc.), Faculty of Mechanical Engineering, Brno University of Technology, branch Instrumentation, Regulation and Automation Technique
  • 1984, CSc. (Ph.D.), Faculty of Mechanical Engineering, Brno University of Technology, branch Structure of Production Machines and Facilities
  • 1986, Mgr. (MSc.), Faculty of Sciences, Masaryk University in Brno, branch Mathematical Computer Science
  • 1987, RNDr., Faculty of Sciences, Masaryk University in Brno, branch Mathematical Computer Science
  • 2006, Doc. (Assoc. Prof.), Faculty of Mechanical Engineering, Brno University of Technology, branch Structural and Process Engineering
  • 2012. Prof., Faculty of Business and Economics, Mendel University in Brno, branch Managerial Computer Science

Career overview

  • 1978-1979, technical staff, Department of Machinery and Automation of Building Industry, Faculty of Civil Engineering, Brno University of Technology
  • 1979-1982, postgraduate (research education) Faculty of Mechanical Engineering, Brno University of Technology
  • 1982-1994, senior lecturer, Department of Instrumentation and Automation Technique, Faculty of Mechanical Engineering, Brno University of Technology
  • 1989-1991, research worker, Department of Technology Research, VUVL Brno
  • 1994-2006, senior lecturer, Institute of Automation and Computer Science, Faculty of Mechanical Engineering, Brno University of Technology
  • 2006-2012, assoc. prof., Institute of Automation and Computer Science, Faculty of Mechanical Engineering, Brno University of Technology
  • 2006-2012, assoc. prof., Department of Informatics, Faculty of Business and Economics, Mendel University in Brno
  • 2012-present, professor, Institute of Automation and Computer Science, Faculty of Mechanical Engineering, Brno University of Technology
  • 2012-present, professor, Department of Informatics, Faculty of Business and Economics, Mendel University in Brno

Pedagogic activities

  • BSC study programme: methods and software of system simulation
  • MSC study programme: methods and algorithms of system simulation, MSC Thesis seminars and projects
  • Ph.D. study programme: artificial intelligence methods in simulation and optimization
  • MSC Thesis supervised in applied informatics
  • Ph.D. Thesis supervised for applied informatics

Scientific activities

  • Image processing algorithms in real time
  • Artificial intelligence methods in modelling, simulation and optimization
  • Neural neworks and evolutionary algorithms for data classification and prediction

Academic internships abroad

  • 1987, Magdeburg University of Technology (Germany)
  • 1995, Graz University of Technology (Austria)

Non-University activities

  • 2006-present: Member of the System Engineering and Informatics PhD Study Academic Council at Mendel University in Brno
  • 2011-present: Member of expert consultative body of MEYS CR for research, development and innovation
  • 2014-present: Member of the Scientific board of the FBE, Mendel University in Brno

Projects

  • 1996-1997, Active Elements of High-Speed ATM Network and their Using in Academic Network, Education and Research. Research project FR470626
  • 1998-2004, Research of Communication Systems and Technologies. Research design MSM 262200011
  • 2002-2004, Non-Traditional Methods for Investigating Complex and Vague Systems. Research design MSM 261100009
  • 2003-2006, Limits for Broad-Band Signal Transmission on the Twisted Pairs and Other System Co-Existence. Research project GACR 102/03/0434
  • 2003-2006, New Methods for Location and Verification of Compliance of Quality of Service in New Generation Networks. Research project GACR 102/03/0560
  • 2007-2009, Advanced Optimisation of Communications Systems Design by Means of Neural Networks. Research project GACR 102/07/1503
  • 2007-2011, Intelligent systems in automation. Research design MSM 0021630529
  • 2009-2012, The research of energy saving equipment for achievement of interior environment comfort. Research project GACR 101/09/H050 

Sum of citations (without self-citations) indexed within SCOPUS

122

Sum of citations (without self-citations) indexed within ISI Web of Knowledge

78

Supervised courses:

Publications:

  • STASTNY, J; SKORPIL, V:
    Object Recognition by Means of Early Parser Effective Implementation,
    Proc. 40th. Int. Conf. Telecommunications and Signal Processing, pp.271-274, ISBN 978-1-5090-3981-4, (2017)
    conference paper
    akce: 2017 40th International Conference on Telecommunications and Signal Processing (TSP), Barcelona, 05.07.2017-07.07.2017
  • ŠŤASTNÝ, J.; RICHTER, J.:
    Adaptation of Genetic Algorithm to Determine Air Jet Shape of Flow Visualized by Helium Bubbles,
    JOURNAL OF AEROSPACE ENGINEERING, Vol.29, (2016), No.6, pp.1-14, ISSN 0893-1321, ASCE-AMER SOC CIVIL ENGINEERS, 1801 ALEXANDER BELL DR, RESTON, VA 20191-4400, USA
    journal article
  • ŠŤASTNÝ, J.; ŠKORPIL, V.; ČÍŽEK, L.:
    Traveling Salesman Problem Optimization by Means of Graph-based Algorithm,
    Proceedings of the 39th International Conference on Telecommunications and Signal Processing (TSP), pp.207-210, ISBN 978-1-5090-1287-9, (2016)
    conference paper
    akce: Telecommunications and Signal Processing (TSP) 2016, Vídeň, 27.06.2016-29.06.2016
  • ŠŤASTNÝ, J.; ŠKORPIL, V.:
    Ensuring Invariances for Structural Methods of Object Recognition,
    38 International Conference on Telecommunications and Signal Processing, pp.271-275, ISBN 978-1-4799-8497-8, (2015), FEKT Brno
    conference paper
    akce: 38th International Conference on Telecommunications and Signal Processing (TSP 2015), Prague, 09.07.2015-11.07.2015
  • ŠŤASTNÝ, J.; RICHTER, J.; ŠŤASTNÝ, P.:
    Using Neural Networks for Determining Velocity Vectors of Air Flow Visualized by Helium Bubbles,
    Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis, Vol.2014 (62), (2014), No.4, pp.757-768, ISSN 1211-8516
    journal article
  • ŠŤASTNÝ, J.; ŠKORPIL, V.; FEJFAR, J.:
    Visualization of Uncertainty in LANDSAT Classification Process,
    Proceedings of the 38th International conference on Telecommunications and Signal Processing, pp.789-792, ISBN 978-1-4799-8497-8, (2014), Brno University of Technology
    conference paper
    akce: 37th International Conference on Telecommunications and Signal Processing (TSP), Berlín, 01.07.2014-03.07.2014
  • ŠŤASTNÝ, J.; ŠKORPIL, V.; FEJFAR, J.:
    Audio Data Classification by Means of New Algorithms,
    Proceedings of the 36 th International Conference on Telecommunikations and Signal Processing (TSP 2013), pp.507-511, ISBN 978-1-4799-0402-0, (2013), TSP
    conference paper
    akce: 2013 36th International Conference on Telecommunications and Signal Processing, Rome, 02.07.2013-04.07.2013
  • RICHTER, J.; ŠŤASTNÝ, J.; JEDELSKÝ, J.:
    Estimations of Shape and Direction of an Air Jet Using Neural Networks.,
    MENDEL 2013, pp.221-226, ISBN 978-80-214-4755-4, (2013)
    conference paper
    akce: 19th International Conference on Soft Computing, MENDEL 2013, Brno University of Technology, 26.06.2013-28.06.2013

List of publications at Portal BUT

Abstracts of most important papers:

  • ŠŤASTNÝ, J.; RICHTER, J.:
    Adaptation of Genetic Algorithm to Determine Air Jet Shape of Flow Visualized by Helium Bubbles,
    JOURNAL OF AEROSPACE ENGINEERING, Vol.29, (2016), No.6, pp.1-14, ISSN 0893-1321, ASCE-AMER SOC CIVIL ENGINEERS, 1801 ALEXANDER BELL DR, RESTON, VA 20191-4400, USA
    journal article

    During the development of ventilation and air conditioning systems, it is important to verify the functionality of the devised system, especially the method by which air fills the space. In this case, an optical visualization method of introducing helium bubbles into the airflow can be used for this function. A special generator produces small bubbles filled with helium. These bubbles are visible particles of airflow, making it possible to determine the shape of such a flow. This article describes the evaluation of flow images visualized by helium bubbles. Bubbles are detected by comparing intensities and subsequently cleaning faulty bubbles. For a convex airflow shape, exact geometric methods are used, and for a more precisely nonconvex shape of airflow, a genetic algorithm is used, in which a sophisticated algorithm of arranging a boundary line from selected points is applied. The algorithm also includes a specific approach of representing individuals in population inclusive of determining their fitness values. Read More: http://ascelibrary.org/doi/abs/10.1061/%28ASCE%29AS.1943-5525.0000650
  • ŠŤASTNÝ, J.; ŠKORPIL, V.; ČÍŽEK, L.:
    Traveling Salesman Problem Optimization by Means of Graph-based Algorithm,
    Proceedings of the 39th International Conference on Telecommunications and Signal Processing (TSP), pp.207-210, ISBN 978-1-5090-1287-9, (2016)
    conference paper
    akce: Telecommunications and Signal Processing (TSP) 2016, Vídeň, 27.06.2016-29.06.2016

    There are many different algorithms for optimization of logistic and scheduling problems and one of the most known is Genetic algorithm. In this paper we take a deeper look at a draft of new graph-based algorithm for optimization of scheduling problems based on Generalized Lifelong Planning A* algorithm which is usually used for path planning of mobile robots. And then we test it on Traveling Salesman Problem (TSP) against classic implementation of genetic algorithm. The results of these tests are then compared according to the time of finding the best path, its travel distance, an average distance of travel paths found and average time of finding these paths. A comparison of the results shows that the proposed algorithm has very fast convergence rate towards an optimal solution. Thanks to this it reaches not only better solutions than genetic algorithm, but in many instances it also reaches them faster.
  • Lýsek Jiří, Šťastný Jiří:
    Automatic discovery of regression model by means of grammatical and differential evolution

    n this contribution we will discuss the usage of method based on grammatical and differential evolution for automatic discovery of regression models for discrete datasets. The combination of these two methods enables the process to find precise structure of the mathematical model and values for the model constants separately. Used method will be described and tested on selected regression examples. The results will be reported and obtained mathematical models will be presented. Advantages of selected approach will be described and compared to classical methods.
  • ŠŤASTNÝ, J.; RICHTER, J.; ŠŤASTNÝ, P.:
    Using Neural Networks for Determining Velocity Vectors of Air Flow Visualized by Helium Bubbles,
    Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis, Vol.2014 (62), (2014), No.4, pp.757-768, ISSN 1211-8516
    journal article

    One of the important characteristics of air flow is the velocity of flow. To determine the speed, in addition to other methods, we also use the helium bubbles seeding visualization method, when bubbles are injected into the air stream so that the air flow is obvious to the eye. If a video of such flow is taken, it is possible to determine velocity vectors in a pair of consecutive frames of this video footage, derived from the change in position of individual bubbles. This article describes a method of monitoring the bubbles in consecutive video frames. During this process, helium bubbles are detected in the first image of the pair, either by a firmly defined procedure, or with the use of a neural network. For detected bubbles, the velocity vectors are determined according to the way in which they move, therefore, according to their location in the following frame. Another neural network then determines the velocity vector at any point of image, which will be implemented in the construction of vector maps for the first image. A vector map is used for comprehensive evaluation of air flow and thus, plays an important role in the development of ventilation and air conditioning systems.
  • ŠŤASTNÝ, J.; ŠKORPIL, V.; FEJFAR, J.:
    Visualization of Uncertainty in LANDSAT Classification Process,
    Proceedings of the 38th International conference on Telecommunications and Signal Processing, pp.789-792, ISBN 978-1-4799-8497-8, (2014), Brno University of Technology
    conference paper
    akce: 37th International Conference on Telecommunications and Signal Processing (TSP), Berlín, 01.07.2014-03.07.2014

    Many uncertainties can be found in the classification of remotely sensed data. Namely they can arise in defining classification classes. We use two ways, incorporating acquired Corine Land Cover labels and our manually annotated labels. We are describing several visualization possibilities to demonstrate uncertainties in labels and their connections with classification results. We use parallel coordinates to visualize data, presenting problems in classes definitions. These failures can be consequently seen in the results of classification in confusion matrix.