Topics for PhD students

Our experienced advisors offer the following doctorate topics for applicants interested in a Ph.D. study at selected study programmes.

Control and optimization algorithms for autonomous cars
The goal is to build an autonomous race model car and participate in F1/10 competition. The model car construction (mechanical design, electronics design, and basic software) being available, the thesis will focus on advanced aspects of the SW architecture, namely on control and optimization algorithms.
Study program: Control Engineering and Robotics
Czech Technical University – Faculty of Electrical Engineering
Advisor: Prof. Dr. Ing. Zdeněk Hanzálek

Optimization algorithms for electric cars
The task is to design and test algorithms for energetically optimal control of an electric vehicle. Using an appropriate model of the vehicle, analyse existing dynamic programming based optimization algorithm, create your own, make simulations, and choose the most appropriate algorithm.
Study program: Control Engineering and Robotics
Czech Technical University – Faculty of Electrical Engineering
Advisor: Prof. Dr. Ing. Zdeněk Hanzálek

Data-driven design of robust scheduling algorithms for flexible production
Production companies are embarking on an ambitious Factory of Future (or Industry 4.0) program to take advantage of digital technologies. This upgrade will put scheduling and data analytics at the centre of the production system. The thesis aims at designing data-driven algorithms to generate schedules for production, both static and dynamic.
Study program: Control Engineering and Robotics
Czech Technical University – Faculty of Electrical Engineering
Advisor: Prof. Dr. Ing. Zdeněk Hanzálek

3D scene reconstruction from images
3D scene reconstruction from images is a fundamental problem of computer vision. It finds many applications in industry ranging from autonomous driving to movie special effects. The topic is best for students with interest in algorithms, experimental work, and engineering of really working systems.
Study program: Artificial Intelligence and Biocybernetics
Czech Technical University – Faculty of Electrical Engineering
Advisor: Doc. Ing. Tomáš Pajdla, Ph.D.

Algebraic methods in computer vision and robotics
Algebraic techniques have proved very useful in solving difficult problems in geometry of computer vision. We will aim at studying more advanced elements of algebraic geometry and applying them to real engineering problems. The topic is best for students with interest in applied mathematics.
Study program: Artificial Intelligence and Biocybernetics
Czech Technical University – Faculty of Electrical Engineering
Advisor: Doc. Ing. Tomáš Pajdla, Ph.D.

Image-based scene recognition and visual localization
Visual scene recognition and image based localization is an important problem in computer vision and machine learning. We will aim developing new approaches to place representation and its search. The topic is suitable for students with interest computer vision and machine learning applied to real engineering problems.
Study program: Artificial Intelligence and Biocybernetics
Czech Technical University – Faculty of Electrical Engineering
Advisor: Doc. Ing. Tomáš Pajdla, Ph.D.

Polynomial optimization in computer vision and robotics
Polynomial optimization techniques proved very useful in solving interesting problems in geometry of computer vision and robotics. We will aim at studying polynomial optimization techniques and applying them in computer vision and robotics. The topic is suitable for students with interest in mathematics applied to real engineering problems.
Study program: Artificial Intelligence and Biocybernetics
Czech Technical University – Faculty of Electrical Engineering
Advisor: Doc. Ing. Tomáš Pajdla, Ph.D.

Navigation and planning for complex robots
The focus is on the development of new algorithms for processing, analysis, and fusion of data produced by chosen sensors (2D and 3D range sensors or cameras), fast and robust navigation based on these data, and efficient planning in tasks like multi-robot surveillance and reconnaissance, formation keeping, and dexterous cooperative manipulation.
Study program: Artificial Intelligence and Biocybernetics
Czech Technical University – Faculty of Electrical Engineering
Advisor: RNDr. Miroslav Kulich, Ph.D.

Routing problems in mobile robotics
Typical tasks for mobile robots include inspection of a priori known environment, exploration of an unknown environment, or search for an object of interest. These tasks lead to a solution of NP-hard optimization problems. The thesis will focus on research and development of novel approximation methods to solve such an optimization problems.
Study program: Artificial Intelligence and Biocybernetics
Czech Technical University – Faculty of Electrical Engineering
Advisor: RNDr. Miroslav Kulich, Ph.D.

The Spatial Human Locomotion Analysis
The project includes analysis of multichannel data resulting from recording by motion sensors and wireless EEG systems. Research part of the project includes the study of image registration methods, time evolution of their changes and the proposal of Bayesian classification of selected features using computational intelligence methods. Resulting algorithms will be verified for the group of diseased and healthy individuals related to the illness progression and they will be used for early diagnostics of movement disorders in the clinical environment. The thesis will be co-supervised at the Dept of Neurology of the Faculty of Medicine in Hradec Kralove (MUDr. Oldřich Vyšata, Ph.D.).
Study program: Engineering Cybernetics
University of Chemistry and Technology – Faculty of Chemical Engineering
Advisor:Prof. Ing. Aleš Procházka, CSc.

Multi-Channel Data and Image Analysis for Monitoring and Diagnostics in Physiological Signals
The project is devoted to adaptive methods of multi-channel data analysis using computational intelligence and digital multidimensional signal processing tools both in the time and frequency domains. The methodology includes processing of videosequences, 3D geometric modelling, machine learning and pattern recognitiion for data classification. The application will be devoted to rehabilitation analysis and correlations of physiological and GPS signals to physical activities. The thesis will be co-supervised at the Dept of Neurology of the Faculty of Medicine in Hradec Kralove (MUDr. Oldřich Vyšata, Ph.D.).
Study program: Engineering Cybernetics
University of Chemistry and Technology – Faculty of Chemical Engineering
Advisor:Prof. Ing. Aleš Procházka, CSc.

Information Entropy in Cell Motion Detection Using Bright-field Light Microscopy
Bright-field light microscopy is the microscopic technique which can bring undistorted information on a physiological and morphological state of a live cell. The aim of the project will be in the proposal of a method for automatic detection and statistic evaluation of mammalian organelles´ trajectories in micrographs obtained using time-lapse bright-field light microscopy. Digital image processing tools will include methods of information entropy and multivariate statistical analysis. The thesis will be co-supervised at the Inst. of Complex Systems of University of South Bohemia (Ing. Renata Štýsová-Rychtáriková, Ph.D.).
Study program: Engineering Cybernetics
University of Chemistry and Technology – Faculty of Chemical Engineering
Advisor:Prof. Ing. Aleš Procházka, CSc.

Multivariate Statistics in Spatial Reconstruction of Cell Organelles Based on Fluorescence Microscopy
Fluorescence microscopy is a tool of cell biologists in the study of intracellular relations using markers specifically bounded to organelles or using autofluorescence. During observation of autofluorescence and multiple labelling, there exists a common problem of colour aberration that projects each emitted wavelength into a different spatial point. The dissertation will use image processing methods, information entropy and new mathematical procedure for identification of the focal level of each individual fluorophore´s response from the z-stack of microscopic images. The goal is to propose a methodology for automatic fluorophores 3D mapping to enable the full utilization of the information content of microscopy datasets. The thesis will be co-supervised at the Inst. of Complex Systems of the University of South Bohemia (Ing. Renata Štýsová-Rychtáriková, Ph.D.).
Study program Engineering Cybernetics
University of Chemistry and Technology – Faculty of Chemical Engineering
Advisor: Prof. Ing. Aleš Procházka, CSc.

• Advanced methods of long-term multi-channel signal processing in neurosciences

Topic of the thesis is motivated by clinical research performed at the National Institute of Mental Health and neurological departments, focused on sleep medicine. In neurosciences and neurology we meet more and more frequently long-term recordings (mostly so-called polygraphic), where in various channels different physiological signals and additional data are recorded, usually with different sampling frequency. The work will be performed using neurological and neurophysiological data provided by cooperating university hospitals. New approaches will be studied, as for example application of advanced data mining algorithms, including metaheuristics and integration of medical background knowledge in the decision support process. Main aim is design and implementation of advanced methods of biomedical signal preprocessing and processing that will be able to find mutual relations in parallel time series (individual channels in the recordings) and detect significant segments.
Study program: Artificial Intelligence and Biocybernetics
Czech Technical University – Faculty of Biomedical Engineering
Advisor: doc. Ing. Lenka Lhotská, CSc.

Advanced methods of heterogeneous multidimensional data processing in electrophysiology

This topic is proposed based on close cooperation with clinical practice where we acquire data about one patient from various modalities. The basic requirement is to find mutual relations in such data. Thus we speak about large volumes of heterogeneous data and signals that must be evaluated in interrelated context. Representation methods are based on requirements on semantic interoperability. Processing methods are inspired by advanced mathematical transforms, methods of digital signal processing and data mining methods.
Aim of the research is design of suitable methods of data and knowledge representation that serve for efficient storing and communication on one side and design and implementation of advanced methods of processing that allow searching for mutual relations in data and reveal hidden information on the other side.
Study program: Artificial Intelligence and Biocybernetics
Czech Technical University – Faculty of Biomedical Engineering
Advisor: doc. Ing. Lenka Lhotská, CSc.

• Application of virtual reality to rehabilitation
The aim of the project is the research and development of a customized virtual reality system based on a serious game which allows the user to carry out physical and cognitive rehabilitation therapies using a natural user interface based on virtual reality. Within these serious games we can find the exergames. It is a type of serious game which aims to stimulate body mobility through an immersive experience that situates the user inside virtual interactive landscapes.
Study program: Artificial Intelligence and Biocybernetics
Czech Technical University – Faculty of Biomedical Engineering
Advisor: doc. Ing. Lenka Lhotská, CSc.