E. Butkevičiūtė “ECG signal analysis for the modelling of training process and fatique evaluation” doctoral dissertation defence

Thesis Defense

Author, Institution: Eglė Butkevičiūtė, Kaunas University of Technology

Science area, field of science: Natural Sciences, Informatics, N009

Scientific Supervisor: Assoc. Prof. Dr. Liepa Bikulčienė (Kaunas University of Technology, Natural Sciences, Informatics, N009)

Dissertation Defence Board of Informatics Science Field:
Prof. Dr. Habil. Rimantas Barauskas (Kaunas University of Technology, Natural Sciences, Informatics, N009) – chairman
Prof. Dr. Habil. Eugenijus Kaniušas  (Vienna Technical University, Technological Sciences, Measurement Engineering, T010)
Prof. Dr. Tomas Krilavičius (Vytautas Magnus University, Natural Sciences, Informatics, N009)
Prof. Dr. Alfonsas Misevičius (Kaunas University of Technology, Natural Sciences, Informatics, N009)
Assoc. Prof. Dr. Kristina Poškuvienė (Kaunas University of Technology, Natural Sciences, Informatics, N009)

The dissertation defence takes place online.

The doctoral dissertation is available on the internet and at the library of Kaunas University of Technology (K. Donelaičio g. 20, Kaunas).


Biological signals recorded in movement allow to evaluate interactions between different human organism systems and dynamic changes in daily activities. If a person performs physical or mental exercises, multiple systems work in parallel: cardiovascular, muscular, neural and others.  ECG signals recorded in movement are contaminated with various noises. The obtained noise is non-stationary and depends on the intensity of a particular exercise. That is why ordinary filtering methods fail in signal processing without damage to basic signal characteristics. The proposed filtering algorithm is able to adapt to the level of appearing noise in different workloads and maintain the most important ECG parameter values that are essential for the health evaluation and monitoring. Also, in this research a new physiological fatigue evaluation and recognition methodology is proposed that uses linear and non-linear heart rate variability analysis and machine learning techniques. In the classification part the accurate ECG signal parameter estimation algorithms becomes very important. For these parameters search the modified and supplemented k-TEO algorithm was selected and implemented.

We are using cookies to provide statistics that help us give you the best experience of our site. You can find out more or switch them off if you prefer. However, by continuing to use the site without changing settings, you are agreeing to our use of cookies.
I agree