Přístupnostní navigace
E-application
Search Search Close
Bachelor's Thesis
Author of thesis: Jakub Duchaj
Acad. year: 2025/2026
Supervisor: MUDr.Ing. Richard Ředina
Reviewer: Ing. Jiří Chmelík, Ph.D.
This thesis focuses on the analysis of the informational value of feature maps extracted by a segmentation neural network from ECG signals for the purpose of MI classification. The main objective of the work is to understand how discriminative information is represented in these features and to evaluate its usability for classification tasks using machine learning methods. The thesis includes a theoretical introduction to ECG signal acquisition and processing, followed by an exploratory data analysis. The insights obtained from the analysis are subsequently used to design and evaluate classification experiments. The best achieved F1 score of the classification reached 0.469. The results show that the performance of the classification algorithm is primarily influenced by the chosen feature representation.
electrocardiography, myocardial infarction, classification, machine learning, PTB-XL
Date of defence
16.06.2026
Result of the defence
Not defended (thesis was not successfully defended)
Grading
F
Process of defence
Student prezentoval výsledky své práce a komise byla seznámena s posudky. Komise se shodla, že student v BP nesplnil bod 5 v zadání. Student neobhájil bakalářskou práci.
Language of thesis
Czech
Faculty
Fakulta elektrotechniky a komunikačních technologií
Department
Department of Biomedical Engineering
Study programme
Biomedical Technology and Bioinformatics (BPC-BTB)
Composition of Committee
doc. Ing. Petr Kudrna, Ph.D. (předseda) Ing. Markéta Jakubíčková, Ph.D. (místopředseda) MUDr.Ing. Richard Ředina (člen) Ing. Martin Králík (člen) Ing. Jiří Vitouš (člen) doc. Ing. Radim Kolář, Ph.D. (člen)
Supervisor’s reportMUDr.Ing. Richard Ředina
Grade proposed by supervisor: F
Reviewer’s reportIng. Jiří Chmelík, Ph.D.
Grade proposed by reviewer: F
Responsibility: Mgr. et Mgr. Hana Odstrčilová