Přístupnostní navigace
E-application
Search Search Close
Bachelor's Thesis
Author of thesis: Bc. Eva Víšková
Acad. year: 2025/2026
Supervisor: Ing. Enikö Vargová
Reviewer: Ing. Lukáš Smital, Ph.D.
The primary objective of this thesis is to develop an algorithm capable of distinguishing between sinus rhythm, atrial fibrillation, and other arrhythmias (premature ventricular contractions, premature atrial contractions, ventricular tachycardia, and supraventricular tachycardia) using photoplethysmographic (PPG) signals. The theoretical part of this bachelor’s thesis presents a literature review focused on the detection and classification of these arrhythmias in PPG signals, including current approaches and methods proposed by other authors. In the practical implementation, an algorithm for systolic peak detection in PPG signals was developed. The detector employs the principle of zero-crossing points and achieves an accuracy of 97.23% for sinus rhythm signals and 87.79% for atrial fibrillation. The performance is also compared with other available systolic peak detectors, and the one with the highest accuracy is used to detect peaks for feature extraction. A total of 29 features suitable for distinguishing the aforementioned classes are extracted and preprocessed for classification models. Among several developed machine learning models, the Random Forest classifier reaches the best performance (accuracy = 84.35%). Finally, the results are discussed and compared with those of other authors.
Photoplethysmography, PPG, cardiac arrhythmias, machine learning, classification, systolic peak detection, feature extraction
Date of defence
16.06.2026
Result of the defence
Defended (thesis was successfully defended)
Grading
A
Process of defence
Student prezentoval výsledky své práce a komise byla seznámena s posudky. Ing. Smital položil otázku, zda při odstraňování odlehlých hodnot nedochází také k odstranění fyziologicky reálných hodnot souvisejících s arytmiemi a jaký podíl detekovaných chyb tvořily skutečné chyby měření. Ing. Harabiš položil otázku, zda databáze obsahovala pouze pacienty se srdečním onemocněním. Student obhájil bakalářskou práci a odpověděl na otázky členů komise a oponenta.
Language of thesis
English
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. Zuzana Nováková, Ph.D. (člen) Ing. Lukáš Smital, Ph.D. (člen) Ing. Vratislav Harabiš, Ph.D. (člen) Ing. Larisa Chmelíková, Ph.D. (člen)
Supervisor’s reportIng. Enikö Vargová
Grade proposed by supervisor: A
Reviewer’s reportIng. Lukáš Smital, Ph.D.
Grade proposed by reviewer: A
Responsibility: Mgr. et Mgr. Hana Odstrčilová