Detekce a klasifikace artefaktů v PPG signálu
Loading...
Date
Authors
Sujová, Hana
Advisor
Referee
Mark
A
Journal Title
Journal ISSN
Volume Title
Publisher
Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií
ORCID
Abstract
Práca sa zameriava na problematiku detekcie a klasifikácie artefaktov v PPG signáloch. Fotopletyzmografia (PPG) predstavuje rozšírenú metódu na meranie zmien krvného objemu, no jej presnosť často narúšajú rôzne artefakty spôsobené pohybom, kontaktnou silou alebo ambientným svetlom. Cieľom práce je analyzovať vplyv týchto artefaktov na morfológiu signálu. Analýza zahŕňa využitie signálov nameraných pomocou kamery smartfónu. Teoretická časť popisuje charakteristiky PPG signálu, jeho praktické využitie, typy artefaktov a ich zdroje, ako aj dostupné databázy a aplikácie. V praktickej časti bolo realizované meranie signálov podľa stanoveného protokolu a namerané signály boli vizuálne analyzované. Dataset bol rozšírený o ďalšie záznamy z databázy BUT PPG a zo signálov boli vypočítané príznaky. Boli vybrané nainfomatívnejšie príznaky, ktoré boli vstupom pre rôzne klasifikačné algoritmy.
This work focuses on the problem of detecting and classifying artifacts in PPG signals. Photoplethysmography (PPG) is a widely used method for measuring changes in blood volume, but its accuracy is often compromised by various artifacts caused by motion, contact force, and ambient light. The aim of this study is to analyze the impact of these artifacts on the signal's morphology. The analysis involves signals recorded using a smartphone camera. The theoretical part outlines the characteristics of the PPG signal, its practical applications, types of artifacts and their sources, as well as available databases and applications. In the practical part, the signals were measured according to the established protocol and the were visually analyzed. The dataset was extended with additional records from the BUT PPG database and features were extracted from the signals. The most infomative features were selected and formed the input for various classification algorithms.
This work focuses on the problem of detecting and classifying artifacts in PPG signals. Photoplethysmography (PPG) is a widely used method for measuring changes in blood volume, but its accuracy is often compromised by various artifacts caused by motion, contact force, and ambient light. The aim of this study is to analyze the impact of these artifacts on the signal's morphology. The analysis involves signals recorded using a smartphone camera. The theoretical part outlines the characteristics of the PPG signal, its practical applications, types of artifacts and their sources, as well as available databases and applications. In the practical part, the signals were measured according to the established protocol and the were visually analyzed. The dataset was extended with additional records from the BUT PPG database and features were extracted from the signals. The most infomative features were selected and formed the input for various classification algorithms.
Description
Keywords
Citation
SUJOVÁ, H. Detekce a klasifikace artefaktů v PPG signálu [online]. Brno: Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. 2025.
Document type
Document version
Date of access to the full text
Language of document
sk
Study field
bez specializace
Comittee
doc. Ing. Jiří Hozman, Ph.D. (předseda)
Ing. Andrea Němcová, Ph.D. (místopředseda)
Ing. Oto Janoušek, Ph.D. (člen)
Ing. Vojtěch Bartoň (člen)
Ing. Martin Lamoš, Ph.D. (člen)
MUDr. Michal Jurajda, Ph.D. (člen)
Date of acceptance
2025-06-17
Defence
Studentka prezentovala výsledky své práce a komise byla seznámena s posudky. Ing. Lamoš položil otázku: Proč je tak vysoké množství odlehlých hodnot v boxplotech? MUDr. Jurajda položil otázku: jak jsou konstruované prezentované boxploty? Studentka obhájila bakalářskou práci a odpověděla na otázky členů komise a oponenta.
Result of defence
práce byla úspěšně obhájena
