Comparison of Linear and Non-linear Dimension Reduction Techniques for Automatic Apnea Detection

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21460%2F19%3A00337045" target="_blank" >RIV/68407700:21460/19:00337045 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/00023752:_____/19:43920217

Výsledek na webu

<a href="http://dx.doi.org/10.1109/EHB47216.2019.8969972" target="_blank" >http://dx.doi.org/10.1109/EHB47216.2019.8969972</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/EHB47216.2019.8969972" target="_blank" >10.1109/EHB47216.2019.8969972</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Comparison of Linear and Non-linear Dimension Reduction Techniques for Automatic Apnea Detection

Popis výsledku v původním jazyce

Oronasal thermal sensor signal recording within sleeping period was analyzed in sense of detection of respiratory events. The goal was to evaluate what extent an up to date non-linear dimension reduction technique increases performance of apnea classification compared to classifications based on linear dimension reduction and raw data. Based on an extensive database of recordings in apneic patients, we concluded thatn a non-linear approach didn't lead to better classification performance in comparison with a linear decomposition technique. We suggested, that it was due to the signal amplitude is naturally the main feature of respiratory events. However, nonlinear methods do not naturally maintain the amplitude based structure in data. Due to this fact we get the worse signal representation in comparison with linear methods.

Název v anglickém jazyce

Comparison of Linear and Non-linear Dimension Reduction Techniques for Automatic Apnea Detection

Popis výsledku anglicky

Oronasal thermal sensor signal recording within sleeping period was analyzed in sense of detection of respiratory events. The goal was to evaluate what extent an up to date non-linear dimension reduction technique increases performance of apnea classification compared to classifications based on linear dimension reduction and raw data. Based on an extensive database of recordings in apneic patients, we concluded thatn a non-linear approach didn't lead to better classification performance in comparison with a linear decomposition technique. We suggested, that it was due to the signal amplitude is naturally the main feature of respiratory events. However, nonlinear methods do not naturally maintain the amplitude based structure in data. Due to this fact we get the worse signal representation in comparison with linear methods.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20601 - Medical engineering

Projekt

<a href="/cs/project/GA17-20480S" target="_blank" >GA17-20480S: Časový kontext v úloze analýzy dlouhodobého nestacionárního vícerozměrného signálu</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

IEEE E-HEALTH AND BIOENGINEERING EHB 2019

ISBN

978-1-7281-2603-6

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

—

Název nakladatele

Gr. T. Popa University of Medicine and Pharmacy

Místo vydání

Iasi

Místo konání akce

Iasi

Datum konání akce

21. 11. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000558648300104