Active Learning for Semiautomatic Sleep Staging and Transitional EEG Segments

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F18%3A00328067" target="_blank" >RIV/68407700:21230/18:00328067 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21460/18:00328067 RIV/68407700:21730/18:00328067

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/8621339" target="_blank" >https://ieeexplore.ieee.org/document/8621339</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/BIBM.2018.8621339" target="_blank" >10.1109/BIBM.2018.8621339</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Active Learning for Semiautomatic Sleep Staging and Transitional EEG Segments

Popis výsledku v původním jazyce

Semiautomatic sleep staging system based on EEG classification is focused in the paper. Such an expert-in-the-loop system interacts with the annotating expert by suggesting him EEG segments that should be annotated. After a sufficient number of labeled segments is reached, a pattern classification model is trained and used for automatic annotation of the rest of the signal. It is shown that this can save 85% of the labeling effort and consequently improve the annotation quality due to the prevention of errors caused by expert’s fatigue. The selection of the data for labeling is based on confidence based active learning approach. It is shown that such a strategy is statistically significantly better in terms of mean class error than baseline random sampling strategy. Moreover, it is argued that transitional instances that correspond to transitions between sleep stages are often erroneously labeled and their elimination can improve especially the active learning process. This hypothesis is examined and surprisingly such elimination significantly improved the random sampling strategy which became comparable to the active learning without removal of transitions. Although the active learning strategy with transitions removal performed better in terms of mean, there were not sufficient data that would prove this statistically.

Název v anglickém jazyce

Active Learning for Semiautomatic Sleep Staging and Transitional EEG Segments

Popis výsledku anglicky

Semiautomatic sleep staging system based on EEG classification is focused in the paper. Such an expert-in-the-loop system interacts with the annotating expert by suggesting him EEG segments that should be annotated. After a sufficient number of labeled segments is reached, a pattern classification model is trained and used for automatic annotation of the rest of the signal. It is shown that this can save 85% of the labeling effort and consequently improve the annotation quality due to the prevention of errors caused by expert’s fatigue. The selection of the data for labeling is based on confidence based active learning approach. It is shown that such a strategy is statistically significantly better in terms of mean class error than baseline random sampling strategy. Moreover, it is argued that transitional instances that correspond to transitions between sleep stages are often erroneously labeled and their elimination can improve especially the active learning process. This hypothesis is examined and surprisingly such elimination significantly improved the random sampling strategy which became comparable to the active learning without removal of transitions. Although the active learning strategy with transitions removal performed better in terms of mean, there were not sufficient data that would prove this statistically.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

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

2018

Kód důvěrnosti údajů

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

Název statě ve sborníku

2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) - Proceedings

ISBN

978-1-5386-5488-0

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

2621-2627

Název nakladatele

IEEE

Místo vydání

—

Místo konání akce

Madrid

Datum konání akce

3. 12. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000458654000449