Adaptive Segmentation with Successive Windows

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F14%3A00223534" target="_blank" >RIV/68407700:21230/14:00223534 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Adaptive Segmentation with Successive Windows

Popis výsledku v původním jazyce

Segmentation is an important part of signal processing and it significantly influences on a further analysis quality. Adaptive segmentation based on sliding windows has a good performance characteristic and can work online. In the paper fractal dimension, frequency-weighted energy (nonlinear energy operator) and measure M of the Varri method were calculated as signal characteristics in a successive window and results were used as features for adaptive segmentation. Time performance and segmentation quality were compared for these algorithms. For evaluation of segmentation quality, artificial signal, signal with artefacts and normal EEG signal were used. Also a real long-term signal was tested.

Název v anglickém jazyce

Adaptive Segmentation with Successive Windows

Popis výsledku anglicky

Segmentation is an important part of signal processing and it significantly influences on a further analysis quality. Adaptive segmentation based on sliding windows has a good performance characteristic and can work online. In the paper fractal dimension, frequency-weighted energy (nonlinear energy operator) and measure M of the Varri method were calculated as signal characteristics in a successive window and results were used as features for adaptive segmentation. Time performance and segmentation quality were compared for these algorithms. For evaluation of segmentation quality, artificial signal, signal with artefacts and normal EEG signal were used. Also a real long-term signal was tested.

Druh

D - Stať ve sborníku

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2014

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of BioDat 2014 - Conference on Advanced Methods of Biological Data and Signal Processing

ISBN

978-80-01-05624-0

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

—

Název nakladatele

ČVUT

Místo vydání

Praha

Místo konání akce

Praha

Datum konání akce

20. 11. 2014

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—