Simulation, Modification and Dimension Reduction of EEG Feature Space
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21460%2F19%3A00321936" target="_blank" >RIV/68407700:21460/19:00321936 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/978-981-10-9038-7_80" target="_blank" >http://dx.doi.org/10.1007/978-981-10-9038-7_80</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-981-10-9038-7_80" target="_blank" >10.1007/978-981-10-9038-7_80</a>
Alternative languages
Result language
angličtina
Original language name
Simulation, Modification and Dimension Reduction of EEG Feature Space
Original language description
An automated classification of EEG time segments is frequently used technique across many neuro-scientific fields. Generally, segment classification results in labeled EEG time segments (e.g. physiological brain activity, epileptic activity, muscle artifacts or electrode artifacts). However, currently used methods are usually tested on artificial surrogate data and more general validation approach is needed. Here, a generalized statistical model of commonly used discriminating features obtained from real EEG data is presented for the first time. Multivariate probability density functions (PDFs) of classes are fitted on more than twenty thousand of testing segments from human EEG. An unique testing set is designed using a recent non-linear dimension reduction technique. Parametric and non-parametric PDF estimators are applied and compared in sense of feature space model.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20601 - Medical engineering
Result continuities
Project
<a href="/en/project/GA17-20480S" target="_blank" >GA17-20480S: Temporal context in analysis of long-term non-stationary multidimensional signal</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
World Congress on Medical Physics and Biomedical Engineering 2018
ISBN
978-981-10-9038-7
ISSN
—
e-ISSN
1680-0737
Number of pages
5
Pages from-to
425-429
Publisher name
Springer Nature Singapore Pte Ltd.
Place of publication
—
Event location
Prague
Event date
Jun 3, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000449742700080