Feature Selection for Adults Sleep and Neonatal Polysomnographic Data

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F13%3A00193463" target="_blank" >RIV/68407700:21230/13:00193463 - isvavai.cz</a>
Alternative codes found
RIV/68407700:21460/13:00193463
Result on the web
<a href="http://dx.doi.org/10.1007/978-3-642-29305-4_141" target="_blank" >http://dx.doi.org/10.1007/978-3-642-29305-4_141</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-642-29305-4_141" target="_blank" >10.1007/978-3-642-29305-4_141</a>

Result language
angličtina
Original language name
Feature Selection for Adults Sleep and Neonatal Polysomnographic Data
Original language description
This paper proposes the solution to the problem of feature extraction and selection in the field of sleep polysomnographic recording of adults and neonates. The propřed approach has been verified on real clinical datasets. We have used approach based oncomputation of Mutual informatik between expert classification and computed features in preselection stage and Sequential Forward Selection (SFS) algorithm for final selection of the most significant features. The final set of features can be used for classification into the appropriate classes. Proper selection of features may significantly influence the success rate of the classification.
Czech name
—
Czech description
—

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
IFMBE Proceedings: World Congress on Medical Physics and Biomedical Engineering
ISBN
978-3-642-29304-7
ISSN
1680-0737
e-ISSN
—
Number of pages
4
Pages from-to
538-541
Publisher name
Springer
Place of publication
Heidelberg
Event location
Beijing ( Peking)
Event date
May 26, 2012
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)