EEG signal as biometric characteristic and its long-term temporal stability

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F12%3A00193379" target="_blank" >RIV/68407700:21230/12:00193379 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
EEG signal as biometric characteristic and its long-term temporal stability
Original language description
This paper presents results of person identification experiments, based on individual properties of EEG signals. EEG data of each test subject were acquired in two different measurement sessions, with one year time gap between them. Main focus of these experiments was to assess long-term temporal stability of EEG biometrics. Use of EEG data from separate session leads to identification score about 98%. Results for merged EEG sessions reach in average only 78% success rate. Identification algorithm usedfor these experiments utilizes Frequency-Zooming Auto-Regression modeling and Mahalanobis distance-based classifier, several improvements for this algorithm are proposed in this paper.
Czech name
—
Czech description
—

Publication year
2012
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
POSTER 2012 - 16th International Student Conference on Electrical Engineering
ISBN
978-80-01-05043-9
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
1-4
Publisher name
Czech Technical University in Prague
Place of publication
Praha
Event location
Prague
Event date
May 17, 2012
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)