Institutional Repository
Technical University of Crete
EN  |  EL



My Space

Seizure detection using common spatial patterns and classification techniques

Giannakakis Georgios, Tsekos Nikolaos, Giannakaki Aikaterini-Antonia, Michalopoulos Kostas, Vorgia Pelagia, Zervakis Michail

Simple record

Extent4 pagesen
TitleSeizure detection using common spatial patterns and classification techniquesen
CreatorGiannakakis Georgiosen
CreatorΓιαννακακης Γεωργιοςel
CreatorTsekos Nikolaosen
CreatorΤσεκος Νικολαοςel
CreatorGiannakaki Aikaterini-Antoniaen
CreatorΓιαννακακη Αικατερινη-Αντωνιαel
CreatorMichalopoulos Kostasen
CreatorVorgia Pelagiaen
CreatorZervakis Michailen
CreatorΖερβακης Μιχαηλel
PublisherInstitute of Electrical and Electronics Engineersen
Content SummaryThis paper investigates the effectiveness of Common Spatial Patterns (CSP) analysis of EEG signals on the automatic detection of focal epileptic seizures. Focal seizures are characterized by unilaterally triggered abnormal brain activity. CSP analysis has been frequently used in literature for multichannel EEG signal separation between two states. In the present study, EEG recordings from 10 subjects aged 7.7±4.4 years, including 63 seizures, were analyzed with respect to seizure detection and discrimination between interictal and ictal periods. Machine learning techniques of feature selection and classification were used in the analysis, resulting in a best achieved classification accuracy of 91.1%.en
Type of ItemΠλήρης Δημοσίευση σε Συνέδριοel
Type of ItemConference Full Paperen
Date of Item2020-04-22-
Date of Publication2019-
SubjectCommon spatial patternsen
SubjectFocal epilepsyen
SubjectSeizure detectionen
Bibliographic CitationG. Giannakakis, N. Tsekos, K. Giannakaki, K. Michalopoulos, P. Vorgia and M. Zervakis, "Seizure detection using common spatial patterns and classification techniques," in 19th International Conference on Bioinformatics and Bioengineering, 2019, pp. 890-893. doi: 10.1109/BIBE.2019.00166en