Show simple item record

AuthorZabihi M.
AuthorKiranyaz, Mustafa Serkan
AuthorJantti V.
AuthorLipping T.
AuthorGabbouj M.
Available date2022-04-26T12:31:20Z
Publication Date2020
Publication NameIEEE Journal of Biomedical and Health Informatics
ResourceScopus
Identifierhttp://dx.doi.org/10.1109/JBHI.2019.2906400
URIhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85079091217&doi=10.1109%2fJBHI.2019.2906400&partnerID=40&md5=c8f07cb125dddbee8e18626ac1b0098c
URIhttp://hdl.handle.net/10576/30611
AbstractNonlinear dynamics has recently been extensively used to study epilepsy due to the complex nature of the neuronal systems. This study presents a novel method that characterizes the dynamic behavior of pediatric seizure events and introduces a systematic approach to locate the nullclines on the phase space when the governing differential equations are unknown. Nullclines represent the locus of points in the solution space where the components of the velocity vectors are zero. A simulation study over 5 benchmark nonlinear systems with well-known differential equations in three-dimensional exhibits the characterization efficiency and accuracy of the proposed approach that is solely based on the reconstructed solution trajectory. Due to their unique characteristics in the nonlinear dynamics of epilepsy, discriminative features can be extracted based on the nullclines concept. Using a limited training data (only 25% of each EEG record) in order to mimic the real-world clinical practice, the proposed approach achieves 91.15% average sensitivity and 95.16% average specificity over the benchmark CHB-MIT dataset. Together with an elegant computational efficiency, the proposed approach can, therefore, be an automatic and reliable solution for patient-specific seizure detection in long EEG recordings.
Languageen
PublisherInstitute of Electrical and Electronics Engineers Inc.
SubjectComputational efficiency
Differential equations
Efficiency
Electroencephalography
Neurology
Nonlinear equations
Phase space methods
Vector spaces
Average sensitivities
Clinical practices
Discriminative features
Governing differential equations
Limited training data
nullcline
Seizure detection
Simulation studies
Dynamics
accuracy
algorithm
Article
artificial neural network
classification
conceptual framework
cross validation
dynamics
electroencephalography
event related potential
human
measurement accuracy
nerve cell network
nonlinear system
receiver operating characteristic
seizure
sensitivity and specificity
signal processing
support vector machine
training
child
pathophysiology
procedures
seizure
Algorithms
Child
Electroencephalography
Humans
Nonlinear Dynamics
Seizures
Signal Processing, Computer-Assisted
TitlePatient-Specific Seizure Detection Using Nonlinear Dynamics and Nullclines
TypeArticle
Pagination543-555
Issue Number2
Volume Number24
dc.accessType Abstract Only


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record