Detection of epileptiform activity in EEG signals based on time-frequency and nonlinear analysis
We present a new technique for detection of epileptiform activity in EEG signals. After preprocessing of EEG signals we extract representative features in time, frequency and time-frequency domain as well as using nonlinear analysis. The features are extracted in a few frequency sub-bands of clinica...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2015-03-01
|
Series: | Frontiers in Computational Neuroscience |
Subjects: | |
Online Access: | http://journal.frontiersin.org/Journal/10.3389/fncom.2015.00038/full |
_version_ | 1811232530311938048 |
---|---|
author | Dragoljub eGajic Dragoljub eGajic Jovan eGligorijevic Zeljko eDjurovic Stefano eDi Gennaro Ivana eSavic-Gajic |
author_facet | Dragoljub eGajic Dragoljub eGajic Jovan eGligorijevic Zeljko eDjurovic Stefano eDi Gennaro Ivana eSavic-Gajic |
author_sort | Dragoljub eGajic |
collection | DOAJ |
description | We present a new technique for detection of epileptiform activity in EEG signals. After preprocessing of EEG signals we extract representative features in time, frequency and time-frequency domain as well as using nonlinear analysis. The features are extracted in a few frequency sub-bands of clinical interest since these sub-bands showed much better discriminatory characteristics compared with the whole frequency band. Then we optimally reduce the dimension of feature space to two using scatter matrices. A decision about the presence of epileptiform activity in EEG signals is made by quadratic classifiers designed in the reduced two-dimensional feature space. The accuracy of the technique was tested on three sets of electroencephalographic (EEG) signals recorded at the University Hospital Bonn: surface EEG signals from healthy volunteers, intracranial EEG signals from the epilepsy patients during the seizure free interval from within the seizure focus and intracranial EEG signals of epileptic seizures also from within the seizure focus. An overall detection accuracy of 98.7% was achieved. |
first_indexed | 2024-04-12T11:04:26Z |
format | Article |
id | doaj.art-5c53764fada8452c9296a46e2041f83e |
institution | Directory Open Access Journal |
issn | 1662-5188 |
language | English |
last_indexed | 2024-04-12T11:04:26Z |
publishDate | 2015-03-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Computational Neuroscience |
spelling | doaj.art-5c53764fada8452c9296a46e2041f83e2022-12-22T03:35:50ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882015-03-01910.3389/fncom.2015.00038123938Detection of epileptiform activity in EEG signals based on time-frequency and nonlinear analysisDragoljub eGajic0Dragoljub eGajic1Jovan eGligorijevic2Zeljko eDjurovic3Stefano eDi Gennaro4Ivana eSavic-Gajic5School of Electrical Engineering, University of BelgradeCenter of Excellence DEWS, University of L'AquilaFaculty of Engineering, University of KragujevacSchool of Electrical Engineering, University of BelgradeCenter of Excellence DEWS, University of L'AquilaFaculty of Technology, University of NisWe present a new technique for detection of epileptiform activity in EEG signals. After preprocessing of EEG signals we extract representative features in time, frequency and time-frequency domain as well as using nonlinear analysis. The features are extracted in a few frequency sub-bands of clinical interest since these sub-bands showed much better discriminatory characteristics compared with the whole frequency band. Then we optimally reduce the dimension of feature space to two using scatter matrices. A decision about the presence of epileptiform activity in EEG signals is made by quadratic classifiers designed in the reduced two-dimensional feature space. The accuracy of the technique was tested on three sets of electroencephalographic (EEG) signals recorded at the University Hospital Bonn: surface EEG signals from healthy volunteers, intracranial EEG signals from the epilepsy patients during the seizure free interval from within the seizure focus and intracranial EEG signals of epileptic seizures also from within the seizure focus. An overall detection accuracy of 98.7% was achieved.http://journal.frontiersin.org/Journal/10.3389/fncom.2015.00038/fullEpileptiform activityNonLinear AnalysisSeizure detectionQuadratic classifiersScatter matrices |
spellingShingle | Dragoljub eGajic Dragoljub eGajic Jovan eGligorijevic Zeljko eDjurovic Stefano eDi Gennaro Ivana eSavic-Gajic Detection of epileptiform activity in EEG signals based on time-frequency and nonlinear analysis Frontiers in Computational Neuroscience Epileptiform activity NonLinear Analysis Seizure detection Quadratic classifiers Scatter matrices |
title | Detection of epileptiform activity in EEG signals based on time-frequency and nonlinear analysis |
title_full | Detection of epileptiform activity in EEG signals based on time-frequency and nonlinear analysis |
title_fullStr | Detection of epileptiform activity in EEG signals based on time-frequency and nonlinear analysis |
title_full_unstemmed | Detection of epileptiform activity in EEG signals based on time-frequency and nonlinear analysis |
title_short | Detection of epileptiform activity in EEG signals based on time-frequency and nonlinear analysis |
title_sort | detection of epileptiform activity in eeg signals based on time frequency and nonlinear analysis |
topic | Epileptiform activity NonLinear Analysis Seizure detection Quadratic classifiers Scatter matrices |
url | http://journal.frontiersin.org/Journal/10.3389/fncom.2015.00038/full |
work_keys_str_mv | AT dragoljubegajic detectionofepileptiformactivityineegsignalsbasedontimefrequencyandnonlinearanalysis AT dragoljubegajic detectionofepileptiformactivityineegsignalsbasedontimefrequencyandnonlinearanalysis AT jovanegligorijevic detectionofepileptiformactivityineegsignalsbasedontimefrequencyandnonlinearanalysis AT zeljkoedjurovic detectionofepileptiformactivityineegsignalsbasedontimefrequencyandnonlinearanalysis AT stefanoedigennaro detectionofepileptiformactivityineegsignalsbasedontimefrequencyandnonlinearanalysis AT ivanaesavicgajic detectionofepileptiformactivityineegsignalsbasedontimefrequencyandnonlinearanalysis |