Time-frequency signal and image processing of non-stationary signals with application to the classification of newborn EEG abnormalities

QSpace/Manakin Repository

Time-frequency signal and image processing of non-stationary signals with application to the classification of newborn EEG abnormalities

Show simple item record


dc.contributor.author Boashash, B
dc.contributor.author Boubchir, L
dc.contributor.author Azemi, G
dc.date.accessioned 2012-03-21T05:46:01Z
dc.date.available 2012-03-21T05:46:01Z
dc.date.issued 2011-12
dc.identifier.citation Signal Processing and Information Technology (ISSPIT), 2011 IEEE International Symposium on Issue Date : 14-17 Dec. 2011 On page(s): 120 - 129 en_US
dc.identifier.isbn 978-1-4673-0752-9
dc.identifier.other Digital Object Identifier : 10.1109/ISSPIT.2011.6151545
dc.identifier.uri http://hdl.handle.net/10576/10808
dc.description This paper demonstrates that it is possible to improve the classification of EEG non-stationary signals by using new T-F features based on image processing techniques. (Additional details can be found in the comprehensive book on Time-Frequency Signal Analysis and Processing (see http://www.elsevier.com/locate/isbn/0080443354). In addition, the most recent upgrade of the original software package that calculates Time-Frequency Distributions and Instantaneous Frequency estimators can be downloaded from the web site: www.time-frequency.net. This was the first software developed in the field, and it was first released publicly in 1987 at the 1st ISSPA conference held in Brisbane, Australia, and then continuously updated). en_US
dc.description.abstract This paper presents an introduction to time-frequency (T-F) methods in signal processing, and a novel approach for EEG abnormalities detection and classification based on a combination of signal related features and image related features. These features which characterize the non-stationary nature and the multi-component characteristic of EEG signals, are extracted from the T-F representation of the signals. The signal related features are derived from the T-F representation of EEG signals and include the instantaneous frequency, singular value decomposition, and energy based features. The image related features are extracted from the T-F representation considered as an image, using T-F image processing techniques. These combined signal and image features allow to extract more information from a signal. The results obtained on newborn and adult EEG data, show that the image related features improve the performance of the EEG seizure detection in classification systems based on multi-SVM classifier. en_US
dc.language.iso en en_US
dc.publisher IEEE en_US
dc.subject EEG Classification en_US
dc.subject EEG Time-Frequency Analysis en_US
dc.subject Instantaneous Frequency en_US
dc.subject Newborn EEG en_US
dc.subject Seizure en_US
dc.subject Time-Frequency Features en_US
dc.subject Time-Frequency Image Processing en_US
dc.subject time-frequency analysis en_US
dc.subject time-frequency images en_US
dc.subject time-frequency distributions en_US
dc.subject time-frequency detection en_US
dc.subject time-frequency classification en_US
dc.subject multicomponent EEG en_US
dc.subject multichannel EEG en_US
dc.subject Quadratic TFDs en_US
dc.subject MBD en_US
dc.subject Modified B distribution en_US
dc.subject IF model fitting en_US
dc.subject IF classification en_US
dc.subject time-frequency matched filter en_US
dc.subject EEG abnormality en_US
dc.title Time-frequency signal and image processing of non-stationary signals with application to the classification of newborn EEG abnormalities en_US
dc.type Article en_US

Files in this item

Files Size Format View
Boashash-Boubch ... ing-newborn-EEG-abnorm.pdf 3.261Mb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

Search QSpace


Advanced Search

Browse

My Account