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

Show simple item record

Author Boashash, B en_US
Author Boubchir, L en_US
Author Azemi, G en_US
Available date 2012-03-21T05:46:01Z en_US
Publication Date 2011-12 en_US
Citation Boashash, B.; Boubchir, L.; Azemi, G., "Time-frequency signal and image processing of non-stationary signals with application to the classification of newborn EEG abnormalities," Signal Processing and Information Technology (ISSPIT), 2011 IEEE International Symposium on , vol., no., pp.120,129, 14-17 Dec. 2011 en_US
ISBN 978-1-4673-0752-9 en_US
URI http://hdl.handle.net/10576/10808 en_US
URI http://dx.doi.org/10.1109/ISSPIT.2011.6151545
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
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
Language en en_US
Publisher IEEE en_US
Subject EEG Classification en_US
Subject EEG Time-Frequency Analysis en_US
Subject Instantaneous Frequency en_US
Subject Newborn EEG en_US
Subject Seizure en_US
Subject Time-Frequency Features en_US
Subject Time-Frequency Image Processing en_US
Subject time-frequency analysis en_US
Subject time-frequency images en_US
Subject time-frequency distributions en_US
Subject time-frequency detection en_US
Subject time-frequency classification en_US
Subject multicomponent EEG en_US
Subject multichannel EEG en_US
Subject Quadratic TFDs en_US
Subject MBD en_US
Subject Modified B distribution en_US
Subject IF model fitting en_US
Subject IF classification en_US
Subject time-frequency matched filter en_US
Subject EEG abnormality en_US
Title Time-frequency signal and image processing of non-stationary signals with application to the classification of newborn EEG abnormalities en_US
Type Conference Paper en_US


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record