On the Selection of Time-Frequency Features for Improving the Detection and Classification of Newborn EEG Seizure Signals and Other Abnormalities

This paper presents new time-frequency features for seizure detection in newborn EEG signals. These features are obtained by translating some relevant time features or frequency features to the joint time-frequency domain. A calibration procedure is then used for verification. The relevant translated features are ranked and selected according to maximal-relevance and minimal-redundancy criteria. The selected features improve the performance of newborn EEG seizure detection and classification systems by up to 4% for 100 real newborn EEG segments.

[1]  Boualem Boashash,et al.  Time-frequency signal and image processing of non-stationary signals with application to the classification of newborn EEG abnormalities , 2011, 2011 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).

[2]  R. Grebe,et al.  Automated neonatal seizure detection: A multistage classification system through feature selection based on relevance and redundancy analysis , 2006, Clinical Neurophysiology.

[3]  G. Lightbody,et al.  A comparison of quantitative EEG features for neonatal seizure detection , 2008, Clinical Neurophysiology.

[4]  Boualem Boashash,et al.  Time-Frequency Distributions Based on Compact Support Kernels: Properties and Performance Evaluation , 2012, IEEE Transactions on Signal Processing.

[5]  J. Skilling,et al.  Algorithms and Applications , 1985 .

[6]  Boualem Boashash,et al.  A methodology for time-frequency image processing applied to the classification of non-stationary multichannel signals using instantaneous frequency descriptors with application to newborn EEG signals , 2012, EURASIP J. Adv. Signal Process..

[7]  Boualem Boashash,et al.  Estimating and interpreting the instantaneous frequency of a signal. I. Fundamentals , 1992, Proc. IEEE.

[8]  Boualem Boashash,et al.  Calibration of time features and frequency features in the time-frequency domain for improved detection and classification of seizure in newborn EEG signals , 2012, 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA).

[9]  Abdulhamit Subasi,et al.  EEG signal classification using wavelet feature extraction and a mixture of expert model , 2007, Expert Syst. Appl..

[10]  Boualem Boashash,et al.  Improving the classification of newborn EEG time-frequency representations using a combined time-frequency signal and image approach , 2012, 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA).

[11]  A. Flisberg,et al.  Automatic classification of background EEG activity in healthy and sick neonates , 2010, Journal of neural engineering.

[12]  Boualem Boashash,et al.  Estimating and interpreting the instantaneous frequency of a signal. II. A/lgorithms and applications , 1992, Proc. IEEE.

[13]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  J. Frost,et al.  A Multistage System for the Automated Detection of Epileptic Seizures in Neonatal Electroencephalography , 2009, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.