DocumentCode :
1432365
Title :
Forecasting generalized epileptic seizures from the EEG signal by wavelet analysis and dynamic unsupervised fuzzy clustering
Author :
Geva, Amir B. ; Kerem, Dan H.
Author_Institution :
Dept. of Electr. & Comput. Eng., Ben-Gurion Univ. of the Negev, Beer-Sheva, Israel
Volume :
45
Issue :
10
fYear :
1998
Firstpage :
1205
Lastpage :
1216
Abstract :
Dynamic state recognition and event-prediction are fundamental tasks in biomedical signal processing. The authors present a new, electroencephalogram (EEG)-based, brain-state identification method which could form the basis for forecasting a generalized epileptic seizure. The method relies on the existence in the EEG of a preseizure state, with extractable unique features, a priori undefined. The authors exposed 25 rats to hyperbaric oxygen until the appearance of a generalized EEG seizure. EEG segments from the preexposure, early exposure, and the period up to and including the seizure were processed by the fast wavelet transform. Features extracted from the wavelet coefficients were inputted to the unsupervised optimal fuzzy clustering (UOFC) algorithm. The UOFC is useful for classifying similar discontinuous temporal patterns in the semistationary EEG to a set of clusters which may represent brain-states. The unsupervised selection of the number of clusters overcomes the a priori unknown and variable number of states. The usually vague brain state transitions are naturally treated by assigning each temporal pattern to one or more fuzzy clusters. The classification succeeded in identifying several, behavior-backed, EEG states such as sleep, resting, alert and active wakefulness, as well as the seizure. In 16 instances a preseizure state, lasting between 0.7 and 4 min was defined. Considerable individual variability in the number and characteristics of the clusters may postpone the realization of an early universal epilepsy warning. Universality may not be crucial if using a dynamic version of the UOFC which has been taught the individual´s normal vocabulary of EEG states and can be expected to detect unspecified new states.
Keywords :
electroencephalography; feature extraction; fuzzy logic; medical signal processing; wavelet transforms; 0.7 to 4 min; EEG segments; EEG signal; brain-states; discontinuous temporal patterns; dynamic unsupervised fuzzy clustering; early universal epilepsy warning; electrodiagnostics; fast wavelet transform; generalized EEG seizure; generalized epileptic seizures forecasting; hyperbaric oxygen; individual variability; preseizure state; semistationary EEG; unsupervised optimal fuzzy clustering algorithm; wavelet analysis; Biomedical signal processing; Clustering algorithms; Electroencephalography; Epilepsy; Feature extraction; Rats; Signal analysis; Wavelet analysis; Wavelet coefficients; Wavelet transforms; Algorithms; Animals; Cluster Analysis; Electrodes, Implanted; Electroencephalography; Epilepsy; Fuzzy Logic; Hyperbaric Oxygenation; Likelihood Functions; Rats; Signal Processing, Computer-Assisted; Sleep;
fLanguage :
English
Journal_Title :
Biomedical Engineering, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9294
Type :
jour
DOI :
10.1109/10.720198
Filename :
720198
Link To Document :
بازگشت