Seizure detection by a novel wavelet packet method. Academic Article

abstract

• We describe a novel wavelet-based method for the detection of seizure in patients with temporal lobe epilepsy. This method uses local discriminant bases and cross- data entropy algorithms to identify nodes of a wavelet packet dictionary that best discriminate preictal from ictal EEG signals. The algorithms are based on relative entropy criterion as a measure of discrepancy between different classes of signals. The frequency bands associated with these nodes were in the range of interest for seizure events. After selecting two bands, we determined the ratio of energies at the level of wavelet packet chosen by the cross-data entropy algorithm. Preliminary results demonstrate that the wavelet packet energy ratio could serve as a robust criterion in seizure detection.

authors

• Tafreshi, Reza

published proceedings

• Conf Proc IEEE Eng Med Biol Soc

author list (cited authors)

• Tafreshi, R., Dumont, G., Gross, D., Ries, C. R., Puil, E., & MacLeod, B. A.

citation count

• 9

complete list of authors

• Tafreshi, Reza||Dumont, Guy||Gross, Donald||Ries, Craig R||Puil, Ernie||MacLeod, Bern A

publication date

• August 2006

publisher

• Institute of Electrical and Electronics Engineers (IEEE)  Publisher

keywords

• Algorithms
• Artificial Intelligence
• Brain
• Data Compression
• Electroencephalography
• Epilepsy
• Fourier Analysis
• Humans
• Models, Neurological
• Neural Networks, Computer
• Pattern Recognition, Automated
• Seizures
• Signal Processing, Computer-Assisted
• Software
• User-Computer Interface

PubMed Central ID

• 17946742

Digital Object Identifier (DOI)

• 10.1109/IEMBS.2006.259363

start page

• 6141

end page

• 6144

volume

• 2006

URL

• http://dx.doi.org/10.1109/iembs.2006.259363