Seizure detection by a novel wavelet packet method

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

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.

Original languageEnglish
Title of host publication28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06
Pages6141-6144
Number of pages4
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06 - New York, NY, United States
Duration: 30 Aug 20063 Sep 2006

Other

Other28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06
CountryUnited States
CityNew York, NY
Period30/8/063/9/06

Fingerprint

Entropy
Seizures
Temporal Lobe Epilepsy
Glossaries
Electroencephalography
Frequency bands
Stroke

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Tafreshi, R., Dumont, G., Gross, D., Ries, C. R., Puil, E., & MacLeod, B. A. (2006). Seizure detection by a novel wavelet packet method. In 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06 (pp. 6141-6144). [4029931] https://doi.org/10.1109/IEMBS.2006.259363

Seizure detection by a novel wavelet packet method. / Tafreshi, Reza; Dumont, Guy; Gross, Donald; Ries, Craig R.; Puil, Ernie; MacLeod, Bern A.

28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06. 2006. p. 6141-6144 4029931.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tafreshi, R, Dumont, G, Gross, D, Ries, CR, Puil, E & MacLeod, BA 2006, Seizure detection by a novel wavelet packet method. in 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06., 4029931, pp. 6141-6144, 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06, New York, NY, United States, 30/8/06. https://doi.org/10.1109/IEMBS.2006.259363
Tafreshi R, Dumont G, Gross D, Ries CR, Puil E, MacLeod BA. Seizure detection by a novel wavelet packet method. In 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06. 2006. p. 6141-6144. 4029931 https://doi.org/10.1109/IEMBS.2006.259363
Tafreshi, Reza ; Dumont, Guy ; Gross, Donald ; Ries, Craig R. ; Puil, Ernie ; MacLeod, Bern A. / Seizure detection by a novel wavelet packet method. 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06. 2006. pp. 6141-6144
@inproceedings{b04efade0d4347858685a2ae55f2952d,
title = "Seizure detection by a novel wavelet packet method",
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.",
author = "Reza Tafreshi and Guy Dumont and Donald Gross and Ries, {Craig R.} and Ernie Puil and MacLeod, {Bern A.}",
year = "2006",
doi = "10.1109/IEMBS.2006.259363",
language = "English",
isbn = "1424400325",
pages = "6141--6144",
booktitle = "28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06",

}

TY - GEN

T1 - Seizure detection by a novel wavelet packet method

AU - Tafreshi, Reza

AU - Dumont, Guy

AU - Gross, Donald

AU - Ries, Craig R.

AU - Puil, Ernie

AU - MacLeod, Bern A.

PY - 2006

Y1 - 2006

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=34047182666&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34047182666&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2006.259363

DO - 10.1109/IEMBS.2006.259363

M3 - Conference contribution

SN - 1424400325

SN - 9781424400324

SP - 6141

EP - 6144

BT - 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06

ER -