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

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