Cited time in webofscience Cited time in scopus

A wavelet based method for detecting and localizing epileptic neural spikes in EEG

A wavelet based method for detecting and localizing epileptic neural spikes in EEG
Abibullaev, B.Seo, H.D.Kang, W.-S.An, Jin Ung
DGIST Authors
Abibullaev, B.Kang, W.-S.An, Jin Ung
Issued Date
Article Type
Conference Paper
The recording of seizures is of primary interest in the evaluation of epileptic transients. Seizure is the phenomenon of rhythmicity discharge from either a local area or the whole brain and the individual behaviour usually lasts from seconds to minutes. Since seizures in general occur infrequently and unpredictably, an automatic detection of seizures during long-term electroencephalograph (EEG) recordings is highly recommended. As EEG signals are nonstationary, the conventional methods of frequency analysis are not successful for diagnostic purposes. This paper proposes a new method for the detection of epileptic transients in EEG by using continuous wavelet transform (CWT) with suitable mother wavelet functions and thresholding method. We demonstrate the efficiency of our method on data to identify and clearly locate in time the seizure activities. The method is superior both in separation from noise and in identifying superimposed epileptic action potentials based on in sets of combined scales. We prove that this method is fast and simple which also reduces real time computations. Copyright © 2009 ACM.
Institute of Control, Robotics and Systems
Related Researcher
  • 강원석 Kang, Won-Seok 지능형로봇연구부
  • Research Interests Data Mining & Machine Learning for Text & Multimedia; Brain-Sense-ICTConvergence Computing; Computational Olfaction Measurement; Simulation&Modeling
Files in This Item:

There are no files associated with this item.

Appears in Collections:
Convergence Research Center for Wellness 2. Conference Papers
Division of Intelligent Robotics Brain Robot Augmented InteractioN(BRAIN) Laboratory 2. Conference Papers


  • twitter
  • facebook
  • mendeley

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.