Detecting clinically relevant EEG anomalies using discrete wavelet transforms

Authors:
P. Jahankhani;K. Revett;V. Kodogiannis
Affiliations:
Mechatronics Group, School of Computer Science, University of Westminster, London, United Kingdom;Artificial Intelligent and Multimedia, School of Computer Science, University of Westminster, London, United Kingdom;Mechatronics Group, School of Computer Science, University of Westminster, London, United Kingdom
Venue:
WAMUS'05 Proceedings of the 5th WSEAS International Conference on Wavelet Analysis and Multirate Systems
Year:
2005

Citing 4
Cited 0

A Theory for Multiresolution Signal Decomposition: The Wavelet Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Ten lectures on wavelets

Ten lectures on wavelets
Application of Periodogram and AR Spectral Analysis to EEG Signals

Journal of Medical Systems
Automatic recognition of alertness level from EEG by using neural network and wavelet coefficients

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

An EEG is a recording of the electrical signals produced by activity within the brain. A variety of cognitive and pathologies yield specific EEG signatures, which are diagnostic of the condition. As a clinical EEG may contain non-stationary signals, we have employed a Daubechies wavelet to automatically detect embedded signals that vary both in their frequency and magnitude from a clinical EEG dataset. The experimental results indicate that our system is able to identify anomalous signals embedded in a standard EEG data-stream that have frequencies within the range of 0.5-30 Hz.