A collaborative filtering approach for quasi-brain-death EEG analysis

Xia, Yili, Li, Ling, Cao, Jianting, Golz, M., Mandic, Danilo P. (2011) A collaborative filtering approach for quasi-brain-death EEG analysis. In: Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on. . pp. 182-196. IEEE Press ISBN 978-1-4577-0538-0. (doi:10.1109/ICASSP.2011.5946486) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. (Contact us about this Publication)
Official URL
http://dx.doi.org/10.1109/ICASSP.2011.5946486

Abstract

Evaluating the significance differences between the group of comatose patients and the group of brain death is important in the detection of brain death. This paper presents a novel method for the discrimination between discrete states of brain consciousness. Based on a collaborative adaptive filtering ar- chitecture using a convex combination of two heterogeneous adaptive filters, the evolution of the mixing parameter can be used as an indicator of the fundamental signal nature of different EEG recordings. Simulations illustrate the suitabil- ity of this approach to differentiate between the coma and quasi-brain-death states.

Item Type: Conference or workshop item (Paper)
DOI/Identification number: 10.1109/ICASSP.2011.5946486
Uncontrolled keywords: determinacy analysis, Craig interpolants
Subjects: Q Science
Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming,
R Medicine
Divisions: Faculties > Sciences > School of Computing > Computational Intelligence Group
Faculties > Sciences > School of Computing > Data Science
Depositing User: Caroline Li
Date Deposited: 21 Sep 2012 09:49 UTC
Last Modified: 29 May 2019 09:20 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/30759 (The current URI for this page, for reference purposes)
  • Depositors only (login required):