A general-purpose, systematic algorithm is presented,
consisting of a genetic programming module and a
k-nearest neighbour classifier to automatically create
artificial features computer-crafted features possibly
without a known physical meaning directly from the
reconstructed state-space trajectory of intracranial
EEG signals that reveal predictive patterns of
epileptic seizures. The algorithm was evaluated with
IEEG data from seven patients, with prediction defined
over a horizon of 1-5 min before unequivocal
electrographic onset. A total of 59 baseline epochs
(nonseizures) and 55 preictal epochs (preseizures) were
used for validation purposes. Among the results, it is
shown that 12 seizures out of 55 were missed while four
baseline epochs were misclassified, yielding 79per cent
sensitivity and 93per cent specificity.
%0 Journal Article
%1 FGE:OPE:06
%A Firpi, Hiram
%A Goodman, Erik
%A Echauz, Javier
%D 2006
%J Annals of Biomedical Engineering
%K Artificial Epilepsy, Feature Seizure State-space algorithms, extraction, feature, genetic prediction, programming, reconstruction
%N 3
%P 515--529
%R doi:10.1007/s10439-005-9039-7
%T On Prediction of Epileptic Seizures by Means of
Genetic Programming Artificial Features
%V 34
%X A general-purpose, systematic algorithm is presented,
consisting of a genetic programming module and a
k-nearest neighbour classifier to automatically create
artificial features computer-crafted features possibly
without a known physical meaning directly from the
reconstructed state-space trajectory of intracranial
EEG signals that reveal predictive patterns of
epileptic seizures. The algorithm was evaluated with
IEEG data from seven patients, with prediction defined
over a horizon of 1-5 min before unequivocal
electrographic onset. A total of 59 baseline epochs
(nonseizures) and 55 preictal epochs (preseizures) were
used for validation purposes. Among the results, it is
shown that 12 seizures out of 55 were missed while four
baseline epochs were misclassified, yielding 79per cent
sensitivity and 93per cent specificity.
@article{FGE:OPE:06,
abstract = {A general-purpose, systematic algorithm is presented,
consisting of a genetic programming module and a
k-nearest neighbour classifier to automatically create
artificial features computer-crafted features possibly
without a known physical meaning directly from the
reconstructed state-space trajectory of intracranial
EEG signals that reveal predictive patterns of
epileptic seizures. The algorithm was evaluated with
IEEG data from seven patients, with prediction defined
over a horizon of 1-5 min before unequivocal
electrographic onset. A total of 59 baseline epochs
(nonseizures) and 55 preictal epochs (preseizures) were
used for validation purposes. Among the results, it is
shown that 12 seizures out of 55 were missed while four
baseline epochs were misclassified, yielding 79per cent
sensitivity and 93per cent specificity.},
added-at = {2008-06-19T17:35:00.000+0200},
author = {Firpi, Hiram and Goodman, Erik and Echauz, Javier},
biburl = {https://www.bibsonomy.org/bibtex/2c630abe32f18412e74d5ac9b27954b9e/brazovayeye},
doi = {doi:10.1007/s10439-005-9039-7},
interhash = {74b9f95ad9175e2dc20b8d90d966dec1},
intrahash = {c630abe32f18412e74d5ac9b27954b9e},
journal = {Annals of Biomedical Engineering},
keywords = {Artificial Epilepsy, Feature Seizure State-space algorithms, extraction, feature, genetic prediction, programming, reconstruction},
month = {March},
number = 3,
pages = {515--529},
timestamp = {2008-06-19T17:39:38.000+0200},
title = {On Prediction of Epileptic Seizures by Means of
Genetic Programming Artificial Features},
volume = 34,
year = 2006
}