%0 Journal Article %1 Firpi:2007:BE %A Firpi, Hiram %A Goodman, Erik D. %A Echauz, Javier %D 2007 %J IEEE Transactions on Biomedical Engineering %K algorithms, artificial classification, classifier, detection, detectors, diseases, electroencephalography, epilepsy epileptic features, genetic genetically hr, k-nearest medical neighbour patient-specific processing, programmed programming, reconstructed reconstruction730.6 seizure signal state-space trajectories %N 2 %P 212--224 %R 10.1109/TBME.2006.886936 %T Epileptic Seizure Detection Using Genetically Programmed Artificial Features %V 54 %X Patient-specific epilepsy seizure detectors were designed based on the genetic programming artificial features algorithm, a general-purpose, methodic algorithm comprised by a genetic programming module and a k-nearest neighbour classifier to create synthetic features. Artificial features are an extension to conventional features, characterised by being computer-coded and may not have a known physical meaning. In this paper, artificial features are constructed from the reconstructed state-space trajectories of the intracranial EEG signals intended to reveal patterns indicative of epileptic seizure onset. The algorithm was evaluated in seven patients and validation experiments were carried out using 730.6 hr of EEG recordings. The results with the artificial features compare favourably with previous benchmark work that used a handcrafted feature. Among other results, 88 out of 92 seizures were detected yielding a low false negative rate of 4.35percent

@article{Firpi:2007:BE, abstract = {Patient-specific epilepsy seizure detectors were designed based on the genetic programming artificial features algorithm, a general-purpose, methodic algorithm comprised by a genetic programming module and a k-nearest neighbour classifier to create synthetic features. Artificial features are an extension to conventional features, characterised by being computer-coded and may not have a known physical meaning. In this paper, artificial features are constructed from the reconstructed state-space trajectories of the intracranial EEG signals intended to reveal patterns indicative of epileptic seizure onset. The algorithm was evaluated in seven patients and validation experiments were carried out using 730.6 hr of EEG recordings. The results with the artificial features compare favourably with previous benchmark work that used a handcrafted feature. Among other results, 88 out of 92 seizures were detected yielding a low false negative rate of 4.35percent}, added-at = {2008-06-19T17:35:00.000+0200}, author = {Firpi, Hiram and Goodman, Erik D. and Echauz, Javier}, biburl = {https://www.bibsonomy.org/bibtex/285f9654fcc1e9adc1d1b335be7437d5b/brazovayeye}, doi = {10.1109/TBME.2006.886936}, interhash = {962e5e7a5190405c025ce45138c508ad}, intrahash = {85f9654fcc1e9adc1d1b335be7437d5b}, issn = {0018-9294}, journal = {IEEE Transactions on Biomedical Engineering}, keywords = {algorithms, artificial classification, classifier, detection, detectors, diseases, electroencephalography, epilepsy epileptic features, genetic genetically hr, k-nearest medical neighbour patient-specific processing, programmed programming, reconstructed reconstruction730.6 seizure signal state-space trajectories}, month = {February}, number = 2, pages = {212--224}, timestamp = {2008-06-19T17:39:38.000+0200}, title = {Epileptic Seizure Detection Using Genetically Programmed Artificial Features}, volume = 54, year = 2007 }