Towards Personalized Neural Networks for Epileptic Seizure Prediction
Seizure prediction for untreatable epileptic patients, one of the major challenges of present neuroinformatics researchers, will allow a substantial improvement in their safety and quality of life. Neural networks, because of their plasticity and degrees of freedom, seem to be a good approach to consider the enormous variability of physiological systems. Several architectures and training algorithms are comparatively proposed in this work showing that it is possible to find an adequate network for one patient, but care must be taken to generalize to other patients. It is claimed that each patient will have his (her) own seizure prediction algorithms.
KeywordsEpilepsy data mining seizure prediction classification neural networks
Unable to display preview. Download preview PDF.
- 1.Browne, T., Holmes, G.: Handbook of epilepsy. Lippincott Williams & Wilkins (2000)Google Scholar
- 10.Subasi: Epileptic seizure detection using dynamic wavelet network. Expert System with applications 29, 343–355 (2005)Google Scholar
- 13.Freiburger Zentrum fur Datenanalyse und mollbildung, http://www.fdm.uni-freiburg.de/groups/timeseries/epi/EEGData/download/infos.txt
- 14.Le Van Quyen, M., Amor, F., Rudrauf, D.: Exploring the dynamics of collective synchronizations in large ensembles of brain signals. J. Physiol. (in press, 2007)Google Scholar
- 15.The Mathworks, Inc.Google Scholar
- 16.Merkwirth, C., Parlitz, U., Wedekind, I., Lauterborn, W.: TSTOOL User Manual, Version 1.11, http://www.dpi.physik.uni-goettingen.de/tstool/HTML/index.html