Bispectrum and Recurrent Neural Networks: Improved Classification of Interictal and Preictal States
Authors:
Open Access
- 30 October 2019
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 9 (1) , 1-9
Abstract
This work proposes a novel approach for the classification of interictal and preictal brain states based on bispectrum analysis and recurrent Long Short-Term Memory (LSTM) neural networks. Two features were first extracted from bilateral intracranial electroencephalography (iEEG) recordings of dogs with naturally occurring focal epilepsy. Single-layer LSTM networks were trained to classify 5-min long feature vectors as preictal or interictal. Classification performances were compared to previous work involving multilayer perceptron networks and higher-order spectral (HOS) features on the same dataset. The proposed LSTM network proved superior to the multilayer perceptron network and achieved an average classification accuracy of 86.29% on held-out data. Results imply the possibility of forecasting epileptic seizures using recurrent neural networks, with minimal feature extraction.Keywords
Funding Information
- Institute for Data Valorization
This publication has 28 references indexed in Scilit:
- Physiology of functional and effective networks in epilepsyClinical Neurophysiology, 2015
- Network dynamics of the brain and influence of the epileptic seizure onset zoneProceedings of the National Academy of Sciences, 2014
- Functional brain connectivity from EEG in epilepsy: Seizure prediction and epileptogenic focus localizationProgress in Neurobiology, 2014
- Slow modulations of high-frequency activity (40–140 Hz) discriminate preictal changes in human focal epilepsyScientific Reports, 2014
- Forecasting Seizures in Dogs with Naturally Occurring EpilepsyPLOS ONE, 2014
- Prediction of seizure likelihood with a long-term, implanted seizure advisory system in patients with drug-resistant epilepsy: a first-in-man studyThe Lancet Neurology, 2013
- Cross-frequency coupling in real and virtual brain networksFrontiers in Computational Neuroscience, 2013
- Quickest detection of drug-resistant seizures: An optimal control approachEpilepsy & Behavior, 2011
- A novel implanted device to wirelessly record and analyze continuous intracranial canine EEGEpilepsy Research, 2011
- Seizure prediction: the long and winding roadBrain, 2006