Laelaps: An Energy-Efficient Seizure Detection Algorithm from Long-term Human iEEG Recordings without False Alarms
Alessio Burrello1,a, Lukas Cavigelli1,b, Kaspar Schindler2, Luca Benini1,c and Abbas Rahimi1,d
1Integrated Systems Laboratory, ETH Zurich, Switzerland
abualessi@student.ethz.ch
bcavigelli@iis.ee.ethz.ch
cbenini@iis.ee.ethz.ch
dabbas@iis.ee.ethz.ch
2Sleep-Wake-Epilepsy-Center, Inselspital Bern, Switzerland
kaspar.schindler@insel.ch
ABSTRACT
We propose Laelaps, an energy-efficient and fast learning algorithm with no false alarms for epileptic seizure detection from long-term intracranial electroencephalography (iEEG) signals. Laelaps uses end-to-end binary operations by exploiting symbolic dynamics and brain-inspired hyperdimensional computing. Laelaps’s results surpass those yielded by state-of-the-art (SoA) methods [1], [2], [3], including deep learning, on a new very large dataset containing 116 seizures of 18 drug-resistant epilepsy patients in 2656 hours of recordings-each patient implanted with 24 to 128 iEEG electrodes. Laelaps trains 18 patient-specific models by using only 24 seizures: 12 models are trained with one seizure per patient, the others with two seizures. The trained models detect 79 out of 92 unseen seizures without any false alarms across all the patients as a big step forward in practical seizure detection. Importantly, a simple implementation of Laelaps on the Nvidia Tegra X2 embedded device achieves 1.7×-3.9× faster execution and 1.4×-2.9× lower energy consumption compared to the best result from the SoA methods. Our source code and anonymized iEEG dataset are freely available at http://ieeg-swez.ethz.ch.
Keywords: Hyperdimensional computing, Symbolic analysis.
