Back to Search
Start Over
Laelaps: An Energy-Efficient Seizure Detection Algorithm from Long-term Human iEEG Recordings without False Alarms
- Source :
- Proceedings of the 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE), DATE
- Publication Year :
- 2019
- Publisher :
- IEEE, 2019.
-
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 1.7X–3.9X faster execution and 1.4X–2.9X 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.<br />Proceedings of the 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE)<br />ISBN:978-3-9819263-2-3<br />ISBN:978-3-9819263-3-0<br />ISBN:978-1-7281-0331-0
- Subjects :
- Computer science
Feature extraction
02 engineering and technology
Electroencephalography
01 natural sciences
Intracranial Electroencephalography
Epilepsy
Intracranial electroencephalography
0103 physical sciences
Machine learning
symbolic analysis
0202 electrical engineering, electronic engineering, information engineering
medicine
Laelaps
610 Medicine & health
010302 applied physics
Hyperdimensional computing
medicine.diagnostic_test
biology
business.industry
Deep learning
medicine.disease
biology.organism_classification
Symbolic analysis
Seizure detection
020202 computer hardware & architecture
Artificial intelligence
Epileptic seizure
medicine.symptom
business
Algorithm
Subjects
Details
- Language :
- English
- ISBN :
- 978-3-9819263-2-3
978-3-9819263-3-0
978-1-72810-331-0 - ISBNs :
- 9783981926323, 9783981926330, and 9781728103310
- Database :
- OpenAIRE
- Journal :
- Proceedings of the 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE), DATE
- Accession number :
- edsair.doi.dedup.....1c6c97f936ed1a83d37af0ad14e3a917