BrainWave: an energy-efficient EEG monitoring system - evaluation and trade-offs

E. (Barry) de Bruin; Kamlesh Singh; Jos A. Huisken; Henk Corporaal

doi:10.1145/3370748.3406571

BrainWave: an energy-efficient EEG monitoring system - evaluation and trade-offs

E. (Barry) de Bruin, Kamlesh Singh, Jos A. Huisken, Henk Corporaal

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › Academic › peer review

1 Citaat (Scopus)

403 Downloads (Pure)

Samenvatting

This paper presents the design and evaluation of an energy-efficient seizure detection system for emerging EEG-based monitoring applications, such as non-convulsive epileptic seizure detection and Freezing-of-Gait (FoG) detection. As part of the BrainWave system, a BrainWave processor for flexible and energy-efficient signal processing is designed. The key system design parameters, including algorithmic optimizations, feature offloading and near-Threshold computing are evaluated in this work. The BrainWave processor is evaluated while executing a complex EEG-based epileptic seizure detection algorithm. In a 28-nm FDSOI technology, 325 μJ per classification at 0.9 V and 290 μJ at 0.5 V are achieved using an optimized software-only implementation. By leveraging a Coarse-Grained Reconfigurable Array (CGRA), 160 μJ and 135 μJ are obtained, respectively, while maintaining a high level of flexibility. Near-Threshold computing combined with CGRA acceleration leads to an energy reduction of up to 59%, or 55% including idle-Time overhead.

Originele taal-2	Engels
Titel	Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design, ISLPED 2020
Subtitel	ISLPED '20
Uitgeverij	ACM/IEEE
Pagina's	181–186
Aantal pagina's	6
ISBN van elektronische versie	9781450370530
DOI's	https://doi.org/10.1145/3370748.3406571
Status	Gepubliceerd - 10 aug. 2020

Publicatie series

Naam	ACM International Conference Proceeding Series

Duurzame ontwikkelingsdoelstellingen van de VN

Deze output draagt bij aan de volgende duurzame ontwikkelingsdoelstelling(en)

Toegang tot document

10.1145/3370748.3406571

3370748.3406571Definitieve gepubliceerde versie, 916 KB

Andere bestanden en links

Link to publication in Scopus

Brainwave
Huisken, J. A. (Projectmedewerker), Jiao, H. (Project Manager), Singh, K. (Projectmedewerker), Sánchez Martín, V. (Project Manager), de Bruin, B. (Projectmedewerker), van der Hagen, D. (Project communicatie medewerker) & de Mol-Regels, M. (Project communicatie medewerker)
1/09/16 → 30/11/21
Project: Onderzoek direct
Wearable Brainwave Processing Platform
Bergmans, J. W. M. (Project Manager), van der Hagen, D. (Project communicatie medewerker), Sánchez Martín, V. (Program Manager), Corporaal, H. (Projectmedewerker), Pineda de Gyvez, J. (Projectmedewerker) & Huisken, J. A. (Projectmedewerker)
1/09/16 → 30/11/21
Project: Onderzoek direct

Citeer dit

de Bruin, E., Singh, K., Huisken, J. A., & Corporaal, H. (2020). BrainWave: an energy-efficient EEG monitoring system - evaluation and trade-offs. In Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design, ISLPED 2020: ISLPED '20 (blz. 181–186). Artikel 3406571 (ACM International Conference Proceeding Series). ACM/IEEE. https://doi.org/10.1145/3370748.3406571

@inproceedings{de7c72b5be1342988fe66aec8d6761b3,

title = "BrainWave: an energy-efficient EEG monitoring system - evaluation and trade-offs",

abstract = "This paper presents the design and evaluation of an energy-efficient seizure detection system for emerging EEG-based monitoring applications, such as non-convulsive epileptic seizure detection and Freezing-of-Gait (FoG) detection. As part of the BrainWave system, a BrainWave processor for flexible and energy-efficient signal processing is designed. The key system design parameters, including algorithmic optimizations, feature offloading and near-Threshold computing are evaluated in this work. The BrainWave processor is evaluated while executing a complex EEG-based epileptic seizure detection algorithm. In a 28-nm FDSOI technology, 325 μJ per classification at 0.9 V and 290 μJ at 0.5 V are achieved using an optimized software-only implementation. By leveraging a Coarse-Grained Reconfigurable Array (CGRA), 160 μJ and 135 μJ are obtained, respectively, while maintaining a high level of flexibility. Near-Threshold computing combined with CGRA acceleration leads to an energy reduction of up to 59%, or 55% including idle-Time overhead.",

keywords = "edge processing, energy-efficiency, reconfigurable accelerators, system-level trade-offs, wearable EEG monitoring",

author = "{de Bruin}, {E. (Barry)} and Kamlesh Singh and Huisken, {Jos A.} and Henk Corporaal",

year = "2020",

month = aug,

day = "10",

doi = "10.1145/3370748.3406571",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "ACM/IEEE",

pages = "181–186",

booktitle = "Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design, ISLPED 2020",

}

de Bruin, E, Singh, K, Huisken, JA & Corporaal, H 2020, BrainWave: an energy-efficient EEG monitoring system - evaluation and trade-offs. in Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design, ISLPED 2020: ISLPED '20., 3406571, ACM International Conference Proceeding Series, ACM/IEEE, blz. 181–186. https://doi.org/10.1145/3370748.3406571

BrainWave: an energy-efficient EEG monitoring system - evaluation and trade-offs. / de Bruin, E. (Barry); Singh, Kamlesh; Huisken, Jos A. et al.
Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design, ISLPED 2020: ISLPED '20. ACM/IEEE, 2020. blz. 181–186 3406571 (ACM International Conference Proceeding Series).

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › Academic › peer review

TY - GEN

T1 - BrainWave: an energy-efficient EEG monitoring system - evaluation and trade-offs

AU - de Bruin, E. (Barry)

AU - Singh, Kamlesh

AU - Huisken, Jos A.

AU - Corporaal, Henk

PY - 2020/8/10

Y1 - 2020/8/10

N2 - This paper presents the design and evaluation of an energy-efficient seizure detection system for emerging EEG-based monitoring applications, such as non-convulsive epileptic seizure detection and Freezing-of-Gait (FoG) detection. As part of the BrainWave system, a BrainWave processor for flexible and energy-efficient signal processing is designed. The key system design parameters, including algorithmic optimizations, feature offloading and near-Threshold computing are evaluated in this work. The BrainWave processor is evaluated while executing a complex EEG-based epileptic seizure detection algorithm. In a 28-nm FDSOI technology, 325 μJ per classification at 0.9 V and 290 μJ at 0.5 V are achieved using an optimized software-only implementation. By leveraging a Coarse-Grained Reconfigurable Array (CGRA), 160 μJ and 135 μJ are obtained, respectively, while maintaining a high level of flexibility. Near-Threshold computing combined with CGRA acceleration leads to an energy reduction of up to 59%, or 55% including idle-Time overhead.

AB - This paper presents the design and evaluation of an energy-efficient seizure detection system for emerging EEG-based monitoring applications, such as non-convulsive epileptic seizure detection and Freezing-of-Gait (FoG) detection. As part of the BrainWave system, a BrainWave processor for flexible and energy-efficient signal processing is designed. The key system design parameters, including algorithmic optimizations, feature offloading and near-Threshold computing are evaluated in this work. The BrainWave processor is evaluated while executing a complex EEG-based epileptic seizure detection algorithm. In a 28-nm FDSOI technology, 325 μJ per classification at 0.9 V and 290 μJ at 0.5 V are achieved using an optimized software-only implementation. By leveraging a Coarse-Grained Reconfigurable Array (CGRA), 160 μJ and 135 μJ are obtained, respectively, while maintaining a high level of flexibility. Near-Threshold computing combined with CGRA acceleration leads to an energy reduction of up to 59%, or 55% including idle-Time overhead.

KW - edge processing

KW - energy-efficiency

KW - reconfigurable accelerators

KW - system-level trade-offs

KW - wearable EEG monitoring

UR - http://www.scopus.com/inward/record.url?scp=85098267878&partnerID=8YFLogxK

U2 - 10.1145/3370748.3406571

DO - 10.1145/3370748.3406571

M3 - Conference contribution

T3 - ACM International Conference Proceeding Series

SP - 181

EP - 186

BT - Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design, ISLPED 2020

PB - ACM/IEEE

ER -

BrainWave: an energy-efficient EEG monitoring system - evaluation and trade-offs

Samenvatting

Publicatie series

Duurzame ontwikkelingsdoelstellingen van de VN

Toegang tot document

Andere bestanden en links

Vingerafdruk

Projecten

Brainwave

Wearable Brainwave Processing Platform

Citeer dit