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

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

1 Citation (Scopus)

403 Downloads (Pure)

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.

Original language	English
Title of host publication	Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design, ISLPED 2020
Subtitle of host publication	ISLPED '20
Publisher	ACM/IEEE
Pages	181–186
Number of pages	6
ISBN (Electronic)	9781450370530
DOIs	https://doi.org/10.1145/3370748.3406571
Publication status	Published - 10 Aug 2020

Publication series

Name	ACM International Conference Proceeding Series

Keywords

edge processing
energy-efficiency
reconfigurable accelerators
system-level trade-offs
wearable EEG monitoring

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1145/3370748.3406571

3370748.3406571Final published version, 916 KB

Cite this

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 (pp. 181–186). Article 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, pp. 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. p. 181–186 3406571 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › 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

Abstract

Publication series

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Wearable Brainwave Processing Platform

Brainwave

Cite this

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

Abstract

Publication series

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Projects

Wearable Brainwave Processing Platform

Brainwave

Cite this