A 28.2 μc Neuromorphic Sensing System Featuring SNN-based Near-sensor Computation and Event-Driven Body-Channel Communication for Insertable Cardiac Monitoring

Yuming He; Federico Corradi; Chengyao Shi; Ming Ding; Martijn Timmermans; Jan Stuijt; Pieter Harpe; Ilja Ocket; Yao-Hong Liu

doi:10.1109/A-SSCC53895.2021.9634787

A 28.2 μc Neuromorphic Sensing System Featuring SNN-based Near-sensor Computation and Event-Driven Body-Channel Communication for Insertable Cardiac Monitoring

Yuming He
, Federico Corradi
, Chengyao Shi
, Ming Ding
, Martijn Timmermans
, Jan Stuijt
, Pieter Harpe
, Ilja Ocket
, Yao-Hong Liu

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

11 Citations (Scopus)

2 Downloads (Pure)

Abstract

This paper presents an event-driven neuromorphic sensing system capable of performing on-chip feature extraction and 'send-on-delta' transmission for insertable cardiac monitoring. A background offset calibration improves the SNDR of clockless level-crossing ADCs. A fully synthesized spiking neural network extracts full ECG PQRST features with \lt 1 ms time precision. An event-driven body channel communication minimizes transmission energy. The prototype is fabricated in 40nm CMOS and consumes 28.2 \mu \mathrm{W} system power.

Original language	English
Title of host publication	Proceedings - A-SSCC 2021
Subtitle of host publication	IEEE Asian Solid-State Circuits Conference
Publisher	Institute of Electrical and Electronics Engineers
Number of pages	3
ISBN (Electronic)	9781665443500
ISBN (Print)	978-1-6654-4351-7
DOIs	https://doi.org/10.1109/A-SSCC53895.2021.9634787
Publication status	Published - 10 Dec 2021
Event	17th IEEE Asian Solid-State Circuits Conference, A-SSCC 2021 - Busan, Korea, Republic of Duration: 7 Nov 2021 → 10 Nov 2021 Conference number: 17 https://www.a-sscc2021.org/

Conference

Conference	17th IEEE Asian Solid-State Circuits Conference, A-SSCC 2021
Abbreviated title	A-SSCC 2021
Country/Territory	Korea, Republic of
City	Busan
Period	7/11/21 → 10/11/21
Internet address	https://www.a-sscc2021.org/

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

Neuromorphics
Conferences
Neural networks
Prototypes
Electrocardiography
Feature extraction
Sensors

Access to Document

10.1109/A-SSCC53895.2021.9634787

Cite this

He, Y., Corradi, F., Shi, C., Ding, M., Timmermans, M., Stuijt, J., Harpe, P., Ocket, I., & Liu, Y.-H. (2021). A 28.2 μc Neuromorphic Sensing System Featuring SNN-based Near-sensor Computation and Event-Driven Body-Channel Communication for Insertable Cardiac Monitoring. In Proceedings - A-SSCC 2021: IEEE Asian Solid-State Circuits Conference Article 9634787 Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/A-SSCC53895.2021.9634787

@inproceedings{a8776f841c4f4e8cb01e542689028093,

title = "A 28.2 μc Neuromorphic Sensing System Featuring SNN-based Near-sensor Computation and Event-Driven Body-Channel Communication for Insertable Cardiac Monitoring",

abstract = "This paper presents an event-driven neuromorphic sensing system capable of performing on-chip feature extraction and 'send-on-delta' transmission for insertable cardiac monitoring. A background offset calibration improves the SNDR of clockless level-crossing ADCs. A fully synthesized spiking neural network extracts full ECG PQRST features with \textbackslash{}lt 1 ms time precision. An event-driven body channel communication minimizes transmission energy. The prototype is fabricated in 40nm CMOS and consumes 28.2 \textbackslash{}mu \textbackslash{}mathrm\{W\} system power. ",

keywords = "Neuromorphics, Conferences, Neural networks, Prototypes, Electrocardiography, Feature extraction, Sensors",

author = "Yuming He and Federico Corradi and Chengyao Shi and Ming Ding and Martijn Timmermans and Jan Stuijt and Pieter Harpe and Ilja Ocket and Yao-Hong Liu",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 17th IEEE Asian Solid-State Circuits Conference, A-SSCC 2021, A-SSCC 2021 ; Conference date: 07-11-2021 Through 10-11-2021",

year = "2021",

month = dec,

day = "10",

doi = "10.1109/A-SSCC53895.2021.9634787",

language = "English",

isbn = "978-1-6654-4351-7",

booktitle = "Proceedings - A-SSCC 2021",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

url = "https://www.a-sscc2021.org/",

}

He, Y, Corradi, F , Shi, C, Ding, M, Timmermans, M, Stuijt, J, Harpe, P, Ocket, I & Liu, Y-H 2021, A 28.2 μc Neuromorphic Sensing System Featuring SNN-based Near-sensor Computation and Event-Driven Body-Channel Communication for Insertable Cardiac Monitoring. in Proceedings - A-SSCC 2021: IEEE Asian Solid-State Circuits Conference., 9634787, Institute of Electrical and Electronics Engineers, 17th IEEE Asian Solid-State Circuits Conference, A-SSCC 2021, Busan, Korea, Republic of, 7/11/21. https://doi.org/10.1109/A-SSCC53895.2021.9634787

A 28.2 μc Neuromorphic Sensing System Featuring SNN-based Near-sensor Computation and Event-Driven Body-Channel Communication for Insertable Cardiac Monitoring. / He, Yuming; Corradi, Federico ; Shi, Chengyao et al.
Proceedings - A-SSCC 2021: IEEE Asian Solid-State Circuits Conference. Institute of Electrical and Electronics Engineers, 2021. 9634787.

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

TY - GEN

T1 - A 28.2 μc Neuromorphic Sensing System Featuring SNN-based Near-sensor Computation and Event-Driven Body-Channel Communication for Insertable Cardiac Monitoring

AU - He, Yuming

AU - Corradi, Federico

AU - Shi, Chengyao

AU - Ding, Ming

AU - Timmermans, Martijn

AU - Stuijt, Jan

AU - Harpe, Pieter

AU - Ocket, Ilja

AU - Liu, Yao-Hong

N1 - Conference code: 17

PY - 2021/12/10

Y1 - 2021/12/10

N2 - This paper presents an event-driven neuromorphic sensing system capable of performing on-chip feature extraction and 'send-on-delta' transmission for insertable cardiac monitoring. A background offset calibration improves the SNDR of clockless level-crossing ADCs. A fully synthesized spiking neural network extracts full ECG PQRST features with \lt 1 ms time precision. An event-driven body channel communication minimizes transmission energy. The prototype is fabricated in 40nm CMOS and consumes 28.2 \mu \mathrm{W} system power.

AB - This paper presents an event-driven neuromorphic sensing system capable of performing on-chip feature extraction and 'send-on-delta' transmission for insertable cardiac monitoring. A background offset calibration improves the SNDR of clockless level-crossing ADCs. A fully synthesized spiking neural network extracts full ECG PQRST features with \lt 1 ms time precision. An event-driven body channel communication minimizes transmission energy. The prototype is fabricated in 40nm CMOS and consumes 28.2 \mu \mathrm{W} system power.

KW - Neuromorphics

KW - Conferences

KW - Neural networks

KW - Prototypes

KW - Electrocardiography

KW - Feature extraction

KW - Sensors

UR - https://www.scopus.com/pages/publications/85121789212

U2 - 10.1109/A-SSCC53895.2021.9634787

DO - 10.1109/A-SSCC53895.2021.9634787

M3 - Conference contribution

SN - 978-1-6654-4351-7

BT - Proceedings - A-SSCC 2021

PB - Institute of Electrical and Electronics Engineers

T2 - 17th IEEE Asian Solid-State Circuits Conference, A-SSCC 2021

Y2 - 7 November 2021 through 10 November 2021

ER -

He Y, Corradi F , Shi C, Ding M, Timmermans M, Stuijt J et al. A 28.2 μc Neuromorphic Sensing System Featuring SNN-based Near-sensor Computation and Event-Driven Body-Channel Communication for Insertable Cardiac Monitoring. In Proceedings - A-SSCC 2021: IEEE Asian Solid-State Circuits Conference. Institute of Electrical and Electronics Engineers. 2021. 9634787 doi: 10.1109/A-SSCC53895.2021.9634787

A 28.2 μc Neuromorphic Sensing System Featuring SNN-based Near-sensor Computation and Event-Driven Body-Channel Communication for Insertable Cardiac Monitoring

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this