Toward sub-pJ per classification in Body Area Sensor Networks

Paul Chollet; Kevin Colombier; Cyril Lahuec; Matthieu Arzel; Fabrice Seguin

doi:10.1109/NEWCAS.2016.7604764

Toward sub-pJ per classification in Body Area Sensor Networks

Paul Chollet
, Kevin Colombier
, Cyril Lahuec
, Matthieu Arzel
, Fabrice Seguin

Centre national de la recherche scientifique

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

Abstract

Body Area Sensor Networks (BASN) are expected to provide a way to improve medical care while reducing its costs. Reducing their energy consumption is a critical step before building reliable and durable systems. Acquisition and classification of Electrocardiogram (ECG) signals is a central task in medical BASNs. This paper introduces a method to perform the classification between three abnormal types of heart beats at ultra-low power using Sparse Neural Associative Memories (SNAM). Based on recent analog implementation of a SNAM node using the ST CMOS 65 nm design kit, the proposed SNAM uses only 864 fJ per classification. Compared to a digital ultra-low power multi-core architecture, this SNAM consumes several orders of magnitude less energy while achieving classification accuracy of 93.5 %.

Original language	English
Title of host publication	14th IEEE International NEWCAS Conference, NEWCAS 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781467389006
DOIs	https://doi.org/10.1109/NEWCAS.2016.7604764
Publication status	Published - 20 Oct 2016
Event	14th IEEE International NEWCAS Conference, NEWCAS 2016 - Vancouver, Canada Duration: 26 Jun 2016 → 29 Jun 2016

Publication series

Name	14th IEEE International NEWCAS Conference, NEWCAS 2016

Conference

Conference	14th IEEE International NEWCAS Conference, NEWCAS 2016
Country/Territory	Canada
City	Vancouver
Period	26/06/16 → 29/06/16

UN SDGs

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

SDG 7 Affordable and Clean Energy

Access to Document

10.1109/NEWCAS.2016.7604764

Cite this

@inproceedings{05a6e0b9e622480f8b54969d2ea2241c,

title = "Toward sub-pJ per classification in Body Area Sensor Networks",

abstract = "Body Area Sensor Networks (BASN) are expected to provide a way to improve medical care while reducing its costs. Reducing their energy consumption is a critical step before building reliable and durable systems. Acquisition and classification of Electrocardiogram (ECG) signals is a central task in medical BASNs. This paper introduces a method to perform the classification between three abnormal types of heart beats at ultra-low power using Sparse Neural Associative Memories (SNAM). Based on recent analog implementation of a SNAM node using the ST CMOS 65 nm design kit, the proposed SNAM uses only 864 fJ per classification. Compared to a digital ultra-low power multi-core architecture, this SNAM consumes several orders of magnitude less energy while achieving classification accuracy of 93.5 \%.",

author = "Paul Chollet and Kevin Colombier and Cyril Lahuec and Matthieu Arzel and Fabrice Seguin",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 14th IEEE International NEWCAS Conference, NEWCAS 2016 ; Conference date: 26-06-2016 Through 29-06-2016",

year = "2016",

month = oct,

day = "20",

doi = "10.1109/NEWCAS.2016.7604764",

language = "English",

series = "14th IEEE International NEWCAS Conference, NEWCAS 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "14th IEEE International NEWCAS Conference, NEWCAS 2016",

}

Chollet, P, Colombier, K, Lahuec, C, Arzel, M & Seguin, F 2016, Toward sub-pJ per classification in Body Area Sensor Networks. in 14th IEEE International NEWCAS Conference, NEWCAS 2016., 7604764, 14th IEEE International NEWCAS Conference, NEWCAS 2016, Institute of Electrical and Electronics Engineers Inc., 14th IEEE International NEWCAS Conference, NEWCAS 2016, Vancouver, Canada, 26/06/16. https://doi.org/10.1109/NEWCAS.2016.7604764

Toward sub-pJ per classification in Body Area Sensor Networks. / Chollet, Paul; Colombier, Kevin; Lahuec, Cyril et al.
14th IEEE International NEWCAS Conference, NEWCAS 2016. Institute of Electrical and Electronics Engineers Inc., 2016. 7604764 (14th IEEE International NEWCAS Conference, NEWCAS 2016).

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

TY - GEN

T1 - Toward sub-pJ per classification in Body Area Sensor Networks

AU - Chollet, Paul

AU - Colombier, Kevin

AU - Lahuec, Cyril

AU - Arzel, Matthieu

AU - Seguin, Fabrice

PY - 2016/10/20

Y1 - 2016/10/20

N2 - Body Area Sensor Networks (BASN) are expected to provide a way to improve medical care while reducing its costs. Reducing their energy consumption is a critical step before building reliable and durable systems. Acquisition and classification of Electrocardiogram (ECG) signals is a central task in medical BASNs. This paper introduces a method to perform the classification between three abnormal types of heart beats at ultra-low power using Sparse Neural Associative Memories (SNAM). Based on recent analog implementation of a SNAM node using the ST CMOS 65 nm design kit, the proposed SNAM uses only 864 fJ per classification. Compared to a digital ultra-low power multi-core architecture, this SNAM consumes several orders of magnitude less energy while achieving classification accuracy of 93.5 %.

AB - Body Area Sensor Networks (BASN) are expected to provide a way to improve medical care while reducing its costs. Reducing their energy consumption is a critical step before building reliable and durable systems. Acquisition and classification of Electrocardiogram (ECG) signals is a central task in medical BASNs. This paper introduces a method to perform the classification between three abnormal types of heart beats at ultra-low power using Sparse Neural Associative Memories (SNAM). Based on recent analog implementation of a SNAM node using the ST CMOS 65 nm design kit, the proposed SNAM uses only 864 fJ per classification. Compared to a digital ultra-low power multi-core architecture, this SNAM consumes several orders of magnitude less energy while achieving classification accuracy of 93.5 %.

U2 - 10.1109/NEWCAS.2016.7604764

DO - 10.1109/NEWCAS.2016.7604764

M3 - Conference contribution

AN - SCOPUS:84998534542

T3 - 14th IEEE International NEWCAS Conference, NEWCAS 2016

BT - 14th IEEE International NEWCAS Conference, NEWCAS 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th IEEE International NEWCAS Conference, NEWCAS 2016

Y2 - 26 June 2016 through 29 June 2016

ER -

Toward sub-pJ per classification in Body Area Sensor Networks

Abstract

Publication series

Conference

UN SDGs

Access to Document

Fingerprint

Cite this