ECG authentication neural network hardware design with collective optimization of low precision and structured compression

Sai Kiran Cherupally, Gaurav Srivastava, Shihui Yin, Deepak Kadetotad, Chisung Bae, Sang Joon Kim, Seo Jae-Sun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

For wearable devices that monitor personal health, secure access to private medical data becomes a crucial feature. Nowadays, device authentication based on biometrics such as fingerprint or iris has become increasingly popular. In this work, we investigate using electrocardiogram (ECG) signals as the biometric modality for device authentication, and we present accurate and low-power ECG-based authentication hardware. Deep neural networks (DNNs) have been employed with a cost function that maximizes inter-individual distance and minimizes intra-individual distance over time. During DNN training, we also introduce joint optimization of low-precision and structured sparsity, so that the real-time authentication hardware can consume minimal energy and area. Experimental results of custom hardware designed in 65nm LP CMOS technology exhibit low power consumption of 59.4 µW for real-time ECG authentication with a low equal error rate of 1.002% for a large 741-subject in-house ECG database.

Original languageEnglish (US)
Title of host publication2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728103976
DOIs
StatePublished - Jan 1 2019
Event2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Sapporo, Japan
Duration: May 26 2019May 29 2019

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume2019-May
ISSN (Print)0271-4310

Conference

Conference2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019
CountryJapan
CitySapporo
Period5/26/195/29/19

Fingerprint

Electrocardiography
Authentication
Neural networks
Hardware
Biometrics
Cost functions
Electric power utilization
Health
Deep neural networks

Keywords

  • Authentication
  • Deep neural network
  • ECG
  • Low-power hardware
  • Structural sparsity

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Cherupally, S. K., Srivastava, G., Yin, S., Kadetotad, D., Bae, C., Kim, S. J., & Jae-Sun, S. (2019). ECG authentication neural network hardware design with collective optimization of low precision and structured compression. In 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings [8702308] (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAS.2019.8702308

ECG authentication neural network hardware design with collective optimization of low precision and structured compression. / Cherupally, Sai Kiran; Srivastava, Gaurav; Yin, Shihui; Kadetotad, Deepak; Bae, Chisung; Kim, Sang Joon; Jae-Sun, Seo.

2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 8702308 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2019-May).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cherupally, SK, Srivastava, G, Yin, S, Kadetotad, D, Bae, C, Kim, SJ & Jae-Sun, S 2019, ECG authentication neural network hardware design with collective optimization of low precision and structured compression. in 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings., 8702308, Proceedings - IEEE International Symposium on Circuits and Systems, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019, Sapporo, Japan, 5/26/19. https://doi.org/10.1109/ISCAS.2019.8702308
Cherupally SK, Srivastava G, Yin S, Kadetotad D, Bae C, Kim SJ et al. ECG authentication neural network hardware design with collective optimization of low precision and structured compression. In 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. 8702308. (Proceedings - IEEE International Symposium on Circuits and Systems). https://doi.org/10.1109/ISCAS.2019.8702308
Cherupally, Sai Kiran ; Srivastava, Gaurav ; Yin, Shihui ; Kadetotad, Deepak ; Bae, Chisung ; Kim, Sang Joon ; Jae-Sun, Seo. / ECG authentication neural network hardware design with collective optimization of low precision and structured compression. 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings - IEEE International Symposium on Circuits and Systems).
@inproceedings{a9ecd6ff4ab146218399894fdb23f005,
title = "ECG authentication neural network hardware design with collective optimization of low precision and structured compression",
abstract = "For wearable devices that monitor personal health, secure access to private medical data becomes a crucial feature. Nowadays, device authentication based on biometrics such as fingerprint or iris has become increasingly popular. In this work, we investigate using electrocardiogram (ECG) signals as the biometric modality for device authentication, and we present accurate and low-power ECG-based authentication hardware. Deep neural networks (DNNs) have been employed with a cost function that maximizes inter-individual distance and minimizes intra-individual distance over time. During DNN training, we also introduce joint optimization of low-precision and structured sparsity, so that the real-time authentication hardware can consume minimal energy and area. Experimental results of custom hardware designed in 65nm LP CMOS technology exhibit low power consumption of 59.4 µW for real-time ECG authentication with a low equal error rate of 1.002{\%} for a large 741-subject in-house ECG database.",
keywords = "Authentication, Deep neural network, ECG, Low-power hardware, Structural sparsity",
author = "Cherupally, {Sai Kiran} and Gaurav Srivastava and Shihui Yin and Deepak Kadetotad and Chisung Bae and Kim, {Sang Joon} and Seo Jae-Sun",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/ISCAS.2019.8702308",
language = "English (US)",
series = "Proceedings - IEEE International Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings",

}

TY - GEN

T1 - ECG authentication neural network hardware design with collective optimization of low precision and structured compression

AU - Cherupally, Sai Kiran

AU - Srivastava, Gaurav

AU - Yin, Shihui

AU - Kadetotad, Deepak

AU - Bae, Chisung

AU - Kim, Sang Joon

AU - Jae-Sun, Seo

PY - 2019/1/1

Y1 - 2019/1/1

N2 - For wearable devices that monitor personal health, secure access to private medical data becomes a crucial feature. Nowadays, device authentication based on biometrics such as fingerprint or iris has become increasingly popular. In this work, we investigate using electrocardiogram (ECG) signals as the biometric modality for device authentication, and we present accurate and low-power ECG-based authentication hardware. Deep neural networks (DNNs) have been employed with a cost function that maximizes inter-individual distance and minimizes intra-individual distance over time. During DNN training, we also introduce joint optimization of low-precision and structured sparsity, so that the real-time authentication hardware can consume minimal energy and area. Experimental results of custom hardware designed in 65nm LP CMOS technology exhibit low power consumption of 59.4 µW for real-time ECG authentication with a low equal error rate of 1.002% for a large 741-subject in-house ECG database.

AB - For wearable devices that monitor personal health, secure access to private medical data becomes a crucial feature. Nowadays, device authentication based on biometrics such as fingerprint or iris has become increasingly popular. In this work, we investigate using electrocardiogram (ECG) signals as the biometric modality for device authentication, and we present accurate and low-power ECG-based authentication hardware. Deep neural networks (DNNs) have been employed with a cost function that maximizes inter-individual distance and minimizes intra-individual distance over time. During DNN training, we also introduce joint optimization of low-precision and structured sparsity, so that the real-time authentication hardware can consume minimal energy and area. Experimental results of custom hardware designed in 65nm LP CMOS technology exhibit low power consumption of 59.4 µW for real-time ECG authentication with a low equal error rate of 1.002% for a large 741-subject in-house ECG database.

KW - Authentication

KW - Deep neural network

KW - ECG

KW - Low-power hardware

KW - Structural sparsity

UR - http://www.scopus.com/inward/record.url?scp=85066794346&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066794346&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2019.8702308

DO - 10.1109/ISCAS.2019.8702308

M3 - Conference contribution

AN - SCOPUS:85066794346

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

BT - 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -