Multi-Task Learning Mixed-Signal Classifier for In-situ Detection of Atrial Fibrillation and Sepsis

Sudarsan Sadasivuni; Sumukh Prashant Bhanushali; Sai Srinivasa Singamsetti; Imon Banerjee; Arindam Sanyal

doi:10.1109/BioCAS49922.2021.9644994

Multi-Task Learning Mixed-Signal Classifier for In-situ Detection of Atrial Fibrillation and Sepsis

Sudarsan Sadasivuni, Sumukh Prashant Bhanushali, Sai Srinivasa Singamsetti, Imon Banerjee, Arindam Sanyal

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

5 Scopus citations

Abstract

This paper presents an on-chip analog machine learning (ML) classifier IC for detecting atrial fibrillation (AFib) and sepsis from electrocardiogram (ECG) signal. The proposed technique allows continuous in-situ health surveillance using wearables with embedded AI for early detection of underlying health issues. The analog classifier uses custom activation function and performs in-memory computation (IMC) with switched-capacitor circuits for reduced data movement. Designed in 65nm, the test chip achieves average accuracy of 98.2% for AFib detection, and 90.7% for predicting sepsis 4 hours before onset. The energy efficiency of the test-chip is 12.9nJ/classification which is 4× better than state-of-the-art.

Original language	English (US)
Title of host publication	BioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728172040
DOIs	https://doi.org/10.1109/BioCAS49922.2021.9644994
State	Published - 2021
Externally published	Yes
Event	2021 IEEE Biomedical Circuits and Systems Conference, BioCAS 2021 - Virtual, Online, Germany Duration: Oct 6 2021 → Oct 9 2021

Publication series

Name	BioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings

Conference

Conference	2021 IEEE Biomedical Circuits and Systems Conference, BioCAS 2021
Country/Territory	Germany
City	Virtual, Online
Period	10/6/21 → 10/9/21

Keywords

Machine learning
atrial fibrillation
mixed-signal classifier and in-memory computation
sepsis

ASJC Scopus subject areas

Hardware and Architecture
Biomedical Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/BioCAS49922.2021.9644994

Cite this

Sadasivuni, S., Bhanushali, S. P., Singamsetti, S. S., Banerjee, I., & Sanyal, A. (2021). Multi-Task Learning Mixed-Signal Classifier for In-situ Detection of Atrial Fibrillation and Sepsis. In BioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings (BioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BioCAS49922.2021.9644994

Multi-Task Learning Mixed-Signal Classifier for In-situ Detection of Atrial Fibrillation and Sepsis. / Sadasivuni, Sudarsan; Bhanushali, Sumukh Prashant; Singamsetti, Sai Srinivasa et al.
BioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. (BioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings).

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

Sadasivuni, S, Bhanushali, SP, Singamsetti, SS, Banerjee, I & Sanyal, A 2021, Multi-Task Learning Mixed-Signal Classifier for In-situ Detection of Atrial Fibrillation and Sepsis. in BioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings. BioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings, Institute of Electrical and Electronics Engineers Inc., 2021 IEEE Biomedical Circuits and Systems Conference, BioCAS 2021, Virtual, Online, Germany, 10/6/21. https://doi.org/10.1109/BioCAS49922.2021.9644994

Sadasivuni S, Bhanushali SP, Singamsetti SS, Banerjee I, Sanyal A. Multi-Task Learning Mixed-Signal Classifier for In-situ Detection of Atrial Fibrillation and Sepsis. In BioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2021. (BioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings). doi: 10.1109/BioCAS49922.2021.9644994

Sadasivuni, Sudarsan ; Bhanushali, Sumukh Prashant ; Singamsetti, Sai Srinivasa et al. / Multi-Task Learning Mixed-Signal Classifier for In-situ Detection of Atrial Fibrillation and Sepsis. BioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. (BioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings).

@inproceedings{bf061d3dcb3c4dd1abbe7db231a4af97,

title = "Multi-Task Learning Mixed-Signal Classifier for In-situ Detection of Atrial Fibrillation and Sepsis",

abstract = "This paper presents an on-chip analog machine learning (ML) classifier IC for detecting atrial fibrillation (AFib) and sepsis from electrocardiogram (ECG) signal. The proposed technique allows continuous in-situ health surveillance using wearables with embedded AI for early detection of underlying health issues. The analog classifier uses custom activation function and performs in-memory computation (IMC) with switched-capacitor circuits for reduced data movement. Designed in 65nm, the test chip achieves average accuracy of 98.2% for AFib detection, and 90.7% for predicting sepsis 4 hours before onset. The energy efficiency of the test-chip is 12.9nJ/classification which is 4× better than state-of-the-art.",

keywords = "Machine learning, atrial fibrillation, mixed-signal classifier and in-memory computation, sepsis",

author = "Sudarsan Sadasivuni and Bhanushali, {Sumukh Prashant} and Singamsetti, {Sai Srinivasa} and Imon Banerjee and Arindam Sanyal",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE Biomedical Circuits and Systems Conference, BioCAS 2021 ; Conference date: 06-10-2021 Through 09-10-2021",

year = "2021",

doi = "10.1109/BioCAS49922.2021.9644994",

language = "English (US)",

series = "BioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings",

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

booktitle = "BioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings",

}

TY - GEN

T1 - Multi-Task Learning Mixed-Signal Classifier for In-situ Detection of Atrial Fibrillation and Sepsis

AU - Sadasivuni, Sudarsan

AU - Bhanushali, Sumukh Prashant

AU - Singamsetti, Sai Srinivasa

AU - Banerjee, Imon

AU - Sanyal, Arindam

PY - 2021

Y1 - 2021

N2 - This paper presents an on-chip analog machine learning (ML) classifier IC for detecting atrial fibrillation (AFib) and sepsis from electrocardiogram (ECG) signal. The proposed technique allows continuous in-situ health surveillance using wearables with embedded AI for early detection of underlying health issues. The analog classifier uses custom activation function and performs in-memory computation (IMC) with switched-capacitor circuits for reduced data movement. Designed in 65nm, the test chip achieves average accuracy of 98.2% for AFib detection, and 90.7% for predicting sepsis 4 hours before onset. The energy efficiency of the test-chip is 12.9nJ/classification which is 4× better than state-of-the-art.

AB - This paper presents an on-chip analog machine learning (ML) classifier IC for detecting atrial fibrillation (AFib) and sepsis from electrocardiogram (ECG) signal. The proposed technique allows continuous in-situ health surveillance using wearables with embedded AI for early detection of underlying health issues. The analog classifier uses custom activation function and performs in-memory computation (IMC) with switched-capacitor circuits for reduced data movement. Designed in 65nm, the test chip achieves average accuracy of 98.2% for AFib detection, and 90.7% for predicting sepsis 4 hours before onset. The energy efficiency of the test-chip is 12.9nJ/classification which is 4× better than state-of-the-art.

KW - Machine learning

KW - atrial fibrillation

KW - mixed-signal classifier and in-memory computation

KW - sepsis

UR - http://www.scopus.com/inward/record.url?scp=85124202271&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85124202271&partnerID=8YFLogxK

U2 - 10.1109/BioCAS49922.2021.9644994

DO - 10.1109/BioCAS49922.2021.9644994

M3 - Conference contribution

AN - SCOPUS:85124202271

T3 - BioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings

BT - BioCAS 2021 - IEEE Biomedical Circuits and Systems Conference, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE Biomedical Circuits and Systems Conference, BioCAS 2021

Y2 - 6 October 2021 through 9 October 2021

ER -

Multi-Task Learning Mixed-Signal Classifier for In-situ Detection of Atrial Fibrillation and Sepsis

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this