Toward Real-Time, At-Home Patient Health Monitoring Using Reservoir Computing CMOS IC

Sanjeev Tannirkulam Chandrasekaran; Sumukh Prashant Bhanushali; Imon Banerjee; Arindam Sanyal

doi:10.1109/JETCAS.2021.3128587

Toward Real-Time, At-Home Patient Health Monitoring Using Reservoir Computing CMOS IC

Sanjeev Tannirkulam Chandrasekaran, Sumukh Prashant Bhanushali, Imon Banerjee, Arindam Sanyal

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

This work presents a mixed-signal, reservoir-computing neural network (RC-NN) for at-home, real-time health monitoring using intelligent wearable device. The proposed technique is demonstrated on stress detection from electrocardiogram (ECG) signal, and heart diseases detection using a fusion artificial intelligence (AI) model that combines demographic and physiological information. The RC-NN uses a static, random reservoir layer with short-term memory to nonlinearly project input data to high-dimensional plane, and allow easy separation using linear AI model at the output layer. The RC-NN is designed in 65nm CMOS process, and detects stress and heart-diseases with mean accuracies of 92.8% and 86.8% respectively, while consuming 10.97nJ/inference and 2.57nJ/inference respectively.

Original language	English (US)
Pages (from-to)	829-839
Number of pages	11
Journal	IEEE Journal on Emerging and Selected Topics in Circuits and Systems
Volume	11
Issue number	4
DOIs	https://doi.org/10.1109/JETCAS.2021.3128587
State	Published - Dec 1 2021
Externally published	Yes

Keywords

Machine learning
cardiac diseases prediction
data fusion and medical wearable
health monitoring
reservoir computing
stress detection

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.1109/JETCAS.2021.3128587

Cite this

@article{ed0431914d3b4df892806a92ddf05899,

title = "Toward Real-Time, At-Home Patient Health Monitoring Using Reservoir Computing CMOS IC",

abstract = "This work presents a mixed-signal, reservoir-computing neural network (RC-NN) for at-home, real-time health monitoring using intelligent wearable device. The proposed technique is demonstrated on stress detection from electrocardiogram (ECG) signal, and heart diseases detection using a fusion artificial intelligence (AI) model that combines demographic and physiological information. The RC-NN uses a static, random reservoir layer with short-term memory to nonlinearly project input data to high-dimensional plane, and allow easy separation using linear AI model at the output layer. The RC-NN is designed in 65nm CMOS process, and detects stress and heart-diseases with mean accuracies of 92.8% and 86.8% respectively, while consuming 10.97nJ/inference and 2.57nJ/inference respectively.",

keywords = "Machine learning, cardiac diseases prediction, data fusion and medical wearable, health monitoring, reservoir computing, stress detection",

author = "{Tannirkulam Chandrasekaran}, Sanjeev and {Prashant Bhanushali}, Sumukh and Imon Banerjee and Arindam Sanyal",

note = "Publisher Copyright: {\textcopyright} 2011 IEEE.",

year = "2021",

month = dec,

day = "1",

doi = "10.1109/JETCAS.2021.3128587",

language = "English (US)",

volume = "11",

pages = "829--839",

journal = "IEEE Journal on Emerging and Selected Topics in Circuits and Systems",

issn = "2156-3357",

publisher = "IEEE Circuits and Systems Society",

number = "4",

}

TY - JOUR

T1 - Toward Real-Time, At-Home Patient Health Monitoring Using Reservoir Computing CMOS IC

AU - Tannirkulam Chandrasekaran, Sanjeev

AU - Prashant Bhanushali, Sumukh

AU - Banerjee, Imon

AU - Sanyal, Arindam

PY - 2021/12/1

Y1 - 2021/12/1

N2 - This work presents a mixed-signal, reservoir-computing neural network (RC-NN) for at-home, real-time health monitoring using intelligent wearable device. The proposed technique is demonstrated on stress detection from electrocardiogram (ECG) signal, and heart diseases detection using a fusion artificial intelligence (AI) model that combines demographic and physiological information. The RC-NN uses a static, random reservoir layer with short-term memory to nonlinearly project input data to high-dimensional plane, and allow easy separation using linear AI model at the output layer. The RC-NN is designed in 65nm CMOS process, and detects stress and heart-diseases with mean accuracies of 92.8% and 86.8% respectively, while consuming 10.97nJ/inference and 2.57nJ/inference respectively.

AB - This work presents a mixed-signal, reservoir-computing neural network (RC-NN) for at-home, real-time health monitoring using intelligent wearable device. The proposed technique is demonstrated on stress detection from electrocardiogram (ECG) signal, and heart diseases detection using a fusion artificial intelligence (AI) model that combines demographic and physiological information. The RC-NN uses a static, random reservoir layer with short-term memory to nonlinearly project input data to high-dimensional plane, and allow easy separation using linear AI model at the output layer. The RC-NN is designed in 65nm CMOS process, and detects stress and heart-diseases with mean accuracies of 92.8% and 86.8% respectively, while consuming 10.97nJ/inference and 2.57nJ/inference respectively.

KW - Machine learning

KW - cardiac diseases prediction

KW - data fusion and medical wearable

KW - health monitoring

KW - reservoir computing

KW - stress detection

UR - http://www.scopus.com/inward/record.url?scp=85121828196&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85121828196&partnerID=8YFLogxK

U2 - 10.1109/JETCAS.2021.3128587

DO - 10.1109/JETCAS.2021.3128587

M3 - Article

AN - SCOPUS:85121828196

SN - 2156-3357

VL - 11

SP - 829

EP - 839

JO - IEEE Journal on Emerging and Selected Topics in Circuits and Systems

JF - IEEE Journal on Emerging and Selected Topics in Circuits and Systems

IS - 4

ER -

Toward Real-Time, At-Home Patient Health Monitoring Using Reservoir Computing CMOS IC

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this