TY - JOUR
T1 - A Bio-Inspired Reservoir-Computer for Real-Time Stress Detection from ECG Signal
AU - Chandrasekaran, Sanjeev Tannirkulam
AU - Bhanushali, Sumukh Prashant
AU - Banerjee, Imon
AU - Sanyal, Arindam
N1 - Funding Information:
Manuscript received May 18, 2020; revised July 28, 2020; accepted August 11, 2020. Date of publication August 17, 2020; date of current version September 3, 2020. This article was approved by Associate Editor Paul Walsh. This work was supported by the Air Force Research Laboratory under Agreement FA8650-18-2-5402. (Corresponding author: Sanjeev Tannirkulam Chandrasekaran.) Sanjeev Tannirkulam Chandrasekaran, Sumukh Prashant Bhanushali, and Arindam Sanyal are with the Department of Electrical Engineering, University at Buffalo, Buffalo, NY 14260 USA (e-mail: stannirk@buffalo.edu).
Publisher Copyright:
© 2018 IEEE.
PY - 2020
Y1 - 2020
N2 - This letter presents the first on-chip bio-inspired reservoir computer (RC) prototype implemented in a 65-nm CMOS. The RC comprises 50 time-multiplexed neurons, and each neuron embeds a strong nonlinearity in a feedback loop. The RC applies a nonlinear transformation to the input and projects it to high-dimensional space, thus allowing linear separation by a simple logistic-regression (LR) layer implemented off-chip. We demonstrate real-time stress detection from electrocardiogram (ECG) signals using the RC. The RC achieves 93% classification accuracy which is 6% better than the state-of-the-art digital classifiers. Operating at 40 kHz, the prototype consumes 27.5 nJ/classification which is 7× lower than the state-of-the-art ECG processors performing similar complexity classification task.
AB - This letter presents the first on-chip bio-inspired reservoir computer (RC) prototype implemented in a 65-nm CMOS. The RC comprises 50 time-multiplexed neurons, and each neuron embeds a strong nonlinearity in a feedback loop. The RC applies a nonlinear transformation to the input and projects it to high-dimensional space, thus allowing linear separation by a simple logistic-regression (LR) layer implemented off-chip. We demonstrate real-time stress detection from electrocardiogram (ECG) signals using the RC. The RC achieves 93% classification accuracy which is 6% better than the state-of-the-art digital classifiers. Operating at 40 kHz, the prototype consumes 27.5 nJ/classification which is 7× lower than the state-of-the-art ECG processors performing similar complexity classification task.
KW - Electrocardiogram (ECG) sensor
KW - machine learning (ML)
KW - reservoir computing
KW - stress detection
UR - http://www.scopus.com/inward/record.url?scp=85091119851&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85091119851&partnerID=8YFLogxK
U2 - 10.1109/LSSC.2020.3016924
DO - 10.1109/LSSC.2020.3016924
M3 - Article
AN - SCOPUS:85091119851
SN - 2573-9603
VL - 3
SP - 290
EP - 293
JO - IEEE Solid-State Circuits Letters
JF - IEEE Solid-State Circuits Letters
M1 - 9169659
ER -