TY - GEN
T1 - 7.5nJ/inference CMOS Echo State Network for Coronary Heart Disease prediction
AU - Chandrasekaran, Sanjeev Tannirkulam
AU - Banerjee, Imon
AU - Sanyal, Arindam
N1 - Funding Information:
ACKNOWLEDGMENT This material is based on research sponsored by Air Force Research Laboratory under agreement number FA8650-18-2-5402. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation thereon. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of Air Force Research Laboratory or the U.S. Government.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - This work presents the first on-chip, mixed-signal echo state network (ESN) for early prediction of heart disease. The ESN comprises an input layer, a non-linear projection (NP) layer, and an output layer. Only the output layer of the ESN requires training. The input layer weights are time-invariant and drawn from a static binary random distribution. Thus, the proposed ESN has significantly lower trainable parameters compared to other non-linear neural networks used for similar prediction tasks. A 65nm prototype is validated with the Cleveland Heart Disease (CHD) dataset. The ESN achieves a mean accuracy of 84.6% over 5 test chips while consuming 7.5nJ energy/inference.
AB - This work presents the first on-chip, mixed-signal echo state network (ESN) for early prediction of heart disease. The ESN comprises an input layer, a non-linear projection (NP) layer, and an output layer. Only the output layer of the ESN requires training. The input layer weights are time-invariant and drawn from a static binary random distribution. Thus, the proposed ESN has significantly lower trainable parameters compared to other non-linear neural networks used for similar prediction tasks. A 65nm prototype is validated with the Cleveland Heart Disease (CHD) dataset. The ESN achieves a mean accuracy of 84.6% over 5 test chips while consuming 7.5nJ energy/inference.
KW - Machine learning
KW - cardiac diseases prediction
KW - data fusion and medical wearable
KW - echo state network
UR - http://www.scopus.com/inward/record.url?scp=85123440862&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85123440862&partnerID=8YFLogxK
U2 - 10.1109/ESSDERC53440.2021.9631777
DO - 10.1109/ESSDERC53440.2021.9631777
M3 - Conference contribution
AN - SCOPUS:85123440862
T3 - European Solid-State Device Research Conference
SP - 103
EP - 106
BT - ESSDERC 2021 - IEEE 51st European Solid-State Device Research Conference, Proceedings
PB - Editions Frontieres
T2 - 51st IEEE European Solid-State Device Research Conference, ESSDERC 2021
Y2 - 6 September 2021 through 9 September 2021
ER -