In-sensor neural network for high energy efficiency analog-to-information conversion

Sudarsan Sadasivuni, Sumukh Prashant Bhanushali, Imon Banerjee, Arindam Sanyal

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

This work presents an on-chip analog-to-information conversion technique that utilizes analog hyper-dimensional computing based on reservoir-computing paradigm to process electrocardiograph (ECG) signals locally in-sensor and reduce radio frequency transmission by more than three orders-of-magnitude. Instead of transmitting the naturally sparse ECG signal or extracted features, the on-chip analog-to-information converter analyzes the ECG signal through a nonlinear reservoir kernel followed by an artificial neural network, and transmits the prediction results. The proposed technique is demonstrated for detection of sepsis onset and achieves state-of-the-art accuracy and energy efficiency while reducing sensor power by 159 × with test-chips prototyped in 65 nm CMOS.

Original languageEnglish (US)
Article number18253
JournalScientific reports
Volume12
Issue number1
DOIs
StatePublished - Dec 2022

ASJC Scopus subject areas

  • General

Fingerprint

Dive into the research topics of 'In-sensor neural network for high energy efficiency analog-to-information conversion'. Together they form a unique fingerprint.

Cite this