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

Autor: Sadasivuni S; Electrical Engineering, University at Buffalo, Buffalo, 14260, USA., Bhanushali SP; School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, 85287, USA., Banerjee I; Mayo Clinic, Phoenix, 85054, USA., Sanyal A; School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, 85287, USA. arindam.sanyal@asu.edu.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2022 Oct 29; Vol. 12 (1), pp. 18253. Date of Electronic Publication: 2022 Oct 29.
DOI: 10.1038/s41598-022-23100-4
Abstrakt: 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 [Formula: see text] with test-chips prototyped in 65 nm CMOS.
(© 2022. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje