Why the study?
Signal envelopes contain important features for machine learning applications, but conventionally raw analog signals are digitized before feature extraction in the digital domain.
The proposed ultra-low-power envelope-to-digital converter achieves 7.1 effective bits of resolution while consuming only 9.6 nW, demonstrating potential for low-power respiratory monitoring applications.
May enable low-power wearable respiratory monitoring; leaves open clinical validation in cardiovascular care.
The signal’s envelope contains important features for a host of applications empowered by machine learning algorithms. Conventionally, the raw analog signal is digitized first, followed by feature extraction in the digital domain. This brief presents an ultra-low-power envelope-to-digital converter (EDC), with respiratory monitoring as one of its applications. The EDC consists of a passive switched-capacitor envelope detector and an inseparable successive-approximation-register analog-to-digital converter (ADC). The two blocks at different sampling rates directly integrate without a buffer between them thanks to a ping-pong operation of their sampling capacitors. An EDC prototype was fabricated in a 180-nm CMOS. It provides 7.1 effective bits of ADC resolution and supports input signal bandwidth up to 5 kHz and an envelope bandwidth up to 50 Hz while consuming 9.6 nW.
No takes yet. Share an insight, caveat, or question.
Shi et al. (2019) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: