Flexible, Self-Adaptive Sense-and-Compress SoC for Sub-microWatt Always-On Sensory Recording

Jaro De Roose (Corresponding author), Haoming Xin, Ahmed Hallawa, Gerd Ascheid, Pieter J.A. Harpe, Marian Verhelst

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

We present a 5-sensor, fully integrated sensing system with interchangeable sensors and programmable configuration to create a sub-microWatt multisensor node that can tackle a wide range of sensing applications. Furthermore, the sensor node is capable of autonomously adapting its configuration to the application requirements hence minimizing system power. Such self-reconfiguration is enabled at low overhead by developing an automated offline optimization strategy, in combination with an autonomous embedded configuration controller, using the concept of behavioral trees (BTs). The resulting fully integrated platform consumes a maximum of 321 nW when sampling at 500 Hz and 3025 nW at 8 kHz. Furthermore, we demonstrate the end-to-end autonomous optimization flow for two different applications exploiting different sensors: 1) human activity recognition using accelerometers and 2) machine listening using a microphone. Both use cases demonstrate that the introduced system and methodology reduces the power by more than a factor 2 without losing significant application detection accuracy.

Original languageEnglish
Article number9171886
Pages (from-to)362-365
Number of pages4
JournalIEEE Solid-State Circuits Letters
Volume3
DOIs
Publication statusPublished - 2020

Keywords

  • Automated optimization
  • behavioral tree (BT)
  • flexible sensor node
  • low overhead flexible hardware
  • ultralow power

Fingerprint Dive into the research topics of 'Flexible, Self-Adaptive Sense-and-Compress SoC for Sub-microWatt Always-On Sensory Recording'. Together they form a unique fingerprint.

Cite this