In-Ear PPG for Vital Signs

Earables are now pervasive, and their established purpose, ergonomy, and noninvasive interaction uncover exciting opportunities for sensing and healthcare research. However, it is critical to understand and characterize sensory measurements’ accuracy in earables impacting healthcare decisions. We re...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE pervasive computing 2022-01, Vol.21 (1), p.65-74
Hauptverfasser: Ferlini, Andrea, Montanari, Alessandro, Min, Chulhong, Li, Hongwei, Sassi, Ugo, Kawsar, Fahim
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Earables are now pervasive, and their established purpose, ergonomy, and noninvasive interaction uncover exciting opportunities for sensing and healthcare research. However, it is critical to understand and characterize sensory measurements’ accuracy in earables impacting healthcare decisions. We report a systematic characterization of in-ear photoplethysmography (PPG) in measuring vital signs: heart rate (HR), heart rate variability (HRV), blood oxygen saturation (SpO_22), and respiration rate (RR). We explore in-ear PPG inaccuracies stemming from different sensor placements and motion-induced artifacts. We observe statistically significant differences across sensor placements and between artifact types, with ITC placement showing the lowest intersubject variability. However, our study shows the absolute error climbs up to 29.84, 24.09, 3.28, and 30.80%, respectively, for HR, HRV, SpO_22, and RR during motion activities. Our preliminary results suggest that in-ear PPG is reasonably accurate in detecting vital signs but demands careful mechanical design and signal processing treatment.
ISSN:1536-1268
1558-2590
DOI:10.1109/MPRV.2021.3121171