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’… Click to show full abstract
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$_2$2), and respiration rate (RR). We explore in-ear PPG inaccuracies stemming from different sensor placements and motion-induced artifacts. We observe statistically significant differences across sensor placements and between artifact types, with ITC placement showing the lowest intersubject variability. However, our study shows the absolute error climbs up to 29.84, 24.09, 3.28, and 30.80%, respectively, for HR, HRV, SpO$_2$2, 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.
               
Click one of the above tabs to view related content.