A candidate-based causal Viterbi estimator with a learned accept/hold/reject reporting policy reduces motion-window heart-rate MAE from ≈10.8 to 6.2 BPM at 50% coverage on ring PPG and improves reported-window accuracy on PPG-DaLiA.
Sensors , volume =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CITRUS: Candidate Inference and Temporal-tracking for Reliable, Unobtrusive Sensing of Wearable Heart Rate under Motion
A candidate-based causal Viterbi estimator with a learned accept/hold/reject reporting policy reduces motion-window heart-rate MAE from ≈10.8 to 6.2 BPM at 50% coverage on ring PPG and improves reported-window accuracy on PPG-DaLiA.