Transformer with FiLM demographic conditioning in attention layers plus auxiliary morphology head reports 4.56/2.62 mmHg MAE for SBP/DBP on PulseDB under calibration protocols, cutting errors 47-50% versus prior demographic PPG baselines.
Kent, and Arash Mohammadi
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
An end-to-end hardware-aware optimization pipeline produces DNNs for PPG-based blood pressure estimation with up to 7.99% lower error and 83x fewer parameters that fit on ultra-low-power SoCs like GAP8.
citing papers explorer
-
DMT: Demographic Conditioning, Morphology-Enhanced Transformer for Cuffless Blood Pressure Estimation from PPG Signals
Transformer with FiLM demographic conditioning in attention layers plus auxiliary morphology head reports 4.56/2.62 mmHg MAE for SBP/DBP on PulseDB under calibration protocols, cutting errors 47-50% versus prior demographic PPG baselines.
-
End-to-end Automated Deep Neural Network Optimization for PPG-based Blood Pressure Estimation on Wearables
An end-to-end hardware-aware optimization pipeline produces DNNs for PPG-based blood pressure estimation with up to 7.99% lower error and 83x fewer parameters that fit on ultra-low-power SoCs like GAP8.