New SIFPBPNet model improves cuffless blood pressure estimation

Researchers have developed a novel dual-path network called SIFPBPNet for estimating blood pressure using wearable photoplethysmography (PPG) signals. This network addresses population heterogeneity by separately processing steady-state and instantaneous features. The steady-state path utilizes a graph attention network to capture long-term individual characteristics, while the instantaneous path focuses on short-term dynamics and integrates the steady-state information via cross-attention. Experiments on a large dataset showed SIFPBPNet achieved a Mean Absolute Error of 8.57 mmHg for systolic and 5.97 mmHg for diastolic blood pressure, outperforming existing methods. AI

IMPACT This new model could lead to more accurate and personalized cuffless blood pressure monitoring devices.

RANK_REASON The cluster contains a research paper detailing a new model for a specific task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• graph attention network
• Instantaneous Feature Path
• photoplethysmography
• SIFPBPNet
• Steady-state Feature Path

• paper
• model release
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →