Cylindrical geodesic flow improves wearable heart signal translation
Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation
Artificial Intelligence
Summary
Wearable devices often measure heart signals from different body spots, but these signals can look different and are tricky to match up. The authors found that existing methods don’t handle the circular nature of heartbeats well, leading to errors when translating one signal into another. They created a new way that respects the natural shape and timing of these signals, improving accuracy. Their approach works better than other methods on tasks involving pulse and heart sound data.
What this means in practice
- •For wearable device engineers: Improve the accuracy of translating heartbeat signals between different sensor locations on the body for better cardiovascular monitoring.
- •For biomedical signal processing teams: Enhance algorithms for reconstructing target cardiac waveforms from varying sensor inputs with less distortion and alignment errors.
Authors
Onur Selim Kilic, Afra Nawar, Cem Okan Yaldiz, Michael J. Cho, Ahmet Rasim Emirdagi, Demet Tangolar, Amirali Aghazadeh, Amit J. Shah, Omer T. Inan
Abstract
Paired translation between quasiperiodic physiological waveforms (i.e., recovering a target oscillatory signal from the source) is central to the interpretation of cardiovascular signals derived from wearables placed at different body locations. This source-to-target mapping in these problems carries inherent geometric structure: the phase wraps around the cycle and must be treated as a circular variable, the amplitude remains strictly positive, and the beat-to-beat alignment can drift unpredictably across cycles and subjects. While deep neural networks have been used for phase estimation and complex-valued signal modeling, prior work does not explicitly learn phase transport between paired signals. Consequently, neither endpoint-supervised regression nor the standard affine path used in flow matching accounts for this phase--amplitude structure. We introduce \emph{cylindrical geodesic flow matching} for paired cardiovascular waveform translation. We show that the standard affine path used in flow matching distorts intermediate amplitude and instantaneous frequency when interpolating between quasiperiodic signals; replacing it with a closed-form geodesic on the phase--amplitude cylinder eliminates these artifacts and converts each training pair into dense, geometry-consistent velocity supervision. On zero-shot photoplethysmography and limited-support seismocardiography adaptation benchmarks, our method consistently outperforms interpolation baselines and matches or exceeds direct supervised prediction, reducing Hilbert Transform, $L_2$, and Dynamic Time Warping distance by up to ${\sim}15\%$ over the strongest competing baseline. These results suggest that bridge geometry is a critical inductive bias for flow matching on oscillatory signal translation.