Abstract
A hydration reminder feature on a wearable device follows a timer or manual entries rather than systemic hydration, so reminders can arrive at the wrong time. To address these deficiencies, this disclosure describes a hydration reminder system in which micro-electrodes on a back plate of the device measure skin resistance. A micro-camera or a near-infrared (NIR) emitter and detector capture skin texture and spectral absorption. A pre-trained artificial intelligence (AI) hydration model fuses the electrical and optical readings with heart rate from a photoplethysmography (PPG) sensor or an electrocardiography (ECG) electrode and ambient conditions. The hydration model discriminates surface sweat from a change in skin moisture and computes a hydration index. The hydration reminder system can deliver a haptic and visual reminder when the hydration index falls below a personalized threshold. An intake log and feedback from the user can calibrate the hydration model on the device.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Chern, Yann-Cherng, "Wearable Hydration Reminder System Using Multi-Modal Skin Sensor Fusion and User-Guided On-Device Model Calibration", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/12018