On-Chip Processing-Assisted TinyML for Heart Rate Monitoring Using Noncontact Ballistocardiogram-Based Bed Sensor

Heart rate monitoring (HRM) serves as a fundamental component of healthcare systems, providing essential insights into cardiovascular function and overall physiological status. Conventional HRM systems commonly rely on contact-based sensing modalities, such electrocardiogram (ECG) and photoplethysmogram (PPG) wearables, which require direct skin contact and complex wiring. This work presents a non-contact ballistocardiogram (NCBCG) bed sensor system integrated with tiny machine learning (TinyML) to provide on-chip processing for non-contact HRM. The proposed system incorporates a polyvinylidene fluoride (PVDF) film sensor placed beneath the mattress, enabling comfortable, non-intrusive, and continuous monitoring. We design a TinyML model offers on-chip processing on a microcontroller unit (MCU), reducing dependency on cloud-based or external. Experimental findings demonstrate that the system achieves the accurate heart rate estimation, which is compliant with AAMI standard. These results highlight the feasibility and reliability for accurate heart rate estimation using embedded artificial intelligence. The work demonstrates potential for real-world applications in long-term remote healthcare and home-based monitoring.