Heart Rate Monitoring Using Continuous-Wave Radar in Home Environment

Radar-based, contactless in-home vital sign monitoring can significantly improve the healthcare of the rapidly growing aging population by enabling early detection of clinical events and continuous tracking of physiological states, while maintaining privacy, comfort, and user compliance. We introduce a unique experimental environment, collected for over a year – consisting of populated test homes, equipped with arrays of continuous-wave radar sensors placed on ceilings and walls, with occupants engaged in everyday activities within the homes. We applied and compared multiple analytical methods to extract heart rate from the radar data, using combinations of normalized cross-correlation (NXC), machine learning with individual sensors, and sensor fusion. Our results show that sensor fusion leads to the lowest mean absolute errors, reduced by over 30% from single-sensor machine learning models and over 80% from NXC. We additionally observed that a dense sensor array design enhances signal quality and reduces noise by more than 15%, providing more accurate heart rate monitoring even during dynamic activities, such as jumping and walking. These results highlight the effectiveness of sensor fusion and dense array designs in real-world settings. Our novel experimental platform and analytical results represent a meaningful step toward scalable application of radar technology in real residential settings for non-contact health monitoring.