mmHRR: Monitoring Heart Rate Recovery with Millimeter Wave Radar

Abstract: Heart rate recovery (HRR) within the initial minute following exercise is a widely utilized metric for assessing cardiac autonomic function in individuals and predicting mortality risk in patients with cardiovascular disease. However, prevailing solutions for HRR monitoring typically involve the use of specialized medical equipment or contact wearable sensors, resulting in high costs and poor user experience. In this paper, we propose a contactless HRR monitoring technique, mmHRR, which achieves accurate heart rate (HR) estimation with a commercial mmWave radar. Unlike HR estimation at rest, the HR varies quickly after exercise and the heartbeat signal entangles with the respiration harmonics. To overcome these hurdles and effectively estimate the HR from the weak and non-stationary heartbeat signal, we propose a novel signal processing pipeline, including dynamic target tracking, adaptive heartbeat signal extraction, and accurate HR estimation with composite sliding windows. Real-world experiments demonstrate that mmHRR exhibits exceptional robustness across diverse environmental conditions, and achieves an average HR estimation error of 3.31 bpm (beats per minute), 71% lower than that of the state-of-the-art method.

mmHRR: Monitoring Heart Rate Recovery with Millimeter Wave Radar

The paper "mmHRR: Monitoring Heart Rate Recovery with Millimeter Wave Radar" (2503.22202) introduces mmHRR, a system utilizing millimeter wave radar to achieve contactless monitoring of heart rate recovery (HRR) following exercise. This paper aims to address the limitations in traditional HRR monitoring systems, including high costs and the discomfort associated with wearable devices, by employing commercial off-the-shelf (COTS) mmWave radar.

Introduction to mmHRR

HRR is a critical measure for evaluating cardiac autonomic function and predicting mortality risk for cardiovascular disease patients. However, traditional HRR monitoring methods utilizing medical equipment and wearable sensors are expensive and often uncomfortable. mmHRR proposes a solution by leveraging mmWave radar to monitor HRR contactlessly and accurately. Following exercise, HR decreases rapidly, posing challenges for accurate monitoring due to a non-stationary heartbeat signal entangled with respiratory harmonics.

System Architecture and Design

mmHRR implements a sophisticated signal processing pipeline to extract the heartbeat signal from radar data, which includes challenges posed by respiratory harmonics.

Signal Preprocessing

The method begins by extracting chest motion data from radar reflections and applying filtering techniques to attenuate background noise, emphasizing the frequency domain characteristics of heartbeat signals. This precision is crucial in isolating the weak signal caused by the heartbeat amidst ambient noise.

Figure 1: Non-stationary property of heartbeat signal and interference of respiratory harmonics on heartbeat estimation.

Heartbeat Signal Extraction

The paper models chest movement and utilizes an enhanced variational mode decomposition (VMD) algorithm to separate respiratory harmonics from the heartbeat signal. VMD is optimized using a correlation coefficient and energy loss coefficient to balance bandwidth constraints and resolve mode aliasing issues effectively.

Figure 2: The decomposition result when encountering mode aliasing.

Heart Rate Estimation

Heartbeat estimation employs a peak counting algorithm within adaptive-sized sliding windows, allowing precise synchronization with the dynamic heart rate changes post-exercise. This method dynamically adjusts based on real-time peak data to ensure accurate HR estimation.

Figure 3: The composite sliding windows algorithm of mmHRR.

Evaluation and Results

The system was rigorously tested with 14 healthy users performing controlled exercise routines. Compared to state-of-the-art methods, mmHRR significantly reduces average HR estimation error, demonstrating robustness under diverse conditions, including varying user postures, distances, and angles from the radar.

Figure 4: Overall performance.

Figure 5: Performance at different distances.

The evaluation emphasizes mmHRR's capability in reliably estimating HRR in various indoor environments, confirming its practical utility beyond laboratory conditions.

Implications and Future Work

mmHRR offers a promising contactless solution for HRR monitoring, showing potential for broader application in home and clinical settings. Future work could explore enhancements in signal processing algorithms to further minimize errors and adaptability to dynamic heart rate variations. Additional studies may also investigate the integration of mmHRR with other health monitoring systems to provide comprehensive cardiac assessments.

Conclusion

mmHRR represents a significant advancement in contactless HRR monitoring technologies, achieving accurate HR estimation and outperforming conventional methods in terms of user comfort and setup convenience. The integration of mmWave radar into health monitoring opens avenues for innovations in non