Heart Rate Variability Monitoring Based on Doppler Radar Using Deep Learning

Within the context of a smart home, detecting the operating status of appliances in the environment plays a pivotal role, estimating power consumption, issuing overuse reminders, and identifying faults. The traditional contact-based approaches require equipment updates such as incorporating smart sockets or high-precision electric meters. Non-constant approaches involve the use of technologies like laser and Ultra-Wideband (UWB) radar. The former can only monitor one appliance at a time, and the latter is unable to detect appliances with extremely tiny vibrations and tends to be susceptible to interference from human activities. To address these challenges, we introduce HomeOSD, an advanced appliance status-detection system that uses mmWave radar. This innovative solution simultaneously tracks multiple appliances without human activity interference by measuring their extremely tiny vibrations. To reduce interference from other moving objects, like people, we introduce a Vibration-Intensity Metric based on periodic signal characteristics. We present the Adaptive Weighted Minimum Distance Classifier (AWMDC) to counteract appliance vibration fluctuations. Finally, we develop a system using a common mmWave radar and carry out real-world experiments to evaluate HomeOSD’s performance. The detection accuracy is 95.58%, and the promising results demonstrate the feasibility and reliability of our proposed system.

HomeOSD: Appliance Operating-Status Detection Using mmWave Radar

Sheng,

Li,

et al. 2024

Feasibility of Early Assessment for Psychological Distress: HRV-Based Evaluation Using IR-UWB Radar

Lee,

Ahmed

et al. 2024

Mental distress-induced imbalances in autonomic nervous system activities adversely affect the electrical stability of the cardiac system, with heart rate variability (HRV) identified as a related indicator. Traditional HRV measurements use electrocardiography (ECG), but impulse radio ultra-wideband (IR-UWB) radar has shown potential in HRV measurement, although it is rarely applied to psychological studies. This study aimed to assess early high levels of mental distress using HRV indices obtained using radar through modified signal processing tailored to reduce phase noise and improve positional accuracy. We conducted 120 evaluations on 15 office workers from a software startup, with each 5 min evaluation using both radar and ECG. Visual analog scale (VAS) scores were collected to assess mental distress, with evaluations scoring 7.5 or higher classified as high-mental distress group, while the remainder formed the control group. Evaluations indicating high levels of mental distress showed significantly lower HRV compared to the control group, with radar-derived indices correlating strongly with ECG results. The radar-based analysis demonstrated a significant ability to differentiate high mental distress, supported by receiver operating characteristic (ROC) analysis. These findings suggest that IR-UWB radar could be a supportive tool for distinguishing high levels of mental stress, offering clinicians complementary diagnostic insights.

Radar-Based Heart Cardiac Activity Measurements: A Review

Frazao,

Pinho,

Albuquerque

2024

In recent years, with the increased interest in smart home technology and the increased need to remotely monitor patients due to the pandemic, demand for contactless systems for vital sign measurements has also been on the rise. One of these kinds of systems are Doppler radar systems. Their design is composed of several choices that could possibly have a significant impact on their overall performance, more specifically those focused on the measurement of cardiac activity. This review, conducted using works obtained from relevant scientific databases, aims to understand the impact of these design choices on the performance of systems measuring either heart rate (HR) or heart rate variability (HRV). To that end, an analysis of the performance based on hardware architecture, carrier frequency, and measurement distance was conducted for works focusing on both of the aforementioned cardiac parameters, and signal processing trends were discussed. What was found was that the system architecture and signal processing algorithms had the most impact on the performance, with FMCW being the best performing architecture, whereas factors like carrier frequency did not have an impact.This means that newer systems can focus on cheaper, lower-frequency systems without any performance degradation, which will make research easier.