Respiro: Continuous Respiratory Rate Monitoring During Motion via Wearable Ultra-Wideband Radar
summary
The gist
Deviations in respiratory rate often precede abnormalities in other vital signs Respiro: Continuous Respiratory Rate Monitoring During Motion via Wearable Ultra-Wideband Radar Our method extracted…
In short
Respiro is a wearable device using off-the-shelf ultra-wideband (UWB) radar to monitor respiratory rate while people move. The system processes complex radar signals to extract breathing patterns, achieving accuracy better than accelerometer-based methods during activity. This shows UWB radar can provide unobtrusive and effective respiratory monitoring in everyday life.
Key concepts
- Ultra-Wideband (UWB) Radar
- This is a type of radar technology that uses very short pulses across a wide range of frequencies. It's used here because it allows the device to detect subtle changes in the body's movement and breathing without being overly sensitive to general motion, making it suitable for wearable use.
- Complex Channel Impulse Response (CIR)
- The CIR is a mathematical representation of how a signal travels through an environment. In this study, researchers compute its magnitude to extract information about the wearer's respiratory signal from these complex measurements. This step is crucial for turning raw radar data into meaningful breathing information.
- Cross-correlation Maximization
- This is a technique used in data processing to align different sets of measurements. Since the raw radar signals are not perfectly aligned, this method shifts one signal relative to another until they match best. This helps ensure that the extracted respiratory rate calculation is accurate despite movement.
- Ground Truth
- Ground truth refers to the true, known value of a measurement against which a system's performance is compared. In this experiment, researchers used a spirometer as the ground truth to verify how accurately their Respiro device measured the actual respiratory rate.
Terminology used across episodes
This episode discusses
- Respiro: Continuous Respiratory Rate Monitoring During Motion via Wearable Ultra-Wideband Radar · Paper Radio
- Band-of-Interest-based Channel Impulse Response Fusion for Breathing Rate Estimation with UWB
The paper
Respiro: Continuous Respiratory Rate Monitoring During Motion via Wearable Ultra-Wideband Radar · Read on arXiv
Sebastian Reidy, Manuel Meier, Christian Holz
Department of Computer Science, ETH Zurich
Deviations in respiratory rate often precede abnormalities in other vital signs. However, continuously monitoring respiratory rates outside clinical settings remains challenging due to the obtrusive nature and sensitivity to body motions in existing monitoring approaches. In this study, we propose a single-point-of-contact wearable device that leverages off-the-shelf, consumer-grade ultra-wideband radar to monitor respiratory rate as part of a chest strap. Our signal processing pipeline reliably extracts the wearer's respiratory signal from windowed complex channel impulse responses. In a controlled experiment, twelve participants performed various activities to evaluate the system's accuracy under motion while capturing ground-truth recordings through a spirometer. Our method extracted respiratory rates with less than 1 breath per minute deviation in 71% of all measurements, averaging 1.11 breaths per minute across all sessions and participants. Our findings underscore the potential of consumer-grade ultra-wideband radar technology in body-worn devices for unobtrusive yet effective respiratory monitoring.
DOI: 10.1109/BHI62660.2024.10913592
Transcript
Introduction to the show: ident: Electrical Engineering. The day in electrical engineering: signals, systems and the hardware that carries them.
Rosa: I'm Rosa.
Dev: And I'm Dev, here with Taro.
Rosa: We're looking at the paper: "Respiro: Continuous Respiratory Rate Monitoring During Motion via Wearable Ultra-Wideband Radar".
Dev: Here's the gist of the paper. Deviations in respiratory rate often precede abnormalities in other vital signs Respiro: Continuous Respiratory Rate Monitoring During Motion via Wearable Ultra-Wideband Radar Our method extracted respiratory rates with less than 1 breath per minute deviation in 71% of all measurements Page 6, Table I shows the aggregated results of the user study categorized by activity.
Rosa: Our findings underscore the potential of consumer-grade ultra-wideband radar technology in bodyworn devices for unobtrusive yet effective respiratory monitoring Page 6, V.
Dev: DISCUSSION.
Rosa: System Proposal and Methodology The study proposes Respiro, a single-point-of-contact wearable device that leverages off-the-shelf, consumergrade ultra-wideband radar to monitor respiratory rate as part of a chest strap Page 1, Abstract—Deviations in respiratory rate often precede abnormalities in other vital signs..
Paper summary: Taro: So, to wrap up on the "Respiro: Continuous Respiratory Rate Monitoring During Motion via Wearable Ultra-Wideband Radar" paper, the authors present this single point of contact wearable UWB radar system for tracking respiratory rate. They claim that their method works during activities where it is less prone to motion artifacts compared to methods based on accelerometers.
Dev: And when compared with ground truth reference measurements, they found that their method performs on par and sometimes better than more complex measuring methods while being less prone to motion artifacts than accelerometer based approaches.
Rosa: It seems like the implication is that we can get continuous respiratory rate monitoring in everyday life using UWB radar. This paper shows it works during activities where it's less prone to motion artifacts, which is important for real world use outside of a lab setting.
Taro: The paper also flags a limitation: they only evaluated this method using IMU based baseline algorithms, and most contact based methods require extra hardware like custom antennas.
Dev: So the work suggests that consumer grade ultra wideband radar technology has potential for body worn devices for unobtrusive yet effective respiratory monitoring. It’s a system that works during specific movements but needs more research on different types of movement and perhaps more diverse participant groups before it becomes standard equipment.
Conclusion: Rosa: So, we're wrapping up on Respiro, which is about tracking your breathing continuously even when you're moving around using this wearable UWB radar system.
Dev: Right, so the core of it is that this chest strap setup uses consumer grade radar to pick up the wearer's breathing rate without needing a lot of complex stuff on the outside.
Rosa: The authors, they’re showing how this works during activities where it’s usually tricky for other motion sensors, like walking or running.
Dev: And what they found is that their method gets pretty close to the truth, with less than one breath per minute deviation in seventy-one percent of all the measurements they took.
Rosa: So, it sounds like a way to get real-time breathing data without needing a complicated setup or constant manual checks.
Dev: That’s what it promises, but we gotta remember they only tested this system during specific activities and with twelve healthy adults, which is a small sample size and not really outside of the lab setting yet.
Rosa: Yeah, so the big question is whether this works reliably when someone's actually doing something unpredictable in their daily life.
Dev: And that brings us to how it stacks up against other things, like accelerometers, and how accurate it is when they compare it to a spirometer for ground truth data.
Rosa: It seems like the authors are really pointing toward UWB radar as a promising tool for unobtrusive monitoring that doesn't get in the way of what you're actually doing.
Dev: Exactly, but we still need to see how this holds up when people have different body types or are doing things that aren't exactly those controlled activities they tested.
Rosa: Right, so the next step is figuring out if this system can handle the messiness of real life movements and what kind of real-world monitoring it could actually do.
More episodes
- Daily Summary for 2026-11-19
- 2111.07910-Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction
- 2203.02149-HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging
- 2205.10102-Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging
- 2311.10959-Structure-Aware Sparse-View X-ray 3D Reconstruction
- 2403.04116-Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis
- 2410.02572-Combining Pre- and Post-Demosaicking Noise Removal for RAW Video
- 2604.17453-Learned Nonlocal Feature Matching and Filtering for RAW Image Denoising
- 2603.20387-End-to-End Multi-Task Learning for Adjustable Joint Noise Reduction and Hearing Loss Compensation
- 2507.20825-Chirp-Permuted AFDM: A Versatile and Multifunctional Waveform for 6G