---
title: "A Comparative Study of Ceiling-Mounted FMCW, IR-UWB and Wi-Fi Radar for In-Bedroom Human Activity Monitoring and Sleep Interruption Detection"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.20322v1"
permalink: "https://feed.astralor.com/items/itm_d25623ebaaffd36dedc6d93c"
published: "2026-08-20T17:58:22.000Z"
score: 77
channel: "ai"
tags: ["FMCW radar","IR-UWB","Wi-Fi sensing","Human Activity Recognition","Contact-free RF sensing","Sleep Monitoring"]
---

# A Comparative Study of Ceiling-Mounted FMCW, IR-UWB and Wi-Fi Radar for In-Bedroom Human Activity Monitoring and Sleep Interruption Detection

## AI commentary

> What makes this paper valuable is its fair head-to-head comparison of three contact-free RF approaches, exposing a core engineering trade-off between accuracy and environmental robustness. Teams building bedroom sleep monitoring or eldercare products should pay special attention to FMCW's generalization advantage in unseen rooms, as it may matter more in deployment than lab-only F1 scores.

## At a glance

This paper presents a controlled comparison of ceiling-mounted FMCW radar, IR-UWB, and Wi-Fi sensing for contact-free in-bedroom human activity monitoring and sleep interruption detection. Using synchronized recordings from 20 participants across six room layouts, the authors evaluate all three technologies with the same CNN on a fine-grained 10-class activity recognition task and a coarse 4-class sleep monitoring task. IR-UWB achieves the best cross-subject accuracy (89.0% macro F1), while FMCW generalizes best to unseen room layouts (83.8% macro F1). For sleep monitoring, all technologies exceed 92% macro F1. The results highlight a fundamental trade-off between recognition performance and environmental robustness, offering practical guidance for healthcare RF sensing system design.

## Key points

- First controlled comparison of three ceiling-mounted RF sensing technologies under identical deployment conditions, using 20 subjects and six room layouts.
- IR-UWB leads cross-subject activity recognition with 89.0% macro F1; FMCW generalizes best to unseen layouts at 83.8% macro F1.
- All technologies exceed 92% macro F1 on the sleep monitoring task, supporting contact-free health monitoring.
- Reveals a fundamental trade-off between recognition performance and environmental robustness, linked to range resolution, antenna diversity, Doppler resolution, and spatial information retention.

## Full text

Despite their growing importance for contact-free radio frequency (RF) based healthcare monitoring, different radio technologies such as frequency-modulated continuous wave (FMCW) radar, impulse radio ultra-wideband (IR-UWB), and Wi-Fi sensing are rarely compared under identical deployment conditions, as existing studies typically differ in hardware, datasets, and evaluation methodologies. In addition, the performance of ceiling-mounted radars, despite their practical deployment and cost advantages in healthcare environments, remain underexplored. Therefore, this paper presents a controlled comparison and analysis of ceiling-mounted FMCW, IR-UWB, and Wi-Fi sensing using synchronized recordings from 20 participants across six room layouts. All technologies are evaluated with the same convolutional neural network (CNN) on both a fine-grained 10-class human activity recognition (HAR) task and a coarse 4-class sleep monitoring task. IR-UWB achieves the highest cross-subject activity recognition performance (89.0% macro F1), while FMCW generalizes best to unseen room layouts (83.8% macro F1). For sleep monitoring, all technologies exceed 92% macro F1 in unseen environments. The results reveal a fundamental trade-off between recognition performance and environmental robustness, which can be explained through differences in range resolution, antenna diversity, Doppler resolution, and spatial information retention. These findings provide practical guidelines for the design of healthcare-oriented RF sensing systems.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_d25623ebaaffd36dedc6d93c