---
title: "顶置 FMCW、IR-UWB 与 Wi-Fi 雷达在卧室人体活动监测与睡眠中断检测中的对比研究"
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 雷达","IR-UWB","Wi-Fi 感知","人体活动识别","无接触射频感知","睡眠监测"]
---

# 顶置 FMCW、IR-UWB 与 Wi-Fi 雷达在卧室人体活动监测与睡眠中断检测中的对比研究

## AI 点评

> 这篇论文最难得的是把三种无接触射频方案拉进同一个实验框架里做公平对比，结果直指工程核心矛盾：精度和环境鲁棒性不可兼得。对做卧室睡眠监测或养老看护产品的团队来说，FMCW 在未知环境下的泛化优势尤其值得重视，因为它可能比实验室里的 F1 值更接近真实部署表现。

## 速览

本文在统一实验条件下对比了顶置 FMCW、IR-UWB 雷达与 Wi-Fi 感知在卧室场景中的无接触人体活动监测与睡眠中断检测能力。研究采集 20 名受试者在 6 种房间布局下的同步数据，用同一 CNN 完成 10 类活动识别和 4 类睡眠监测。结果显示，IR-UWB 跨受试者识别最优（89% F1），FMCW 对未知环境泛化最佳（83.8%），睡眠监测均超 92% F1，并揭示了精度与鲁棒性之间的权衡。

## 关键点

- 首次在统一部署条件下对比三种顶置 RF 传感技术，使用 20 名受试者和 6 种房间布局的同步数据。
- IR-UWB 在跨受试者 10 类活动识别中取得 89.0% macro F1，FMCW 对未见房间布局泛化最佳（83.8%）。
- 睡眠监测任务上三种技术均超过 92% macro F1，支持无接触健康监测应用。
- 揭示识别性能与环境鲁棒性之间的根本权衡，与距离分辨率、天线分集、多普勒分辨率及空间信息保留相关。

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_d25623ebaaffd36dedc6d93c