Ceiling-Mounted FMCW vs. IR-UWB vs. Wi-Fi Radar: A Controlled Comparison for Human Activity Recognition and Sleep Monitoring

Forum topic · 小凯 · 2026-08-22

Summary

This arXiv paper (2608.20322) by Anton Lambrecht, Reda El Hail, Xianjun Jiao, and Pieter Crombez presents a controlled comparison of ceiling-mounted FMCW radar, IR-UWB, and Wi-Fi sensing for contactless health monitoring. The authors collected synchronized recordings from 20 participants across six room layouts, then evaluated all three radio technologies with the same CNN on two tasks: fine-grained 10-class human activity recognition and coarse-grained 4-class sleep monitoring. IR-UWB achieved the best cross-subject activity recognition (89.0% macro F1), while FMCW radar generalized best to unseen room layouts (83.8% macro F1). For sleep monitoring, all technologies exceeded 92% macro F1 in unseen environments. The findings reveal a fundamental trade-off between recognition performance and environmental robustness, explained by differences in range resolution, antenna diversity, Doppler resolution, and spatial information preservation.

Paper Overview

Field: Machine Learning Authors: Anton Lambrecht, Reda El Hail, Xianjun Jiao, Pieter Crombez arXiv: 2608.20322

Abstract

Although RF-based contactless health monitoring is increasingly important, different radio technologies (FMCW radar, IR-UWB, and Wi-Fi sensing) are rarely compared under identical deployment conditions. Moreover, the performance of ceiling-mounted radar, despite its practical and cost advantages in real deployments, remains underexplored.

This paper presents a controlled comparison of FMCW, IR-UWB, and Wi-Fi sensing using synchronized recordings of 20 participants across six room layouts. All technologies were evaluated with the same CNN on:

Fine-grained human activity recognition: 10 activity classes
Coarse-grained sleep monitoring: 4 classes

Key Findings

IR-UWB achieved the best cross-subject activity recognition performance: 89.0% macro F1
FMCW radar generalized best to unseen room layouts: 83.8% macro F1
For sleep monitoring, all technologies exceeded 92% macro F1 in unseen environments

Discussion

The results reveal a fundamental trade-off between recognition performance and environmental robustness. The authors explain this trade-off through differences in range resolution, antenna diversity, Doppler resolution, and spatial information preservation across the three radio technologies.

---

*Source: arXiv:2608.20322*