Less is More: The Dilution Effect in Multi-Link Wireless Sensing

2026-02-11

AI Summary

This study challenges the prevailing assumption in wireless sensing that “more links are better” by investigating whether dense deployments genuinely improve human activity detection accuracy. Deploying a 9-node ESP32-C3 mesh network (72 links) in a real residential environment, the authors conducted a 12-day in-situ experiment to systematically compare single-link and multi-link fusion performance. They identify and name a previously unreported “dilution effect,” wherein irrelevant links introduce noise that overwhelms useful signals, causing fused performance to fall below that of a single high-quality link (AUC 0.541 vs. 0.489; Cohen’s d = 0.86). The study further reveals that link placement influences performance far more than classifier choice, with no significant difference between random and optimized link selection (p = 0.35). The authors publicly release 312 hours of labeled CSI data and associated code.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

Wireless sensing approaches promise to transform smart infrastructures into privacy-preserving motion detectors, yet commercial adoption remains limited. A common assumption may explain this gap: that denser sensor deployments yield better accuracy. We tested this assumption with a 12-day naturalistic study using a 9-node ESP32-C3 mesh (72 sensing links) in a residential environment. Our results show that a single well-placed link outperformed the full 72-link mesh (AUC 0.541 vs. 0.489, Cohen's $d$=0.86). Even a random link selection matched optimized selection ($p$=0.35). The benefit comes from avoiding multi-link fusion, not from choosing the right link. We attribute this to a "dilution effect": links whose Fresnel zones miss activity regions contribute noise that overwhelms signal from informative links. In our deployment, strategic link placement mattered 2.7$\times$ more than classifier choice. We release 312 hours of labeled CSI data, firmware, and analysis code to enable validation across diverse environments.

Problem

• wireless sensing
• dilution effect
• multi-link deployment
• Fresnel zones
• channel state information

Innovation

• dilution effect
• wireless sensing
• link placement
• CSI
• multi-link fusion