PoHAR: Understanding Hyperlocal Human Activities with Pollution Sensor Networks

2026-05-10

AI Summary

This work addresses the challenge of efficiently coordinating resource-constrained, low-power indoor air pollution sensor networks to recognize localized human activities while preserving privacy. It proposes the first ultra-local activity sensing approach based on air pollution measurements. The method employs conflict-free replicated data types for distributed state synchronization, dynamically identifies activity-relevant sensor groups through hierarchical clustering combined with a self-supervised distance metric, and leverages a leader election mechanism to collaboratively invoke lightweight off-the-shelf machine learning models for inference. Evaluated on hardware with limited computational resources, the framework achieves 97.41% overall activity recognition accuracy and 99.68% accuracy for cooking activity detection, with on-device inference latency under 34 microseconds, establishing a novel paradigm for privacy-preserving distributed collaborative sensing.

Abstract

Low-cost air quality sensors are becoming ubiquitous in our daily lives as public awareness of air pollution continues to grow, and people take measures to monitor and improve the air they breathe indoors. Besides the standard operation of these sensors, fluctuations in environmental parameters can be leveraged to understand human behavior and activities in indoor spaces. Unlike traditional audio-visual, Radio Frequency, and inertial sensors, air quality sensors are easily scalable to a household, are privacy-preserving, and more economical. Such distributed sensor networks must jointly make decisions to monitor indoor occupants for downstream smart home and healthcare applications. However, due to low processing power, memory, and energy, they often struggle to maintain distributed data consensus and identify activity-affected sensor groups for accurate on-device inference. In this paper, we propose PoHAR framework that implements: (i) a conflict-free replicated data primitive for data sharing, (ii) a hierarchical clustering for ESP32 to detect activity-affected sensor groups with a self-supervised distance metric, and (iii) a leader-based group inference with off-the-shelf ML classifiers, enabling the sensor network to collaboratively detect hyperlocal indoor activities. Our extensive experiments demonstrated on-device activity detection, achieving 97.41% accuracy for indoor activity and 99.68% for cooking activity, using off-the-shelf ML models with latency below 34 microseconds.

Problem

• hyperlocal human activities
• pollution sensor networks
• distributed data consensus
• activity-affected sensor groups
• on-device inference

Innovation

• conflict-free replicated data type
• hierarchical clustering
• self-supervised distance metric
• on-device inference
• hyperlocal activity recognition