PoHAR: Understanding Hyperlocal Human Activities with Pollution Sensor Networks

TL;DR

PoHAR is a framework that enables low-cost pollution sensor networks to collaboratively detect indoor human activities with high accuracy and minimal latency, leveraging conflict-free data sharing and hierarchical clustering.

Contribution

The paper introduces PoHAR, a novel framework combining conflict-free data primitives, hierarchical clustering, and leader-based inference for hyperlocal activity detection in sensor networks.

Findings

Achieved 97.41% accuracy in indoor activity detection.

Achieved 99.68% accuracy in cooking activity detection.

Latency of activity detection is below 34 microseconds.

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.