Model-Based Event Detection in Wireless Sensor Networks

TL;DR

This paper introduces a PCA-based method for detecting environmental events in wireless sensor networks by modeling normal patterns and identifying deviations, demonstrated by rain event detection using temperature data.

Contribution

It applies PCA for event detection in sensor networks, capturing seasonal trends and detecting discrete events through divergence analysis, which is a novel application in this context.

Findings

Successfully detected rain onset using temperature data

Model captures daily and seasonal environmental trends

Divergence method effectively identifies discrete events

Abstract

In this paper we present an application of techniques from statistical signal processing to the problem of event detection in wireless sensor networks used for environmental monitoring. The proposed approach uses the well-established Principal Component Analysis (PCA) technique to build a compact model of the observed phenomena that is able to capture daily and seasonal trends in the collected measurements. We then use the divergence between actual measurements and model predictions to detect the existence of discrete events within the collected data streams. Our preliminary results show that this event detection mechanism is sensitive enough to detect the onset of rain events using the temperature modality of a wireless sensor network.