Not all those who drift are lost: Drift correction and calibration scheduling for the IoT

TL;DR

This paper introduces a probabilistic drift correction method for IoT sensors using Gaussian Process Regression, significantly improving data accuracy and proposing an uncertainty-based calibration schedule to further enhance sensor performance.

Contribution

It presents a novel Gaussian Process Regression-based drift correction technique and an uncertainty-driven calibration scheduling approach for IoT sensors.

Findings

MSE reduced by up to 90% with the proposed method

Average MSE reduction of over 20% across tests

Calibration scheduling further reduces MSE by up to 15.7%

Abstract

Sensors provide a vital source of data that link digital systems with the physical world. However, as sensors age, the relationship between what they measure and what they output changes. This is known as sensor drift and poses a significant challenge that, combined with limited opportunity for re-calibration, can severely limit data quality over time. Previous approaches to drift correction typically require large volumes of ground truth data and do not consider measurement or prediction uncertainty. In this paper, we propose a probabilistic sensor drift correction method that takes a fundamental approach to modelling the sensor response using Gaussian Process Regression. Tested using dissolved oxygen sensors, our method delivers mean squared error (MSE) reductions of up to 90% and more than 20% on average. We also propose a novel uncertainty-driven calibration schedule optimisation approach that builds on top of drift correction and further reduces MSE by up to 15.7%.