A Deep Learning Approach for Blind Drift Calibration of Sensor Networks

TL;DR

This paper introduces PRNet, a deep learning model that performs blind, online calibration of sensor data in wireless sensor networks, significantly improving accuracy without ground truth.

Contribution

The paper presents a novel deep learning approach, PRNet, for blind calibration of sensor networks, enabling online correction without ground truth data, outperforming previous methods.

Findings

PRNet improves sensing accuracy and detects drifted sensors effectively.

PRNet calibrates twice as many drifted sensors with 80% recovery rate.

The approach provides insights for designing neural networks for sensor calibration.

Abstract

Temporal drift of sensory data is a severe problem impacting the data quality of wireless sensor networks (WSNs). With the proliferation of large-scale and long-term WSNs, it is becoming more important to calibrate sensors when the ground truth is unavailable. This problem is called "blind calibration". In this paper, we propose a novel deep learning method named projection-recovery network (PRNet) to blindly calibrate sensor measurements online. The PRNet first projects the drifted data to a feature space, and uses a powerful deep convolutional neural network to recover the estimated drift-free measurements. We deploy a 24-sensor testbed and provide comprehensive empirical evidence showing that the proposed method significantly improves the sensing accuracy and drifted sensor detection. Compared with previous methods, PRNet can calibrate 2x of drifted sensors at the recovery rate of 80% under the same level of accuracy requirement. We also provide helpful insights for designing deep neural networks for sensor calibration. We hope our proposed simple and effective approach will serve as a solid baseline in blind drift calibration of sensor networks.