A Deep Learning Approach for Blind Drift Calibration of Sensor Networks
This addresses data quality issues in wireless sensor networks, particularly for large-scale and long-term deployments, but is incremental as it builds on existing calibration approaches with a novel deep learning method.
The paper tackles the problem of blind drift calibration in sensor networks by proposing a deep learning method called PRNet, which improves sensing accuracy and can calibrate twice as many drifted sensors at an 80% recovery rate compared to previous methods.
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.