A Deep Learning Approach for Blind Drift Calibration of Sensor Networks

• Published in: IEEE sensors journal 2017-07, Vol.17 (13), p.4158-4171
• Main Authors: Wang, Yuzhi, Yang, Anqi, Chen, Xiaoming, Wang, Pengjun, Wang, Yu, Yang, Huazhong
• Format: Article
• Language: English
• Subjects: Artificial neural networks; blind calibration; Calibration; convolutional neural networks; Data models; Deep learning; Detection; Drift estimation; Ground truth; Monitoring; Neural networks; Noise measurement; Projection; Recovery; Remote sensors; Sensor networks; Sensors; Wireless sensor networks
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2017.2703885

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 driftfree 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 2× 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.