论文标题
在环境传感器网络中建模校准不确定性
Modelling calibration uncertainty in networks of environmental sensors
论文作者
论文摘要
低成本传感器的网络变得无处不在，但经常遭受精确度和漂移差的障碍。带有参考传感器的常规托管可以重新校准，但复杂且昂贵。或者，可以使用低成本移动传感器传输校准。但是，推断校准（不确定性）变得困难。我们提出了一种变异方法，以模拟整个网络的校准。我们证明了合成和真实空气污染数据的方法，并发现其性能比最新技术（多跳校准）更好。我们将其扩展到公民科学家标签产生的分类数据。总结：该方法实现了不确定性量化的校准，这是低成本传感器部署和公民科学研究的障碍之一。
Networks of low-cost sensors are becoming ubiquitous, but often suffer from poor accuracies and drift. Regular colocation with reference sensors allows recalibration but is complicated and expensive. Alternatively the calibration can be transferred using low-cost, mobile sensors. However inferring the calibration (with uncertainty) becomes difficult. We propose a variational approach to model the calibration across the network. We demonstrate the approach on synthetic and real air pollution data, and find it can perform better than the state of the art (multi-hop calibration). We extend it to categorical data produced by citizen-scientist labelling. In Summary: The method achieves uncertainty-quantified calibration, which has been one of the barriers to low-cost sensor deployment and citizen-science research.
