School of Electrical Engineering, University of Belgrade, 11120 Belgrade, Serbia.
Innovation Center of the School of Electrical Engineering in Belgrade, 11120 Belgrade, Serbia.
Sensors (Basel). 2023 Mar 4;23(5):2815. doi: 10.3390/s23052815.
Public air quality monitoring relies on expensive monitoring stations which are highly reliable and accurate but require significant maintenance and cannot be used to form a high spatial resolution measurement grid. Recent technological advances have enabled air quality monitoring that uses low-cost sensors. Being inexpensive and mobile, with wireless transfer support, such devices represent a very promising solution for hybrid sensor networks comprising public monitoring stations supported by many low-cost devices for complementary measurements. However, low-cost sensors can be influenced by weather and degradation, and considering that a spatially dense network would include them in large numbers, logistically adept solutions for low-cost device calibration are essential. In this paper, we investigate the possibility of a data-driven machine learning calibration propagation in a hybrid sensor network consisting of One public monitoring station and ten low-cost devices equipped with NO, PM, relative humidity, and temperature sensors. Our proposed solution relies on calibration propagation through a network of low-cost devices where a calibrated low-cost device is used to calibrate an uncalibrated device. This method has shown an improvement of up to 0.35/0.14 for the Pearson correlation coefficient and a reduction of 6.82 µg/m/20.56 µg/m for the RMSE, for NO and PM, respectively, showing promise for efficient and inexpensive hybrid sensor air quality monitoring deployments.
公共空气质量监测依赖于昂贵的监测站，这些监测站高度可靠且准确，但需要大量维护，并且不能用于形成高空间分辨率的测量网格。最近的技术进步使得使用低成本传感器进行空气质量监测成为可能。这些设备具有成本低、移动性强、支持无线传输等特点，是由许多低成本设备组成的混合传感器网络的理想选择，这些低成本设备可以为公共监测站提供补充测量。然而，低成本传感器会受到天气和降解的影响，而且考虑到密集的空间网络会包含大量传感器，因此对于低成本设备的校准来说，逻辑上合理的解决方案至关重要。在本文中，我们研究了在由一个公共监测站和十个配备 NO、PM、相对湿度和温度传感器的低成本设备组成的混合传感器网络中，基于数据驱动的机器学习进行校准传播的可能性。我们提出的解决方案依赖于通过低成本设备网络进行校准传播，其中一个经过校准的低成本设备用于校准未经校准的设备。对于 NO 和 PM，该方法分别显示出 Pearson 相关系数提高了 0.35/0.14，RMSE 降低了 6.82µg/m/20.56µg/m，这表明该方法在高效、低成本的混合传感器空气质量监测方面具有很大的应用潜力。
