Concept Drift Mitigation in Low-Cost Air Quality Monitoring Networks.

Future air quality monitoring networks will integrate fleets of low-cost gas and particulate matter sensors that are calibrated using machine learning techniques. Unfortunately, it is well known that concept drift is one of the primary causes of data quality loss in machine learning application operational scenarios. The present study focuses on addressing the calibration model update of low-cost NO2 sensors once they are triggered by a concept drift detector. It also defines which data are the most appropriate to use in the model updating process to gain compliance with the relative expanded uncertainty (REU) limits established by the European Directive. As the examined methodologies, the general/global and the importance weighting calibration models were applied for concept drift effects mitigation. Overall, for all the devices under test, the experimental results show the inadequacy of both models when performed independently. On the other hand, the results from the application of both models through a stacking ensemble strategy were able to extend the temporal validity of the used calibration model by three weeks at least for all the sensor devices under test. Thus, the usefulness of the whole information content gathered throughout the original co-location process was maximized.

Crowdsensing IoT Architecture for Pervasive Air Quality and Exposome Monitoring: Design, Development, Calibration, and Long-Term Validation.

A pervasive assessment of air quality in an urban or mobile scenario is paramount for personal or city-wide exposure reduction action design and implementation. The capability to deploy a high-resolution hybrid network of regulatory grade and low-cost fixed and mobile devices is a primary enabler for the development of such knowledge, both as a primary source of information and for validating high-resolution air quality predictive models. The capability of real-time and cumulative personal exposure monitoring is also considered a primary driver for exposome monitoring and future predictive medicine approaches. Leveraging on chemical sensing, machine learning, and Internet of Things (IoT) expertise, we developed an integrated architecture capable of meeting the demanding requirements of this challenging problem. A detailed account of the design, development, and validation procedures is reported here, along with the results of a two-year field validation effort.