Concept Drift Mitigation in Low-Cost Air Quality Monitoring Networks

被引:0
作者
D'Elia, Gerardo [1 ,2 ]
Ferro, Matteo [3 ]
Sommella, Paolo [2 ]
Ferlito, Sergio [1 ]
De Vito, Saverio [1 ]
Di Francia, Girolamo [1 ]
机构
[1] ENEA CR Portici, TERIN SSI EDS Lab, P E Fermi 1, I-80055 Portici, Italy
[2] Univ Salerno, Dept Ind Engn DIIn, Via Giovanni Paolo II 132, I-84084 Fisciano, Italy
[3] Hippocratica Imaging S r l, Via Giulio Pastore 32, I-84131 Salerno, Italy
关键词
air quality network; concept drift; general calibration; global calibration; importance weighting; relative expanded uncertainty; calibration model update; PERFORMANCE EVALUATION; CALIBRATION; SENSORS; NO2; POLLUTION; O-3;
D O I
10.3390/s24092786
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
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.
引用
收藏
页数:12
相关论文
共 31 条
[1]   Learning Calibration Functions on the Fly: Hybrid Batch Online Stacking Ensembles for the Calibration of Low-Cost Air Quality Sensor Networks in the Presence of Concept Drift [J].
Bagkis, Evangelos ;
Kassandros, Theodosios ;
Karatzas, Kostas .
ATMOSPHERE, 2022, 13 (03)
[2]   Handling Concept Drift for Predictions in Business Process Mining [J].
Baier, Lucas ;
Reimold, Josua ;
Kuhl, Niklas .
2020 IEEE 22ND CONFERENCE ON BUSINESS INFORMATICS (CBI 2020), VOL I - RESEARCH PAPERS, 2020, :76-83
[3]   Distributed Multi-Scale Calibration of Low-Cost Ozone Sensors in Wireless Sensor Networks [J].
Barcelo-Ordinas, Jose M. ;
Ferrer-Cid, Pau ;
Garcia-Vidal, Jorge ;
Ripoll, Anna ;
Viana, Mar .
SENSORS, 2019, 19 (11)
[4]   Influence of Concept Drift on Metrological Performance of Low-Cost NO2 Sensors [J].
D'Elia, Gerardo ;
Ferro, Matteo ;
Sommella, Paolo ;
De Vito, Saverio ;
Ferlito, Sergio ;
D'Auria, Paolo ;
Di Francia, Girolamo .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
[5]   A Global Multiunit Calibration as a Method for Large-Scale IoT Particulate Matter Monitoring Systems Deployments [J].
De Vito, Saverio ;
D'Elia, Gerardo ;
Ferlito, Sergio ;
Di Francia, Girolamo ;
Davidovic, Milos D. ;
Kleut, Duska ;
Stojanovic, Danka ;
Jovasevic-Stojanovic, Milena .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2024, 73 :1-16
[6]   Global calibration models match ad-hoc calibrations field performances in low cost particulate matter sensors [J].
De Vito, Saverio ;
D'Elia, Gerardo ;
Di Francia, Girolamo .
2022 IEEE INTERNATIONAL SYMPOSIUM ON OLFACTION AND ELECTRONIC NOSE (ISOEN 2022), 2022,
[7]   On the robustness of field calibration for smart air quality monitors [J].
De Vito, Saverio ;
Esposito, Elena ;
Castell, Nuria ;
Schneider, Philipp ;
Bartonova, A. .
SENSORS AND ACTUATORS B-CHEMICAL, 2020, 310
[8]   Learning in Nonstationary Environments: A Survey [J].
Ditzler, Gregory ;
Roveri, Manuel ;
Alippi, Cesare ;
Polikar, Robi .
IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE, 2015, 10 (04) :12-25
[9]  
EC, 2010, Guide to the Demonstration of Equivalence of Ambient Air Monitoring Methods Report by an EC Working Group on Guidance for the Demonstration of Equivalence
[10]   Optimal Field Calibration of Multiple IoT Low Cost Air Quality Monitors: Setup and Results [J].
Esposito, E. ;
D'Elia, G. ;
Ferlito, S. ;
Del Giudice, A. ;
Fattoruso, G. ;
D'Auria, P. ;
De Vito, S. ;
Di Francia, G. .
COMPUTATIONAL SCIENCE AND ITS APPLICATIONS - ICCSA 2020, PT V, 2020, 12253 :700-708