Air Qality Sensor Network Data Acquisition, Cleaning, Visualization, and Analytics: A Real-world IoT Use Case Federica Rollo University of Modena and Reggio Emilia ‘Enzo Ferrari’ Engineering Department Italy federica.rollo@unimore.it Bharath Sudharsan National University of Ireland, Galway Data Science Institute Ireland b.sudharsan1@nuigalway.ie Laura Po University of Modena and Reggio Emilia ‘Enzo Ferrari’ Engineering Department Italy laura.po@unimore.it John Breslin National University of Ireland, Galway Data Science Institute Ireland john.breslin@nuigalway.ie ABSTRACT Monitoring and analyzing air quality is of primary importance to encour- age more sustainable lifestyles and plan corrective actions. This paper presents the design and end-to-end implementation 1 of a real-world ur- ban air quality data collection and analytics use case which is a part of the TRAFAIR (Understanding Trafc Flows to Improve Air Quality) European project [1, 2]. This implementation is related to the project work done in Modena city, Italy, starting from distributed low-cost multi-sensor IoT devices installation, LoRa network setup, data collection at LoRa server database, ML-based anomaly measurement detection plus clean- ing, sensor calibration, central control and visualization using designed SenseBoard [3]. KEYWORDS IoT Analytics, Anomalies Detection, Real-world Applications. ACM Reference Format: Federica Rollo, Bharath Sudharsan, Laura Po, and John Breslin. 2021. Air Quality Sensor Network Data Acquisition, Cleaning, Visualization, and Analytics: A Real- world IoT Use Case. In Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2021 ACM International Symposium on Wearable Computers (UbiComp-ISWC ’21 Adjunct), September 21–26, 2021, Virtual, USA. ACM, New York, NY, USA, 2 pages. https: //doi.org/10.1145/3460418.3479277 1 INTRODUCTION Urban air pollution is a serious public health hazard in many EU cities. In this paper, we employ low-cost IoT devices to monitor air quality in mul- tiple location points at an urban scale. Using low-cost sensors is the only way to be able to carry out hyper-local monitoring in a city. However, managing low-cost AQ sensors is challenging. They are less reliable than the Air Quality Monitoring (AQM) legal stations and require a complex calibration process to obtain pollutant concentration data from the raw observations in millivolt they measured. The deployed implementation allows building a historical air quality dataset that contains accurate (cal- ibrated with great precision close to AQM stations) and reliable (resilient LoRa networks) concentrations of air pollutants. These data can be the foundation for European Environment Agency (EEA), World Health Or- ganization (WHO), other e-government bodies to design ML algorithms for advanced air-quality analytics. 1 Code released at https://github.com/bharathsudharsan/Air-Quality-IoT-Analytics Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for proft or commercial advantage and that copies bear this notice and the full citation on the frst page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s). UbiComp-ISWC ’21 Adjunct, September 21–26, 2021, Virtual, USA © 2021 Copyright held by the owner/author(s). ACM ISBN 978-1-4503-8461-2/21/09. https://doi.org/10.1145/3460418.3479277 Figure 1: Infrastructure design and implementation for the air- quality dataset build and analytics use case. 2 IMPLEMENTATION In implementation Step I (Section 2.1), we explain the IoT device installa- tion plus data acquisition process, then apply ML algorithms to detect anomalies and clean collected sensor data. In Step II (Section 2.2), we present the designed visualization platform to monitor and control the IoT devices and LoRa network. In Step III (Section 2.3), we present example analytics applications of our dataset. 2.1 Data Acquisition and Cleaning Numerous IoT devices are exploited to monitor and collect the pollution level on an urban scale in Modena, Florence, Pisa, Livorno, Santiago de Compostela, and Zaragoza (cities in Italy and Spain). As shown in 67