Adaptive machine learning strategies for network calibration of IoT smart air quality monitoring devices

Vito, Saverio De; Francia, G. Di; Esposito, E.; Ferlito, Sergio; Formisano, Fabrizio; Massera, Ettore

doi:10.1016/j.patrec.2020.04.032

Cited by 43 publications

(27 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Continuous learning, online learning, and adaptive learning are quite similar machine learning paradigms to incremental learning. De Vito et al [34] show that adaptive and incremental strategies, such as performing periodic recalibration, can improve the performance of initially trained calibration models for low-cost sensors. Through experiments carried out on measurements collected from 18-months electrochemical sensors deployments, monitoring CO, NO 2 , and O 3 concentrations, the authors demonstrate that such strategies improve the overall performance of calibration models and make them less sensitive to seasonal changes or other variations.…”

Section: Other Machine Learning Paradigmsmentioning

confidence: 99%

Low-Cost Outdoor Air Quality Monitoring and Sensor Calibration

Concas

Mineraud

Lagerspetz

et al. 2021

ACM Trans. Sen. Netw.

132

View full text Add to dashboard Cite

The significance of air pollution and the problems associated with it are fueling deployments of air quality monitoring stations worldwide. The most common approach for air quality monitoring is to rely on environmental monitoring stations, which unfortunately are very expensive both to acquire and to maintain. Hence, environmental monitoring stations are typically sparsely deployed, resulting in limited spatial resolution for measurements. Recently, low-cost air quality sensors have emerged as an alternative that can improve the granularity of monitoring. The use of low-cost air quality sensors, however, presents several challenges: They suffer from cross-sensitivities between different ambient pollutants; they can be affected by external factors, such as traffic, weather changes, and human behavior; and their accuracy degrades over time. Periodic re-calibration can improve the accuracy of low-cost sensors, particularly with machine-learning-based calibration, which has shown great promise due to its capability to calibrate sensors in-field. In this article, we survey the rapidly growing research landscape of low-cost sensor technologies for air quality monitoring and their calibration using machine learning techniques. We also identify open research challenges and present directions for future research.

show abstract

Section: Other Machine Learning Paradigmsmentioning

confidence: 99%

Low-Cost Outdoor Air Quality Monitoring and Sensor Calibration

Concas

Mineraud

Lagerspetz

et al. 2021

ACM Trans. Sen. Netw.

132

View full text Add to dashboard Cite

show abstract

“…This brings issues of optimal training test split, both in terms of amount of data and also temporal position of the data. Similar issues are encountered in low cost sensor calibration [19,27]. Additionally, since we are dealing with time series analysis test data will always need to be temporally separated and have timestamp later in time compared to training data.…”

Section: Resultsmentioning

confidence: 95%

Modeling Indoor Particulate Matter and Small Ion Concentration Relationship—A Comparison of a Balance Equation Approach and Data Driven Approach

et al. 2020

View full text Add to dashboard Cite

In this work we explore the relationship between particulate matter (PM) and small ion (SI) concentration in a typical indoor elementary school environment. A range of important air quality parameters (radon, PM, SI, temperature, humidity) were measured in two elementary schools located in urban background and suburban area in Belgrade city, Serbia. We focus on an interplay between concentrations of radon, small ions (SI) and particulate matter (PM) and for this purpose, we utilize two approaches. The first approach is based on a balance equation which is used to derive approximate relation between concentration of small ions and particulate matter. The form of the obtained relation suggests physics based linear regression modelling. The second approach is more data driven and utilizes machine learning techniques, and in this approach, we develop a more complex statistical model. This paper attempts to put together these two methods into a practical statistical modelling approach that would be more useful than either approach alone. The artificial neural network model enabled prediction of small ion concentration based on radon and particulate matter measurements. Models achieved median absolute error of about 40 ions/cm3 and explained variance of about 0.7. This could potentially enable more simple measurement campaigns, where a smaller number of parameters would be measured, but still allowing for similar insights.

show abstract

“…Substantial algorithmic developments have been proposed in the last decade on the best ways to build those maps. These algorithmic developments slightly differ in ambition and scope, whether the eNoses are mounted in mobile platforms based on terrestrial or aerial robots [198]- [202], or by deploying chemical sensor networks over the area of interest [203]- [205]. The use of machine learning methods for sensor array calibration in this application scenario has been widely explored [206].…”

Section: C5) Chemical Mapping and Chemical Source Localizationmentioning

confidence: 99%

Artificial Olfaction in the 21^st Century

et al. 2021

View full text Add to dashboard Cite

The human olfactory system remains one of the most challenging biological systems to replicate. Humans use it without thinking, where it can equally offer protection from harm and bring enjoyment in equal measure. It is the system's ability to detect and analyze complex odors, without the need for specialized infra-structure, that is the envy of many scientists. The field of artificial olfaction has recruited and stimulated interdisciplinary research and commercial development for several applications that include malodor measurement, medical diagnostics, food and beverage quality, environment and security. Over the last century, innovative engineers and scientists have been focused on solving a range of problems associated with measurement and control of odor. The IEEE Sensors Journal has published Special Issues on olfaction in 2002 and 2012. Here we continue that coverage. In this article, we summarize early work in the 20 th Century that served as the foundation upon which we have been building our odormonitoring instrumental and measurement systems. We then examine the current state of the art that has been achieved over the last two decades as we have transitioned into the 21 st Century. Much has been accomplished, but great progress is needed in sensor technology, system design, product manufacture and performance standards. In the final section, we predict levels of performance and ubiquitous applications that will be realized during in the mid to late 21 st Century.

show abstract

Adaptive machine learning strategies for network calibration of IoT smart air quality monitoring devices

Cited by 43 publications

References 16 publications

Low-Cost Outdoor Air Quality Monitoring and Sensor Calibration

Low-Cost Outdoor Air Quality Monitoring and Sensor Calibration

Modeling Indoor Particulate Matter and Small Ion Concentration Relationship—A Comparison of a Balance Equation Approach and Data Driven Approach

Artificial Olfaction in the 21^st Century

Contact Info

Product

Resources

About

Adaptive machine learning strategies for network calibration of IoT smart air quality monitoring devices

Cited by 43 publications

References 16 publications

Low-Cost Outdoor Air Quality Monitoring and Sensor Calibration

Low-Cost Outdoor Air Quality Monitoring and Sensor Calibration

Modeling Indoor Particulate Matter and Small Ion Concentration Relationship—A Comparison of a Balance Equation Approach and Data Driven Approach

Artificial Olfaction in the 21st Century

Contact Info

Product

Resources

About

Artificial Olfaction in the 21^st Century