Calibration of MOX gas sensors in open sampling systems based on Gaussian Processes

Monroy, Javier; Lilienthal, Achim J.; Blanco, José Luis Santiago; González-Jiménez, Javier; Trincavelli, Marco

doi:10.1109/icsens.2012.6411464

Cited by 14 publications

(14 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Of course these limitations become extremely significant for mobile applications like personal pollution exposition evaluation. In fact, mobile platforms, as they navigate relatively to the source, may cross pollutants plume several times, experiencing sudden and rapid gas concentration transitions [10]. A rapid detection of the concentration changes is hence paramount for personal exposure quantification.…”

Section: Introductionmentioning

confidence: 99%

Dynamic neural network architectures for on field stochastic calibration of indicative low cost air quality sensing systems

Esposito

Vito

Salvato

et al. 2016

Sensors and Actuators B: Chemical

113

View full text Add to dashboard Cite

In the last few years, the interest in the development of new pervasive or mobile implementations of air quality multisensor devices has significantly grown. New application opportunities appeared together with new challenges due to limitations in dealing with rapid pollutants concentrations transients both for static and mobile deployments. In this work, we propose a Dynamic Neural Network (DNN) approach to the stochastic prediction of air pollutants concentrations by means of chemical multisensor devices. DNN architectures have been devised and tested in order to tackle the cross sensitivities issues and sensors inherent dynamic limitations. Testing have been performed using an on-field recorded dataset from a pervasive deployment in Cambridge (UK), encompassing several weeks. The results obtained with the dynamic model are compared with the response of the static neural network and the performance analysis indicates the capability of the on-field dynamic multivariate calibration to ameliorate the static calibration approach performance in this real world air quality monitoring scenario. Interestingly, results analysis also suggests that the improvements are more significant when pollutants concentration changes more rapidly.

show abstract

Section: Introductionmentioning

confidence: 99%

Dynamic neural network architectures for on field stochastic calibration of indicative low cost air quality sensing systems

Esposito

Vito

Salvato

et al. 2016

Sensors and Actuators B: Chemical

113

View full text Add to dashboard Cite

show abstract

“…A great body of work is dedicated to calibrating low-cost sensors, e.g., [12,19,31,34]. The existing literature on sensor calibration can be classified into micro-and macro-calibration approaches [46,48].…”

Section: Sensor Calibrationmentioning

confidence: 99%

Reducing multi-hop calibration errors in large-scale mobile sensor networks

Saukh

Hasenfratz

Thiele

2015

Proceedings of the 14th International Conference on Information Processing in Sensor Networks

View full text Add to dashboard Cite

Frequent sensor calibration is essential in sensor networks with low-cost sensors. We exploit the fact that temporally and spatially close measurements of different sensors measuring the same phenomenon are similar. Hence, when calibrating a sensor, we adjust its calibration parameters to minimize the differences between co-located measurements of previously calibrated sensors. In turn, freshly calibrated sensors can now be used to calibrate other sensors in the network, referred to as multi-hop calibration.We are the first to study multi-hop calibration with respect to a reference signal (micro-calibration) in detail. We show that ordinary least squares regression-commonly used to calibrate noisy sensors-suffers from significant error accumulation over multiple hops. In this paper, we propose a novel multi-hop calibration algorithm using geometric mean regression, which (i) highly reduces error propagation in the network, (ii) distinctly outperforms ordinary least squares in the multi-hop scenario, and (iii) requires considerably fewer ground truth measurements compared to existing network calibration algorithms. The proposed algorithm is especially valuable when calibrating large networks of heterogeneous sensors with different noise characteristics. We provide theoretical justifications for our claims. Then, we conduct a detailed analysis with artificial data to study calibration accuracy under various settings and to identify different error sources. Finally, we use our algorithm to accurately calibrate 13 million temperature, ground ozone (O3), and carbon monoxide (CO) measurements gathered by our mobile air pollution monitoring network.

show abstract

“…Los investigadores en estaárea están interesados en determinar el desempeño de los sensores para identificar, discriminar y conocer el grado de concentración de distintos olores en tiempo real [8][9][10][11]. Lo que permitiría detectar la fuga de combustibles, gases explosivos o tóxicos, o el monitoreo oportuno de calidad del aire entre otras situaciones donde el tiempo es crítico.…”

Section: Introductionunclassified

Identificación de gases mediante medición de complejidad

Medina

González-Mendoza

2015

RCS

View full text Add to dashboard Cite

Resumen. El análisis de datos provenientes de narices electrónicas son afectados por distintos factores, cuya principal característica es la aleatoriedad. Fenómenos como flujos caóticos y concentraciones irregulares de gases o presencia de gases ajenos a un gas por detectar, dificultan a los algoritmos de clasificación empleados en estaárea su identificación. Debe considerarse también que la estructura de los vectores de estos datos son de alta dimensionalidad y pocas muestras, lo que dificulta descubrir patrones en ellos. En este trabajo se empleó el concepto de Medición de Complejidad, el cual define la cantidad de desorden presente en un sistema. Para demostrar la eficiencia de este concepto en la identificación de olores, se analizó un conjunto de mediciones de una nariz electrónica expuesta a mezclas de etileno, metano y monóxido de carbono a distintas concentraciones y bajo condiciones de flujo de gases muy cercanos a la realidad. Los resultados indican que la medición de complejidad logra discriminar los gases que constituyeron las distintas mezclas, identificando el desempeño de los sensores para reconocerlos de acuerdo a las magnitudes de complejidad y desorden.Palabras clave: Medición de complejidad, sensores MOX, identificación de gases, clasificación por medición de complejidad.

show abstract

Calibration of MOX gas sensors in open sampling systems based on Gaussian Processes

Cited by 14 publications

References 13 publications

Dynamic neural network architectures for on field stochastic calibration of indicative low cost air quality sensing systems

Dynamic neural network architectures for on field stochastic calibration of indicative low cost air quality sensing systems

Reducing multi-hop calibration errors in large-scale mobile sensor networks

Identificación de gases mediante medición de complejidad

Contact Info

Product

Resources

About