Title :
Dynamic multivariate regression for on-field calibration of high speed air quality chemical multi-sensor systems
Author :
De Vito, S. ; Delli Veneri, P. ; Esposito, E. ; Salvato, M. ; Bright, V. ; Jones, R.L. ; Popoola, O.
Author_Institution :
UTTP-MDB, ENEA - Agenzia per le Nuove Tecnol. l´Energia e lo Sviluppo Economico Sostenibile, Portici, Italy
Abstract :
In the last few years, the interest in the development of new pervasive or mobile implementations of air quality multi-sensor devices, has significantly grown. New application opportunities appeared together with new challenges due to limitations in dealing with rapid pollutants concentrations transients. In this work, we propose a Dynamic Neural Network (DNN) approach to the stochastic prediction of air pollutants concentrations by means of chemical multi-sensor 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. Results have been compared with those obtainable by static models showing the performance advantages of on-field dynamic multivariate calibration in a real world air quality monitoring scenario.
Keywords :
air pollution; air quality; calibration; chemical sensors; chemical variables measurement; computerised instrumentation; neural nets; prediction theory; regression analysis; sensor fusion; stochastic processes; Cambridge; DNN approach; UK; air pollutant concentration transient; air quality monitoring; dynamic multivariate regression; dynamic neural network approach; high speed air quality chemical multisensor system; on-field calibration; on-field recorded dataset; stochastic prediction; Calibration; Chemical sensors; Estimation; Monitoring; Neural networks; Sensors; Transient analysis; air quality monitoring; dynamic neural networks; multivariate calibration;
Conference_Titel :
AISEM Annual Conference, 2015 XVIII
Conference_Location :
Trento
DOI :
10.1109/AISEM.2015.7066794