Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Odour classification system for continuous monitoring applications
Ist Teil von
Sensors and actuators. B, Chemical, 2009-06, Vol.139 (2), p.265-273
Ort / Verlag
Elsevier B.V
Erscheinungsjahr
2009
Link zum Volltext
Quelle
Elsevier ScienceDirect Journals Complete
Beschreibungen/Notizen
In this paper, we investigate the classification performance of an electronic nose system, based on tin dioxide gas sensors. In contrast to previous studies, the electronic nose is mounted on a mobile platform and samples are analyzed using only transient information in the signals. The motivation behind this work is to explore the feasibility of using electronic nose devices for odour classification in a number of future application domains which require fast and possibly real-time odour identification. To perform transient based analysis of the signals, a comparative study of different methods for feature extraction was performed. Additionally, the application of a relevance vector machine classifier is explored to further analyze the classification performance based on quality of the obtained samples. The results presented in this study can be used for the development of electronic nose devices particularly suitable for environmental monitoring applications.