Using the classification model of an electronic nose to assign unknown malodours to environmental sources and to monitor them continuously

Abstract

The paper provides some considerations resulting from measurements with electronic noses around real sources of malodour in the environment: compost facilities, printing houses, paint shops, waste water treatment plants, rendering plants, settling ponds of sugar factories. The study aims at supplying the concrete information requested by the final user in the field: either a warning signal when the malodour level exceeds some given threshold value, the identification of the source of an odour detected on site, or on-line identification and monitoring of an odour in the field. Very simple instruments are used, either in the laboratory or directly in the field, with a home-made portable e-nose, based on tin oxide sensors. Even with such simple operating conditions, the classification results with DA and PCA are fairly good. The classification functions calibrated with the statistical procedure, on the basis of the learning phase, are used to recognise and to monitor a given malodour. This odour is sometimes mixed with other odorous interferences in the field. The observations reveal some features useful in the frame of the development of a field detector.

Three years experiment with the same tin oxide sensor arrays for the identification of malodorous sources in the environment

“…After the first measurement campaign, in 1998, the results were quite promising [12][13][14][15], in spite of the environmental constraints (temperature and humidity influence [14], wind speed effect, odour variation in nature and in concentration, ever changing background air, chemical interference, difficulties of the maintenance). Similar results are obtained with the observations made with the field instrument in 1999, notably around the compost area.…”

“…A discriminant function model is also trained with field data and the so calibrated classification functions are further used for validation purpose around the compost area [15]. Five classification functions (one for each source and one for the odourless air) are provided by DFA to assign a new case into one of the known groups: a case is classified into the group for which it has the highest classification score.…”

Application of Multivariate Data Analyses in Waste Management

“…Vergnoux et al [21] applied a PCA on NIR spectra as well as on physico-chemical and biochemical parameters to derive regularities from the data. Nicolas et al [9] used PCA to evaluate data from an electronic nose. The correlations between the sensor of an electronic nose and chemical substances were determined by Romain et al [11] using PCA.…”

“…Campitelli and Ceppi [3] carried out a DA to distinguish between compost and vermicompost on the basis of parameters such as total organic carbon (TOC), germination index (GI), pH, total nitrogen (TN), and water soluble carbon (WSC). Nicolas et al [9] performed a DA to classify data of an electric nose according to defined exceeded levels of odour. Ecke et al [71] investigated samples from three different landfill sites by the biochemical methane potential and used DA for data evaluation.…”

A Disposable Sensor For Assessing Artocarpus heterophyllus L. (Jackfruit) Maturity

“…Unlike PCA CDA knows the class membership of each case. It is mainly used in the second step, to build a classification model, which will be applied for the identification of unknown samples [9]. Therefore to validate the method, a classification model is computed, as shown in Fig.5 and Table 2) the four "unknowns" which belongs to the category of 70-80 days are successfully and well classified in the corresponding group as illustrated in Fig.…”