Odour measurement using conducting polymer gas sensors and an artificial neural network decision system

The conventional way of assessing the magnitude of nuisance odours using an olfactometer and a sensory panel is costly. This paper describes experiments that have been conducted into matching the results from trained sensory panellists to those from a conducting polymer-based electronic nose. By taking the data from the electronic nose and applying them to a trained neural network, it has been shown that the data can be manipulated to give rise to results that are within a few percent of those from the sensory panellists. This is the first time that an electronic nose has been calibrated in terms of odour intensity measurements and it points the way forward to more objective measurements of nuisance odours