Gas classification in motion: An experimental analysis

Abstract This work deals with the problem of volatile chemical classification with an electronic nose (e-nose), and particularly focuses on the case where the e-nose is not collecting samples in a stationary fashion but is carried by a moving platform (mobile robot, car, bike, etc.). We bring to light that, under these specific circumstances, substantial changes in the transient response of the gas sensors arise (something that has not been considered until now). We experimentally demonstrate that these changes in the sensor's response have an important impact on the classification accuracy if not properly considered, resulting in a decrease of up to 30% in some configurations. We back our conclusions with an extensive experimental evaluation consisting of a mobile robot inspecting a long indoor corridor with two chemical volatiles sources (ethanol and acetone) more than 240 times, at four different motion speeds. The paper also reveals the relevance of training the classifiers with data collected in motion, and proposes different training schemes suitable to this problem.