Optimal selection of SAW sensors for E-Nose applications

Electronic noses (E-Nose) are devices used to substitute human or canine olfactory systems in detecting gases or chemical substances. The success of an E-Nose in detecting a set of target gases depends on how optimal is the choice of the gas sensors. This paper proposes a novel algorithm for selection of an optimal set of surface acoustic wave (SAW) sensors for an E-Nose from a given set of available gas sensors. The sensor performance is quantified in terms of separability of data obtained from them. A similarity measure specifying how similar the responses of sensors are when exposed to a set of gases, is also defined. The sensor selection algorithm is then specified as an optimization problem in terms of separability of target gases and similarity of sensor responses. The advantage of the proposed method lies in its performance being independent of the choice of the pattern recognition engine.