Conformal predictions for electronic nose system: an application to tea classification

Conformal predictors are recently developed general learning framework and allow us to make estimation of confidence in the classification of individual examples. In this paper, we consider conformal predictions for electronic nose system and present an investigation into the performance of conformal predictors for discriminating the aroma of different types of tea using an electronic nose system based on gas sensors. We discuss how conformal predictors based on Support Vector Machine can be extended to multi-class problems and compare their performance on a tea classification dataset.