Abstract: Identifying relevant machine-learning features for multi-sensing platforms is both an applicative limitation to recognize environments and a necessity to interpret the physical relevance of transducers' complementarity in their information processing. Pa rticularly for long acquisitions, feature extraction must be fully automatized without human intervention and resilient to perturbations without increasing significantly the computational cost of a classifier. In this study, we investigate the relative r esistance and current modulation of a 24-dimensional conductimetric electronic nose, which uses the exponential moving average as a floating reference in a low-cost information descriptor for environment recognition. In particular, we identified that dep ending on the structure of a linear classifier, the 'modema' descriptor is optimized for different material sensing elements' contributions to classify information patterns. The low-pass filtering optimization leads to opposite behaviors between unsuperv ised and supervised learning: the latter one favors longer integration of the reference, allowing to recognize five different classes over 90%, while the first one prefers using the latest events as its reference to cluster patterns by environment nature . Its electronic implementation shall greatly diminish the computational requirements of conductimetric electronic noses for on-board environment recognition without human supervision.

Abstract: Multivariate data analysis and machine-learning classification become popular tools to extract features without physical models for complex environments recognition. For electronic noses, time sampling over multiple sensing elements must be a fair compro mise between a period sufficiently long to output a meaningful information pattern, and sufficiently short to minimize training time for practical applications. Particularly when reactivity's kinetic differs from thermodynamic in sensitive materials, fin ding the best compromise to get the most from data is not obvious. Here, we investigate on the influence of data acquisition to improve or alter data clustering for molecular recognition on a conducting polymer electronic nose. We found out that waiting for sensing elements to reach their steady state is not required for classification, and that reducing data acquisition down to the first dynamical information suffice to recognize molecular gases by principal component analysis with the same materials. Especially for online inference, this study shows that a good sensing array is no array of good sensors, and that new figure-of-merits shall be defined for sensing hardware aiming machine-learning pattern-recognition rather than metrology.