Search

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. Particularly 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 on the relative resistance 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 depending 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 unsupervised 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 clusterize 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.

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 sensors must be a fair compromise 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 kinetics differ from thermodynamics' in sensitive materials, finding 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 the sensors 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. Particularly 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.

Organic semiconductors have enough molecular versatility to feature chemo-specific electrical sensitivity to large families of chemical substituents via different intermolecular bonding modes. This study demonstrates that one single conducting polymer can be tuned to either discriminate water-, ethanol- or acetone-vapors, on demand, by changing the nature of its dopant. Seven triflate salts differ from mild to strong p-dopant on poly(3hexylthiophene) sensing micro-arrays. Each material shows a pattern of conductance modulation for the polymer which is reversible, reproducible, and distinctive of other gas exposures. Based on principal component analysis, an array doped with only two different triflates can be trained to reliably discriminate gases, which re-motivates using conducting polymers as a class of materials for integrated electronic noses. More importantly, this method points out the existence of tripartite donor-acceptor charge-transfer complexes responsible for chemospecific molecular sensing. By showing that molecular acceptors can have duality to p-dope semiconductors and to coordinate donor gases, such behavior can be used to understand the role of frontier orbital overlapping in organic semiconductors, the formation of charge-transfer complexes via Lewis acid-base adducts in molecular semiconductors.