Search

Multivariate data analysis and machine learning classification have 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 compromise between a period sufficiently long to output a meaningful information pattern and sufficiently short to minimize training time for practical applications. Particularly when a reactivity's kinetics differ from the thermodynamics in sensitive materials, finding the best compromise to get the most from the data is not obvious. Here, we investigate 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 suffices 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 not an array of good sensors, and that new figures of merit should be defined for sensing hardware using machine learning pattern recognition rather than metrology. [ABSTRACT FROM AUTHOR]

This study presents the development of an electronic nose comprising eight homemade sensors with pure P3HT and doped with different materials. The objective is to electronically identify the gases exposed on these sensors and evaluate the accuracy of target gas classification. The resistance variation for each sensor is measured over time and the collected data were processed by three different identification techniques as following: principal component analysis (PCA), linear discriminate analysis (LDA), and nearest neighbor analysis (kNN). The merit factor for the analysis is the relative modulation of the resistance is very important and computationally gives different results. In addition, the fact that we have sensors made with innovative materials where the reproducibility of the response for the same material can be a constraint in the recognition. In contrast, we have shown that despite the lack of reproducibility for the same material on two different sensors and despite the instability during the ten last sec, we have good recognition rates and we can even say which algorithm is better. It is noted that the LDA is the most reliable and efficient method for gas classification with a prediction accuracy equal to 100%, whereas it reach 93.52% and 73.14% for PCA and kNN, respectively, for other techniques for 40% of training dataset and 60% of testing dataset. [ABSTRACT FROM AUTHOR]

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(3-hexylthiophene) 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. [Display omitted] • Metal triflates as affordable p-dopants for semiconducting polymers. • Chemically-specific gas sensitivity of metal triflate doped P3HT. • Pattern recognition to identify acetone, water and ethanol with two triflated-P3HT. • Tripartite molecular charge-transfers between gas, dopant and semiconductor. [ABSTRACT FROM AUTHOR]