A graphene chemical vapor sensor with an unmodified surface has been fabricated and thoroughly characterized upon exposure to headspace vapor of a variety of solvents and related compounds. The vapor sensor exhibits excellent discrimination toward a variety of chemical compounds. Principle component analysis (PCA) was performed to explore the extent of grouping for each compound and separation between compounds and chemical classes. The prediction accuracy of the sensor is evaluated with linear discrimination analysis, k-nearest neighbor, random forest, and support vector classifiers. The combination of PCA and prediction accuracies demonstrates the discrimination capability of an unmodified graphene chemical vapor sensor. Such a vapor sensor is very attractive for application in small, low-power, robust, and adaptable cross-reactive arrays in electronic noses.

A graphene chemical sensor is subjected to a set of structurally and chemically similar hydrocarbon compounds consisting of toluene, o-xylene, p-xylene, and mesitylene. The fractional change in resistance of the sensor upon exposure to these compounds exhibits a similar response magnitude among compounds, whereas large variation is observed within repetitions for each compound, causing a response overlap. Therefore, traditional features depending on maximum response change will cause confusion during further discrimination and classification analysis. More robust features that are less sensitive to concentration, sampling, and drift variability would provide higher quality information. In this work, we have explored the advantage of using transient-based exponential fitting coefficients to enhance the discrimination of similar compounds. The advantages of such feature analysis to discriminate each compound is evaluated using principle component analysis (PCA). In addition, machine learning-based classification algorithms were used to compare the prediction accuracies when using fitting coefficients as features. The additional features greatly enhanced the discrimination between compounds while performing PCA and also improved the prediction accuracy by 34% when using linear discrimination analysis.