Chemiresistive Sensor Array and Machine Learning Classification of Food.

Successful identification of complex odors by sensor arrays remains a challenging problem. Herein, we report robust, category-specific multiclass-time series classification using an array of 20 carbon nanotube-based chemical sensors. We differentiate between samples of cheese, liquor, and edible oil based on their odor. In a two-stage machine-learning approach, we first obtain an optimal subset of sensors specific to each category and then validate this subset using an independent and expanded data set. We determined the optimal selectors via independent selector classification accuracy, as well as a combinatorial scan of all 4845 possible four selector combinations. We performed sample classification using two models-a k-nearest neighbors model and a random forest model trained on extracted features. This protocol led to high classification accuracy in the independent test sets for five cheese and five liquor samples (accuracies of 91% and 78%, respectively) and only a slightly lower (73%) accuracy on a five edible oil data set.

Fully-drawn carbon-based chemical sensors on organic and inorganic surfaces.

Mechanical abrasion is an extremely simple, rapid, and low-cost method for deposition of carbon-based materials onto a substrate. However, the method is limited in throughput, precision, and surface compatibility for drawing conductive pathways. Selective patterning of surfaces using laser-etching can facilitate substantial improvements to address these current limitations for the abrasive deposition of carbon-based materials. This study demonstrates the successful on-demand fabrication of fully-drawn chemical sensors on a wide variety of substrates (e.g., weighing paper, polymethyl methacrylate, silicon, and adhesive tape) using single-walled carbon nanotubes (SWCNTs) as sensing materials and graphite as electrodes. Mechanical mixing of SWCNTs with solid or liquid selectors yields sensors that can detect and discriminate parts-per-million (ppm) quantities of various nitrogen-containing vapors (pyridine, aniline, triethylamine).