Machine-Learning Identification of the Sensing Descriptors Relevant in Molecular Interactions with Metal Nanoparticle-Decorated Nanotube Field-Effect Transistors

Abstract

Carbon nanotube-based field-effect transistors (NTFETs) are ideal sensor devices as they provide rich information regarding carbon nanotube interactions with target analytes and have potential for miniaturization in diverse applications in medical, safety, environmental, and energy sectors. Herein, we investigate chemical detection with cross-sensitive NTFETs sensor arrays comprised of metal nanoparticle-decorated single-walled carbon nanotubes (SWCNTs). By combining analysis of NTFET device characteristics with supervised machine-learning algorithms, we have successfully discriminated among five selected purine compounds, adenine, guanine, xanthine, uric acid, and caffeine. Interactions of purine compounds with metal nanoparticle-decorated SWCNTs were corroborated by density functional theory calculations. Furthermore, by testing a variety of prepared as well as commercial solutions with and without caffeine, our approach accurately discerns the presence of caffeine in 95% of the samples with 48 features using a linear discriminant analysis and in 93.4% of the samples with only 11 features when using a support vector machine analysis. We also performed recursive feature elimination and identified three NTFET parameters, transconductance, threshold voltage, and minimum conductance, as the most crucial features to analyte prediction accuracy.

Chemical Gas Sensors: Recent Developments, Challenges, and the Potential of Machine Learning—A Review

“…The stratified k-fold CV is an efficient approach to shuffle the entire dataset and then divide it into equal subsets with a good representation of all the training examples. Therefore, their trained SVM model was successfully able to distinguish caffeine with an accuracy rate of 93.4% [139] (see Figure 17Bb-3). Most recently, Hayasaka et al [140] fabricated a highly selective sensor using pristine graphene and ALD-RuO 2 -based GFET devices with machine learning.…”

“…In 2019, Bian et al [139] synthesized a sensing array using different metal catalysts decorated on single-walled carbon nanotube (SWCNTs) to develop a FET device for the detection of purine compounds (adenine, guanine, xanthine, uric acid, and caffeine). The 11 different features were extracted from the response curve of the FET device.…”

Chemiresistive Sensor Array and Machine Learning Classification of Food

“…Detection of chemical inputs is achieved through a combination of multiple sensing channels where each channel responds to several analytes. , Single-walled carbon nanotube (SWCNT) chemiresistors and carbon nanotube-based electrochemical sensors have been shown to provide suitable platforms for array-based detection of various gases . Several sensor arrays comprising CNT-based sensing channels have been used to discriminate between single volatile organic compound (VOC) vapors, − inorganic gases, , and biological samples. − However, few reports have been published on the differentiation between food samples, among them are the determination of caffeine content in coffee, the electrochemical detection and differentiation between rice wines, electrochemical determination of capsaicin content of hot sauces, and chemiresistive differentiation of liquors using multiwalled CNT/polymer composites. , …”

“…12 Several sensor arrays comprising CNT-based sensing channels have been used to discriminate between single volatile organic compound (VOC) vapors, 13−18 inorganic gases, 19,20 and biological samples. 21−24 However, few reports have been published on the differentiation between food samples, among them are the determination of caffeine content in coffee, 25 the electrochemical detection and differentiation between rice wines, 26 electrochemical determination of capsaicin content of hot sauces, 27 and chemiresistive differentiation of liquors using multiwalled CNT/polymer composites. 28,29 Herein, we differentiate between complex odors using an array of 20 SWCNT-based chemiresistive sensors (Figure 1).…”

Tetrahydrocannabinol Detection Using Semiconductor-Enriched Single-Walled Carbon Nanotube Chemiresistors

“…Because the sensing mechanism of nanotubes involves measuring changes in charge carrier population and charge pinning, chemical sensitivity can be further enhanced by increasing the ratio between semiconducting and metallic nanotubes through various enrichment methods. − Chemiresistors fabricated from the semiconductor-enriched SWCNTs (s-SWCNTs) have been shown to have 2–3 orders of magnitude higher sensitivity than chemiresistors fabricated from mixed metallic and semiconducting SWCNTs. − Additionally, machine learning algorithms can be used for deeper analysis of sensor time traces. These commonly used algorithms have been shown to be useful for improving the selectivity of nonspecific sensors. − Herein, we show that one of the potential applications of s-SWCNT-based chemiresistor is the detection of delta-9-tetrahydrocannabinol (THC) in human breath.…”