Machine Vision Methods, Natural Language Processing, and Machine Learning Algorithms for Automated Dispersion Plot Analysis and Chemical Identification from Complex Mixtures

Non-destructive method to classify walnut kernel freshness from volatile organic compound (VOC) emissions using gas chromatography-differential mobility spectrometry (GC-DMS) and machine learning analysis

Analysis of volatile organic compounds (VOCs) can be an effective strategy to inspect the quality of horticultural commodities and following their degradation. In this work, we report that VOCs emitted by walnuts can be studied using gas chromatography-differential mobility spectrometry (GC-DMS), and those GC-DMS data can be analyzed to predict the rancidity of walnuts, i.e., classify walnuts into grades of freshness. Walnut kernels were assigned a class n depending on their level of freshness as determined by a peroxide assay. VOC samples were analyzed using GC-DMS. From these VOC data, a partial least square regression (PLSR) model provided a freshness prediction value m , which corresponded to the rancid class n when m = n ± 0.5 . The PLSR model had an accuracy of 80% to predict walnut grade and demonstrated a minimal root mean squared error of 0.42 for the m response variables (representative of walnut grade) with the GC-DMS data. We also conducted gas chromatography-mass spectrometry (GC-MS) experiments to identify volatiles that emerged or were enhanced with more rancid walnuts. The findings of the GC-MS study of walnut VOCs align excellently with the GC-DMS study. Based on our results, we conclude that a GC-DMS device deployed with a pre-trained machine learning model can be a very effective device for classifying walnut grades in the industry.

Portable chemical detection platform for on-site monitoring of odorant levels in natural gas

The adequate odorization of natural gas is critical to identify gas leaks and to reduce accidents. To ensure odorization, natural gas utility companies collect samples to be processed at core facilities or a trained human technician smells a diluted natural gas sample. In this work, we report a detection platform that addresses the lack of mobile solutions capable of providing quantitative analysis of mercaptans, a class of compounds used to odorize natural gas. Detailed description of the platform hardware and software components is provided. Designed to be portable, the platform hardware facilitates extraction of mercaptans from natural gas, separation of individual mercaptan species, and quantification of odorant concentration, with results reported at point-of-sampling. The software was developed to accommodate skilled users as well as minimally trained operators. Detection and quantification of six commonly used mercaptan compounds (ethyl mercaptan, dimethyl sulfide, n-propylmercaptan, isopropyl mercaptan, tert‑butyl mercaptan, and tetrahydrothiophene) at typical odorizing concentrations of 0.1-5 ppm was performed using the device. We demonstrate the potential of this technology to ensure natural gas odorizing concentrations throughout distribution systems.

Predominant SARS-CoV-2 variant impacts accuracy when screening for infection using exhaled breath vapor

BACKGROUND

New technologies with novel and ambitious approaches are being developed to diagnose or screen for SARS-CoV-2, including breath tests. The US FDA approved the first breath test for COVID-19 under emergency use authorization in April 2022. Most breath-based assays measure volatile metabolites exhaled by persons to identify a host response to infection. We hypothesized that the breathprint of COVID-19 fluctuated after Omicron became the primary variant of transmission over the Delta variant.

METHODS

We collected breath samples from 142 persons with and without a confirmed COVID-19 infection during the Delta and Omicron waves. Breath samples were analyzed by gas chromatography-mass spectrometry.

RESULTS

Here we show that based on 63 exhaled compounds, a general COVID-19 model had an accuracy of 0.73 ± 0.06, which improved to 0.82 ± 0.12 when modeling only the Delta wave, and 0.84 ± 0.06 for the Omicron wave. The specificity improved for the Delta and Omicron models (0.79 ± 0.21 and 0.74 ± 0.12, respectively) relative to the general model (0.61 ± 0.13).

CONCLUSIONS

We report that the volatile signature of COVID-19 in breath differs between the Delta-predominant and Omicron-predominant variant waves, and accuracies improve when samples from these waves are modeled separately rather than as one universal approach. Our findings have important implications for groups developing breath-based assays for COVID-19 and other respiratory pathogens, as the host response to infection may significantly differ depending on variants or subtypes.

Sensor technologies for quality control in engineered tissue manufacturing

The use of engineered cells, tissues, and organs has the opportunity to change the way injuries and diseases are treated. Commercialization of these groundbreaking technologies has been limited in part by the complex and costly nature of their manufacture. Process-related variability and even small changes in the manufacturing process of a living product will impact its quality. Without real-time integrated detection, the magnitude and mechanism of that impact are largely unknown. Real-time and non-destructive sensor technologies are key for in-process insight and ensuring a consistent product throughout commercial scale-up and/or scale-out. The application of a measurement technology into a manufacturing process requires cell and tissue developers to understand the best way to apply a sensor to their process, and for sensor manufacturers to understand the design requirements and end-user needs. Furthermore, sensors to monitor component cells' health and phenotype need to be compatible with novel integrated and automated manufacturing equipment. This review summarizes commercially relevant sensor technologies that can detect meaningful quality attributes during the manufacturing of regenerative medicine products, the gaps within each technology, and sensor considerations for manufacturing.

Machine learning and signal processing assisted differential mobility spectrometry (DMS) data analysis for chemical identification

Differential mobility spectrometry (DMS)-based detectors are being widely studied to detect chemical warfare agents, explosives, chemicals, drugs and analyze volatile organic compounds (VOCs). The dispersion plots from DMS devices are complex to effectively analyze through visual inspection. In the current work, we adopted machine learning to differentiate pure chemicals and identify chemicals in a mixture. In particular, we observed the convolutional neural network algorithm exhibits excellent accuracy in differentiating chemicals in their pure forms while also identifying chemicals in a mixture. In addition, we propose and validate the magnitude-squared coherence (msc) between the DMS data of known chemical composition and that of an unknown sample can be sufficient to inspect the chemical composition of the unknown sample. We have shown that the msc-based chemical identification requires the least amount of experimental data as opposed to the machine learning approach.

A Kalman filtering fuzzy logic algorithm for recognition of lane departure

In all kinds of traffic accidents, the unconscious departure of the vehicle from the lane is one of the most important reasons leading to the occurrence of these accidents. In view of the specific problem of lane departure, a lane departure decision-making method is established without calibration relying on the Kalman filtering fuzzy logic algorithm, according to the characteristics of expressway lanes, based on the machine vision and hearing fusion analysis of lane departure, integrating the extraction of the linear lane line model and the region of interest (ROI) in this paper to judge the degree of vehicle departure from the lane by integrating the slope values of the 2 lane lines in the road image. The results show that the system has good lane recognition capabilities and accurate departure decision-making capabilities, and meet the lane departure warning requirements in the expressway environment.

Exploring Negative Spillover Effects on Stakeholders: A Case Study on Social Media Talk about Crisis in the Food Industry Using Data Mining

Focusing on public-centered, social-mediated crisis communication, the current exploratory study drew on situational crisis communication theory to formulate a comprehensive view of consumer reactions to crisis. Data mining and automated content analysis techniques were utilized to analyze social media posts by the public during a crisis in the cereals industry. Two path analyses showed that: (a) crisis-related social media posts tended to skip over competitor brand products, followed by two major reaction paths—(1) a rational path based on guilt attribution that justifies implications for the company and (2) an emotional path associated with public distrust; and (b) public self-blame spilled over to other stakeholders such as the government and economic system. The results give voice to issues that concern the public during crises, both as individuals and as a community. They highlight the fact that sustainable crisis management should involve additional stakeholders. Conclusions and implications for society and practice are suggested.

Identification of Specific Substances in the FAIMS Spectra of Complex Mixtures Using Deep Learning

High-field asymmetric ion mobility spectrometry (FAIMS) spectra of single chemicals are easy to interpret but identifying specific chemicals within complex mixtures is difficult. This paper demonstrates that the FAIMS system can detect specific chemicals in complex mixtures. A homemade FAIMS system is used to analyze pure ethanol, ethyl acetate, acetone, 4-methyl-2-pentanone, butanone, and their mixtures in order to create datasets. An EfficientNetV2 discriminant model was constructed, and a blind test set was used to verify whether the deep-learning model is capable of the required task. The results show that the pre-trained EfficientNetV2 model completed convergence at a learning rate of 0.1 as well as 200 iterations. Specific substances in complex mixtures can be effectively identified using the trained model and the homemade FAIMS system. Accuracies of 100%, 96.7%, and 86.7% are obtained for ethanol, ethyl acetate, and acetone in the blind test set, which are much higher than conventional methods. The deep learning network provides higher accuracy than traditional FAIMS spectral analysis methods. This simplifies the FAIMS spectral analysis process and contributes to further development of FAIMS systems.

Peak detection and random forests classification software for gas chromatography/differential mobility spectrometry (GC/DMS) data

Gas Chromatography/Differential Mobility Spectrometry (GC/DMS) is an effective tool to discern volatile chemicals. The process of correlating GC/DMS data outputs to chemical identities requires time and effort from trained chemists due to lack of commercially available software and the lack of appropriate libraries. This paper describes the coupling of computer vision techniques to develop models for peak detection and can align chemical signatures across datasets. The result is an automatically generated peak table that provides integrated peak areas for the inputted samples. The software was tested against a simulated dataset, whereby the number of detected features highly correlated to the number of actual features (r² = 0.95). This software has also been developed to include random forests, a discriminant analysis technique that generates prediction models for application to unknown samples with different chemical signatures. In an example dataset described herein, the model achieves 3% classification error with 12 trees and 0% classification error with 48 trees. The number of trees can be optimized based on the computational resources available. We expect the public release of this software can provide other GC/DMS researchers with a tool for automated featured extraction and discriminant analysis capabilities.