Food fraud, the sale of goods that have in some way been mislabelled or tampered with, is an increasing concern, with a number of high profile documented incidents in recent years. These recent incidents and their scope show that there are gaps in the food chain where food authentication methods are not applied or otherwise not sufficient and more accessible detection methods would be beneficial. This paper investigates the utility of affordable and portable visible range spectroscopy hardware with partial least squares discriminant analysis (PLS-DA) when applied to the differentiation of apple types and organic status. This method has the advantage that it is accessible throughout the supply chain, including at the consumer level. Scans were acquired of 132 apples of three types, half of which are organic and the remaining non-organic. The scans were preprocessed with zero correction, normalisation and smoothing. Two tests were used to determine accuracy, the first using 10-fold cross-validation and the second using a test set collected in different ambient conditions. Overall, the system achieved an accuracy of 94% when predicting the type of apple and 66% when predicting the organic status. Additionally, the resulting models were analysed to find the regions of the spectrum that had the most significance. Then, the accuracy when using three-channel information (RGB) is presented and shows the improvement provided by spectroscopic data.

Trace methane detection in the parts per million range is reported using a novel detection scheme based on optical emission spectra from low temperature atmospheric pressure microplasmas. These bright low-cost plasma sources were operated under non-equilibrium conditions, producing spectra with a complex and variable sensitivity to trace levels of added gases. A data-driven machine learning approach based on partial least squares discriminant analysis was implemented for CH₄ concentrations up to 100 ppm in He, to provide binary classification of samples above or below a threshold of 2 ppm. With a low-resolution spectrometer and a custom spectral alignment procedure, a prediction accuracy of 98% was achieved, demonstrating the power of machine learning with otherwise prohibitively complex spectral analysis. This work establishes proof of principle for low cost and high-resolution trace gas detection with the potential for field deployment and autonomous remote monitoring.

Trace methane detection in the parts per million range is reported using a novel detection scheme based on optical emission spectra from low temperature atmospheric pressure microplasmas. These bright low-cost plasma sources were operated under non-equilibrium conditions, producing spectra with a complex and variable sensitivity to trace levels of added gases. A data-driven machine learning approach based on Partial Least Squares Discriminant Analysis (PLS-DA) was implemented for CH4 concentrations up to 100 ppm in He, to provide binary classification of samples above or below a threshold of 2 ppm. With a low-resolution spectrometer and a custom spectral alignment procedure, a prediction accuracy of 98% was achieved, demonstrating the power of machine learning with otherwise prohibitively complex spectral analysis. This work establishes proof of principle for low cost and high-resolution trace gas detection with the potential for field deployment and autonomous remote monitoring.