Machine learning-enabled high-throughput industry screening of edible oils.

Long-term consumption of mixed fraudulent edible oils increases the risk of developing of chronic diseases which has been a threat to the public health globally. The complicated global supply-chain is making the industry malpractices had often gone undetected. In order to restore the confidence of consumers, traceability (and accountability) of every level in the supply chain is vital. In this work, we shown that machine learning (ML) assisted windowed spectroscopy (e.g., visible-band, infra-red band) produces high-throughput, non-destructive, and label-free authentication of edible oils (e.g., olive oils, sunflower oils), offers the feasibility for rapid analysis of large-scale industrial screening. We report achieving high-level of discriminant (AUC > 0.96) in the large-scale (n ≈ 11,500) of adulteration in olive oils. Notably, high clustering fidelity of 'spectral fingerprints' achieved created opportunity for (hypothesis-free) self-sustaining large database compilation which was never possible without machine learning. (137 words).

Novel time-domain NMR-based traits for rapid, label-free Olive oils profiling.

Olive oil is one of the oldest and essential edible oils in the market. The classification of olive oils (e.g. extra virgin, virgin, refined) is often influenced by factors ranging from its complex inherent physiochemical properties (e.g. fatty acid profiles) to the undisclosed manufacturing processes. Therefore, olive oils have been the target of adulteration due to its profitable margin. In this work, we demonstrate that multi-parametric time-domain NMR relaxometry can be used to rapidly (in minutes) identify and classify olive oils in label-free and non-destructive manner. The subtle differences in molecular microenvironment of the olive oils induce substantial changes in the relaxation mechanism in the time-domain NMR regime. We demonstrated that the proposed NMR-relaxation based detection (AUC = 0.95) is far more sensitive and specific than the current gold-standards in the field i.e. near-infrared spectroscopy (AUC = 0.84) and Ultraviolet-visible spectroscopy (AUC = 0.73), respectively. We further show that, albeit the inherent complexity of olive plant natural phenotypic variations, the proposed NMR-relaxation based traits may be a viable mean (AUC = 0.71) in tracing the regions of origin for olive trees, in agreement with their geographical orientation.