Total synchronous fluorescence spectroscopy coupled with deep learning to rapidly identify the authenticity of sesame oil

The application of laser‑induced fluorescence in oil spill detection

Over the past two decades, oil spills have been one of the most serious ecological disasters, causing massive damage to the aquatic and terrestrial ecosystems as well as the socio-economy. In view of this situation, several methods have been developed and utilized to analyze oil samples. Among these methods, laser-induced fluorescence (LIF) technology has been widely used in oil spill detection due to its classification method, which is based on the fluorescence characteristics of chemical material in oil. This review systematically summarized the LIF technology from the perspective of excitation wavelength selection and the application of traditional and novel machine learning algorithms to fluorescence spectrum processing, both of which are critical for qualitative and quantitative analysis of oil spills. It can be seen that an appropriate excitation wavelength is indispensable for spectral discrimination due to different kinds of polycyclic aromatic hydrocarbons' (PAHs) compounds in petroleum products. By summarizing some articles related to LIF technology, we discuss the influence of the excitation wavelength on the accuracy of the oil spill detection model and proposed several suggestions on the selection of excitation wavelength. In addition, we introduced some traditional and novel machine learning (ML) algorithms and discussed the strengths and weaknesses of these algorithms and their applicable scenarios. With an appropriate excitation wavelength and data processing algorithm, it is believed that laser-induced fluorescence technology will become an efficient technique for real-time detection and analysis of oil spills.

LC-MS Metabolomic Profiling of Five Types of Unrefined, Cold-Pressed Seed Oils to Identify Markers to Determine Oil Authenticity and to Test for Oil Adulteration

The authenticity of food products marketed as health-promoting foods-especially unrefined, cold-pressed seed oils-should be controlled to ensure their quality and safeguard consumers and patients. Metabolomic profiling using liquid chromatography coupled to quadrupole time-of-flight mass spectrometry (LC-QTOF) was employed to identify authenticity markers for five types of unrefined, cold-pressed seed oils: black seed oil (Nigella sativa L.), pumpkin seed oil (Cucurbita pepo L.), evening primrose oil (Oenothera biennis L.), hemp oil (Cannabis sativa L.) and milk thistle oil (Silybum marianum). Of the 36 oil-specific markers detected, 10 were established for black seed oil, 8 for evening primrose seed oil, 7 for hemp seed oil, 4 for milk thistle seed oil and 7 for pumpkin seed oil. In addition, the influence of matrix variability on the oil-specific metabolic markers was examined by studying binary oil mixtures containing varying volume percentages of each tested oil and each of three potential adulterants: sunflower, rapeseed and sesame oil. The presence of oil-specific markers was confirmed in 7 commercial oil mix products. The identified 36 oil-specific metabolic markers proved useful for confirming the authenticity of the five target seed oils. The ability to detect adulterations of these oils with sunflower, rapeseed and sesame oil was demonstrated.

CNN-LSTM Neural Network for Identification of Pre-Cooked Pasta Products in Different Physical States Using Infrared Spectroscopy

Infrared (IR) spectroscopy is nondestructive, fast, and straightforward. Recently, a growing number of pasta companies have been using IR spectroscopy combined with chemometrics to quickly determine sample parameters. However, fewer models have used deep learning models to classify cooked wheat food products and even fewer have used deep learning models to classify Italian pasta. To solve these problems, an improved CNN-LSTM neural network is proposed to identify pasta in different physical states (frozen vs. thawed) using IR spectroscopy. A one-dimensional convolutional neural network (1D-CNN) and long short-term memory (LSTM) were constructed to extract the local abstraction and sequence position information from the spectra, respectively. The results showed that the accuracy of the CNN-LSTM model reached 100% after using principal component analysis (PCA) on the Italian pasta spectral data in the thawed state and 99.44% after using PCA on the Italian pasta spectral data in the frozen form, verifying that the method has high analytical accuracy and generalization. Therefore, the CNN-LSTM neural network combined with IR spectroscopy helps to identify different pasta products.

Detection of the Adulteration of Motor Oil by Laser Induced Fluorescence Spectroscopy and Chemometric Techniques

Petroleum products are the target of fraudulent practices due to their high commercial value. The aim of this study is to provide a new analysis system to assess motor oil adulteration. For this purpose, Laser Induced Fluorescence (LIF) spectroscopy was exploited coupled with chemometric tools to detect motor oil adulteration by three types of cheap motor oils. Principal Component Analysis (PCA) was able to distinguish samples in three groups according to the type of adulterant. Besides, Partial Least Squares Regression (PLSR) was exploited to determine the percentage of adulteration. The best model was obtained with a regression coefficient of 0.96, Root Mean Square Error of Prediction (RMSEP) of 2.83, Standard Error of Prediction (SEP) of 2.83 and Bias of 0.40. The main results of this work provide new analysis system using the combination of LIF spectroscopy combined to PCA and PLS as an efficient and fast method for motor oil analysis.

Machine Learning-Assisted Synchronous Fluorescence Sensing Approach for Rapid and Simultaneous Quantification of Thiabendazole and Fuberidazole in Red Wine

Rapid analysis of components in complex matrices has always been a major challenge in constructing sensing methods, especially concerning time and cost. The detection of pesticide residues is an important task in food safety monitoring, which needs efficient methods. Here, we constructed a machine learning-assisted synchronous fluorescence sensing approach for the rapid and simultaneous quantitative detection of two important benzimidazole pesticides, thiabendazole (TBZ) and fuberidazole (FBZ), in red wine. First, fluorescence spectra data were collected using a second derivative constant-energy synchronous fluorescence sensor. Next, we established a prediction model through the machine learning approach. With this approach, the recovery rate of TBZ and FBZ detection of pesticide residues in red wine was 101% ± 5% and 101% ± 15%, respectively, without resorting complicated pretreatment procedures. This work provides a new way for the combination of machine learning and fluorescence techniques to solve the complexity in multi-component analysis in practical applications.

Olive oil classification with Laser-induced fluorescence (LIF) spectra using 1-dimensional convolutional neural network and dual convolution structure model

Laser-induced fluorescence (LIF) spectroscopy is widely used for the analysis and classification of olive oil. This paper proposes the classification of LIF data using a specific 1-dimensional convolutional neural network (1D-CNN) model, which does not require pre-processing steps such as normalisation or denoising and can be flexibly applied to massive data. However, by adding a dual convolution structure (Dual-conv) to the model, the features of the 1-dimensional spectra are more scattered within one convolution-pooling process; thus, the classification effects are improved. The models were validated through an olive oil classification experiment which contained a total of 72,000 sets of LIF spectra data, and the classification accuracy rate reached ∼99.69%. Additionally, a common classification approach, the support vector machine (SVM), was utilised for the comparison of the results. The results show that the neural networks perform better than the SVM. The Dual-conv model structure has a faster convergence speed and higher evaluation parameters than those of the 1D-CNN in the same period of iterations, without increasing the data dimension.