Alternative data mining/machine learning methods for the analytical evaluation of food quality and authenticity - A review

Wheat Kernel Variety Identification Based on a Large Near-Infrared Spectral Dataset and a Novel Deep Learning-Based Feature Selection Method

Near-infrared (NIR) hyperspectroscopy becomes an emerging nondestructive sensing technology for inspection of crop seeds. A large spectral dataset of more than 140,000 wheat kernels in 30 varieties was prepared for classification. Feature selection is a critical segment in large spectral data analysis. A novel convolutional neural network-based feature selector (CNN-FS) was proposed to screen out deeply target-related spectral channels. A convolutional neural network with attention (CNN-ATT) framework was designed for one-dimension data classification. Popular machine learning models including support vector machine (SVM) and partial least square discrimination analysis were used as the benchmark classifiers. Features selected by conventional feature selection algorithms were considered for comparison. Results showed that the designed CNN-ATT produced a higher performance than the compared classifier. The proposed CNN-FS found a subset of features, which made a better representation of raw dataset than conventional selectors did. The CNN-ATT achieved an accuracy of 93.01% using the full spectra and keep its high precision (90.20%) by training on the 60-channel features obtained via the CNN-FS method. The proposed methods have great potential for handling the analyzing tasks on other large spectral datasets. The proposed feature selection structure can be extended to design other new model-based selectors. The combination of NIR hyperspectroscopic technology and the proposed models has great potential for automatic nondestructive classification of single wheat kernels.

1H NMR chemometric models for classification of Czech wine type and variety

A set of 917 wines of Czech origin were analysed using nuclear magnetic resonance spectroscopy (NMR) with the aim of building and evaluating multivariate statistical models and machine learning methods for the classification of 6 types based on colour and residual sugar content, 13 wine grape varieties and 4 locations based on ¹H NMR spectra. The predictive models afforded greater than 93% correctness for classifying dry and medium dry, medium, and sweet white wines and dry red wines. The trained Random Forest (RF) model classified Pinot noir with 96% correctness, Blaufränkisch 96%, Riesling 92%, Cabernet Sauvignon 77%, Chardonnay 76%, Gewürtztraminer 60%, Hibernal 60%, Grüner Veltliner 52%, Pinot gris 48%, Sauvignon Blanc 45%, and Pálava 40%. Pinot blanc and Chardonnay, varieties that are often mistakenly interchanged, were discriminated with 71% correctness. The findings support chemometrics as a tool for predicting important features in wine, particularly for quality assessment and fraud detection.

Fraud in Animal Origin Food Products: Advances in Emerging Spectroscopic Detection Methods over the Past Five Years

Animal origin food products, including fish and seafood, meat and poultry, milk and dairy foods, and other related products play significant roles in human nutrition. However, fraud in this food sector frequently occurs, leading to negative economic impacts on consumers and potential risks to public health and the environment. Therefore, the development of analytical techniques that can rapidly detect fraud and verify the authenticity of such products is of paramount importance. Traditionally, a wide variety of targeted approaches, such as chemical, chromatographic, molecular, and protein-based techniques, among others, have been frequently used to identify animal species, production methods, provenance, and processing of food products. Although these conventional methods are accurate and reliable, they are destructive, time-consuming, and can only be employed at the laboratory scale. On the contrary, alternative methods based mainly on spectroscopy have emerged in recent years as invaluable tools to overcome most of the limitations associated with traditional measurements. The number of scientific studies reporting on various authenticity issues investigated by vibrational spectroscopy, nuclear magnetic resonance, and fluorescence spectroscopy has increased substantially over the past few years, indicating the tremendous potential of these techniques in the fight against food fraud. It is the aim of the present manuscript to review the state-of-the-art research advances since 2015 regarding the use of analytical methods applied to detect fraud in food products of animal origin, with particular attention paid to spectroscopic measurements coupled with chemometric analysis. The opportunities and challenges surrounding the use of spectroscopic techniques and possible future directions will also be discussed.

Geographic origin discrimination of pork from different Chinese regions using mineral elements analysis assisted by machine learning techniques

Porkis thelargest-producedandmost-consumedmeat intheworld, and the food market globalization has increased public attention to food origin. Therefore, advanced techniques are required to determine the geographical origin of pork. This study investigated the prospects of using fingerprint analysis of mineral elements and machine learning to facilitate the traceability of pork origin in China. The results showed that each of seven regions had a characteristic element content profile. To improve the performance of the origin traceability model, popular machine learning techniques in food authenticity were introduced. This resulted in a high-performance origin tracing model. Comparing various machine learning algorithms, the feedforward neural network achieved superior performance with an overall accuracy of 95.71% and area under the curve close to one. Thus, this study proves that mineral elements analysis assisted by machine learning can be applied to distinguish pork samples within a country.

Wine Authenticity and Traceability with the Use of FT-IR

Fourier transform infrared spectroscopy (FT-IR) has gained popularity in the wine sector due to its simplicity and ability to provide a wine’s fingerprint. For this reason, it is often used for authentication and traceability purposes with more than satisfactory results. In this review, an outline of the reasons why authenticity and traceability are important to the wine sector is given, along with a brief overview of the analytical methods used for their attainment; statistical issues and compounds, on which authentication usually is based, are discussed. Moreover, insight on the mode of action of FT-IR is given, along with successful examples from its use in different areas of interest for classification. Finally, prospects and challenges for suggested future research are given. For more accurate and effective analyses, the construction of a large database consisting of wines from different regions, varieties and winemaking protocols is suggested.

A Deep Learning Method for Yogurt Preferences Prediction Using Sensory Attributes

During the development of innovative products, consumer preferences are the essential factors for yogurt producers to improve their market share. A high-performance prediction method will be beneficial to understand the intrinsic relevance between preferences and sensory attributes. In this study, a novel deep learning method is proposed that uses an autoencoder to extract product features from the sensory attributes scored by experts, and the sensory features acquired are regressed on consumer preferences with support vector machine analysis. Model performance analysis, hedonic contour mapping, and feature clustering were implemented to validate the overall learning process. The results showed that the deep learning model can vouch an acceptable level of accuracy, and the hedonic mapping reflected could supply a great help for producers’ product design or modification. Finally, hierarchical clustering analysis revealed that for all three brands of yogurts, low temperature (4 °C) storage for no more than 4 weeks can promise the highest consumer preferences.

Utilization of text mining as a big data analysis tool for food science and nutrition

Big data analysis has found applications in many industries due to its ability to turn huge amounts of data into insights for informed business and operational decisions. Advanced data mining techniques have been applied in many sectors of supply chains in the food industry. However, the previous work has mainly focused on the analysis of instrument-generated data such as those from hyperspectral imaging, spectroscopy, and biometric receptors. The importance of digital text data in the food and nutrition has only recently gained attention due to advancements in big data analytics. The purpose of this review is to provide an overview of the data sources, computational methods, and applications of text data in the food industry. Text mining techniques such as word-level analysis (e.g., frequency analysis), word association analysis (e.g., network analysis), and advanced techniques (e.g., text classification, text clustering, topic modeling, information retrieval, and sentiment analysis) will be discussed. Applications of text data analysis will be illustrated with respect to food safety and food fraud surveillance, dietary pattern characterization, consumer-opinion mining, new-product development, food knowledge discovery, food supply-chain management, and online food services. The goal is to provide insights for intelligent decision-making to improve food production, food safety, and human nutrition.

Diagnosis of ventilator-associated pneumonia using electronic nose sensor array signals: solutions to improve the application of machine learning in respiratory research

Background

Ventilator-associated pneumonia (VAP) is a significant cause of mortality in the intensive care unit. Early diagnosis of VAP is important to provide appropriate treatment and reduce mortality. Developing a noninvasive and highly accurate diagnostic method is important. The invention of electronic sensors has been applied to analyze the volatile organic compounds in breath to detect VAP using a machine learning technique. However, the process of building an algorithm is usually unclear and prevents physicians from applying the artificial intelligence technique in clinical practice. Clear processes of model building and assessing accuracy are warranted. The objective of this study was to develop a breath test for VAP with a standardized protocol for a machine learning technique.

Methods

We conducted a case-control study. This study enrolled subjects in an intensive care unit of a hospital in southern Taiwan from February 2017 to June 2019. We recruited patients with VAP as the case group and ventilated patients without pneumonia as the control group. We collected exhaled breath and analyzed the electric resistance changes of 32 sensor arrays of an electronic nose. We split the data into a set for training algorithms and a set for testing. We applied eight machine learning algorithms to build prediction models, improving model performance and providing an estimated diagnostic accuracy.

Results

A total of 33 cases and 26 controls were used in the final analysis. Using eight machine learning algorithms, the mean accuracy in the testing set was 0.81 ± 0.04, the sensitivity was 0.79 ± 0.08, the specificity was 0.83 ± 0.00, the positive predictive value was 0.85 ± 0.02, the negative predictive value was 0.77 ± 0.06, and the area under the receiver operator characteristic curves was 0.85 ± 0.04. The mean kappa value in the testing set was 0.62 ± 0.08, which suggested good agreement.

Conclusions

There was good accuracy in detecting VAP by sensor array and machine learning techniques. Artificial intelligence has the potential to assist the physician in making a clinical diagnosis. Clear protocols for data processing and the modeling procedure needed to increase generalizability.

The occurrence: A meaningful parameter to be considered in the validation of multivariate classification-based screening methods - Application for authenticating virgin olive oil

The development of multivariate screening analytical methods in the analytical chemistry field focused particularly on food authentication is growing in recent years, which is evidenced by the increase of scientific publications. Currently there are several guides and technical reports about how -univariate qualitative methods should be properly validated to produce reliable and accurate (fitted-for-purpose) results. Nevertheless, this is not the case when multivariate methods are considered. Aimed at redressing this untenable disadvantage, this paper proposes some guidelines for the validation of multivariate classification-based screening methods. As an application example, the detection of adulteration of virgin olive oil with any other edible vegetal oils is showed. The analytical techniques employed are liquid chromatography coupled to diode array detector (LC-DAD) and gas chromatography coupled to flame ionization detector (GC-FID). For the correct validation of the multivariate screening method a new parameter which never considered before, named occurrence, is accounted. Also, it has been developed two new applicability indicators of the multivariate screening methods: the assignation error index (I_ERROR) and the index saving (I_SAVING) to establish the validation requirements. Then the validation parameters of the methods: precision (or target predictive value), sensitivity, non-target predictive value, specificity and accuracy were estimated. The main conclusion of the work has been the need to take accounts the occurrence value to establish the specific validation requirements to apply the multivariate screening method in a particular scenario.

Chemometric authentication of farming systems of origin of food (milk and ripened cheese) using infrared spectra, fatty acid profiles, flavor fingerprints, and sensory descriptions

Milk samples from 1264 cows in 85 farms were authenticated for different farming-systems using a 10-fold cross-validated linear-discriminant-analysis using Fourier-transform infrared spectra (FTIRS) and gas-chromatographic fatty-acid (FA) profiles. FTIRS gave correct classification greater than FAs (97.4% vs. 81.1%) during calibration, but slightly worse in validation (73.5% vs 77.3%) and their combination improved the results. All milk samples were processed into ripened model-cheeses, and analyzed by near-infrared-spectrometry (NIRS), by proton-transfer-reaction time-of-flight mass-spectrometry for their volatile organic compound (VOCs) fingerprint and by panel sensory profiling (SENS). Farming-system authentication on cheese samples was less efficient than on milk, but still possible. The instrumental methods yielded similar validation results, better than SENS, and their combination improved the correct classification rate. The efficiency of the different technics was affected by specific farming systems. In conclusion, dairy products could be discriminated for farming-systems with acceptable accuracy, but the methods tested differ in sampling procedure, rapidity and costs.