Spectroscopy and imaging technologies coupled with machine learning for the assessment of the microbiological spoilage associated to ready-to-eat leafy vegetables

AI-based processing of future prepared foods: Progress and prospects

The prepared foods sector has grown rapidly in recent years, driven by the fast pace of modern living and increasing consumer demand for convenience. Prepared foods are taking an increasingly important role in the modern catering industry due to their ease of storage, transportation, and operation. However, their processing faces several challenges, including labor shortages, inefficient sorting, inadequate cleaning, unsafe cutting processes, and a lack of industry standards. The development of artificial intelligence (AI) will change the processing of prepared foods. This review summarizes the progress and prospects of AI applications in the sorting/classification, cleaning, cutting, preprocessing, and freezing of prepared foods, encompassing techniques such as mathematical modeling, chemometrics, machine learning, fuzzy logic, and adaptive neuro fuzzy inference system. For example, AI-powered sorting systems using computer vision have improved accuracy in ingredient classification, while deep learning models in cleaning processes have enhanced microbial contamination detection with high spectral imaging techniques. Despite challenges like managing large-scale data and complex models, AI has shown significant potential to inspire both industry practice and research. AI applications can enhance the efficiency, accuracy, and consistency of prepared foods processing, while also reducing labor costs, improving hygiene monitoring, minimizing resource waste, and decreasing environmental impact. Furthermore, AI-driven resource optimization has demonstrated its potential in reducing energy consumption and promoting sustainable food production practices. In the future, AI technology is expected to further improve model generalization and operation precision, driving the food processing industry toward smarter, more sustainable development. This study provides valuable insights to encourage further innovation in AI applications within food processing and technological advancement in the food industry.

The Role of Near-Infrared Spectroscopy in Food Quality Assurance: A Review of the Past Two Decades

During food quality control, NIR technology enables the rapid and non-destructive determination of the typical quality characteristics of food categories, their origin, and the detection of potential counterfeits. Over the past 20 years, the NIR results for a variety of food groups-including meat and meat products, milk and milk products, baked goods, pasta, honey, vegetables, fruits, and luxury items like coffee, tea, and chocolate-have been compiled. This review aims to give a broad overview of the NIRS processes that have been used thus far to assist researchers employing non-destructive techniques in comparing their findings with earlier data and determining new research directions.

Innovative strategies for protein content determination in dried laver (Porphyra spp.): Evaluation of preprocessing methods and machine learning algorithms through short-wave infrared imaging

In this study, we explored the application of Short-Wave Infrared (SWIR) hyperspectral imaging combined with Competitive Adaptive Reweighted Sampling (CARS) and advanced regression models for the non-destructive assessment of protein content in dried laver. Utilizing a spectral range of 900-1700 nm, we aimed to refine the quality control process by selecting informative wavelengths through CARS and applying various preprocessing techniques (standard normal variate [SNV], Savitzky-Golay filtering [SG], Orthogonal Signal Correction [OSC], and StandardScaler [SS]) to enhance the model's accuracy. The SNV-OSC-StandardScaler- Support vector regression (SVR) model trained on CARS-selected wavelengths significantly outperformed the other configurations, achieving a prediction determination coefficient (Rp2) of 0.9673, root mean square error of prediction of 0.4043, and residual predictive deviation of 5.533. These results highlight SWIR hyperspectral imaging's potential as a rapid and precise tool for assessing dried laver quality, aiding food industry quality control and dried laver market growth.

Monitoring the Bioprotective Potential of Lactiplantibacillus pentosus Culture on Pathogen Survival and the Shelf-Life of Fresh Ready-to-Eat Salads Stored under Modified Atmosphere Packaging

Globally, fresh vegetables or minimally processed salads have been implicated in several foodborne disease outbreaks. This work studied the effect of Lactiplantibacillus pentosus FMCC-B281 cells (F) and its supernatant (S) on spoilage and on the fate of Listeria monocytogenes and Escherichia coli O157:H7 on fresh-cut ready-to-eat (RTE) salads during storage. Also, Fourier transform infrared (FTIR) and multispectral imaging (MSI) analysis were used as rapid and non-destructive techniques to estimate the microbiological status of the samples. Fresh romaine lettuce, rocket cabbage, and white cabbage were used in the present study and were inoculated with L. pentosus and the two pathogens. The strains were grown at 37 °C for 24 h in MRS and BHI broths, respectively, and then were centrifuged to collect the supernatant and the pellet (cells). Cells (F, ~5 log CFU/g), the supernatant (S), and a control (C, broth) were used to spray the leaves of each fresh vegetable that had been previously contaminated (sprayed) with the pathogen (3 log CFU/g). Subsequently, the salads were packed under modified atmosphere packaging (10%CO2/10%O2/80%N2) and stored at 4 and 10 °C until spoilage. During storage, microbiological counts and pH were monitored in parallel with FTIR and MSI analyses. The results showed that during storage, the population of the pathogens increased for lettuce and rocket independent of the treatment. For cabbage, pathogen populations remained stable throughout storage. Regarding the spoilage microbiota, the Pseudomonas population was lower in the F samples, while no differences in the populations of Enterobacteriaceae and yeasts/molds were observed for the C, F, and S samples stored at 4 °C. According to sensory evaluation, the shelf-life was shorter for the control samples in contrast to the S and F samples, where their shelf-life was elongated by 1-2 days. Initial pH values were ca. 6.0 for the three leafy vegetables. An increase in the pH of ca. 0.5 values was recorded until the end of storage at both temperatures for all cases of leafy vegetables. FTIR and MSI analyses did not satisfactorily lead to the estimation of the microbiological quality of salads. In conclusion, the applied bioprotective strain (L. pentosus) can elongate the shelf-life of the RTE salads without an effect on pathogen growth.

Combination of near-infrared spectroscopy with Wasserstein generative adversarial networks for rapidly detecting raw material quality for formula products

Near-infrared spectroscopy (NIRS) has emerged as a key technique for rapid quality detection owing to its fast, non-destructive, and eco-friendly characteristics. However, its practical implementation within the formulation industry is challenging owing to insufficient data, which renders model fitting difficult. The complexity of acquiring spectra and spectral reference values results in limited spectral data, aggravating the problem of low generalization, which diminishes model performance. To address this problem, we introduce what we believe to be a novel approach combining NIRS with Wasserstein generative adversarial networks (WGANs). Specifically, spectral data are collected from representative samples of raw material provided by a formula enterprise. Then, the WGAN augments the database by generating synthetic data resembling the raw spectral data. Finally, we establish various prediction models using the PLSR, SVR, LightGBM, and XGBoost algorithms. Experimental results show the NIRS-WGAN method significantly improves the performance of prediction models, with R2 and RMSE of 0.949 and 1.415 for the chemical components of sugar, respectively, and 0.922 and 0.243 for nicotine. The proposed framework effectively enhances the predictive capabilities of various models, addressing the issue caused by limited training data in NIRS prediction tasks.

Combining AI Tools with Non-Destructive Technologies for Crop-Based Food Safety: A Comprehensive Review

On a global scale, food safety and security aspects entail consideration throughout the farm-to-fork continuum, considering food's supply chain. Generally, the agrifood system is a multiplex network of interconnected features and processes, with a hard predictive rate, where maintaining the food's safety is an indispensable element and is part of the Sustainable Development Goals (SDGs). It has led the scientific community to develop advanced applied analytical methods, such as machine learning (ML) and deep learning (DL) techniques applied for assessing foodborne diseases. The main objective of this paper is to contribute to the development of the consensus version of ongoing research about the application of Artificial Intelligence (AI) tools in the domain of food-crop safety from an analytical point of view. Writing a comprehensive review for a more specific topic can also be challenging, especially when searching within the literature. To our knowledge, this review is the first to address this issue. This work consisted of conducting a unique and exhaustive study of the literature, using our TriScope Keywords-based Synthesis methodology. All available literature related to our topic was investigated according to our criteria of inclusion and exclusion. The final count of data papers was subject to deep reading and analysis to extract the necessary information to answer our research questions. Although many studies have been conducted, limited attention has been paid to outlining the applications of AI tools combined with analytical strategies for crop-based food safety specifically.

Spectroscopic Data for the Rapid Assessment of Microbiological Quality of Chicken Burgers

The rapid assessment of the microbiological quality of highly perishable food commodities is of great importance. Spectroscopic data coupled with machine learning methods have been investigated intensively in recent years, because of their rapid, non-destructive, eco-friendly qualities and their potential to be used on-, in- or at-line. In the present study, the microbiological quality of chicken burgers was evaluated using Fourier transform infrared (FTIR) spectroscopy and multispectral imaging (MSI) in tandem with machine learning algorithms. Six independent batches were purchased from a food industry and stored at 0, 4, and 8 °C. At regular time intervals (specifically every 24 h), duplicate samples were subjected to microbiological analysis, FTIR measurements, and MSI sampling. The samples (n = 274) acquired during the data collection were classified into three microbiological quality groups: “satisfactory”: 4−7 log CFU/g, “acceptable”: 7−8 log CFU/g, and “unacceptable”: >8 logCFU/g. Subsequently, classification models were trained and tested (external validation) with several machine learning approaches, namely partial least squares discriminant analysis (PLSDA), support vector machine (SVM), random forest (RF), logistic regression (LR), and ordinal logistic regression (OLR). Accuracy scores were attained for the external validation, exhibiting FTIR data values in the range of 79.41−89.71%, and, for the MSI data, in the range of 74.63−85.07%. The performance of the models showed merit in terms of the microbiological quality assessment of chicken burgers.

Critical review and recent advances of 2D materials-Based gas sensors for food spoilage detection

Many people around the world are concerned about meat safety and quality, which has resulted in the ongoing advancement of packaged food technology. Since the emergence of graphene in 2004, the number of studies on layered two-dimensional materials (2DMs) for applications ranging from food packaging to meat quality monitoring has been expanding quickly. Recently, scientists have been working hard to develop a novel class of 2DMs that keep the good things about graphene but don't have zero bandgaps at room temperature. Much work has been done on layered transition metal dichalcogenides (TMDCs) like different metal sulfides and selenides for meat spoilage gas sensors. This review looks at (i) the main indicators of meat spoilage and (ii) the detection methods that can be used to find out if meat has been spoiled, such as chemiresistive, electrochemical, and optical methods. (iii) the role of 2DMs in meat spoilage detection and (iv) the emergence of advanced methods for selective classification of target analytes in meat/food spoilage detection in recent years. Thus, this review demonstrates the potential scope of 2DMs for developing intelligent sensor systems for food and meat spoilage detection with high viability, simplicity, cost-effectiveness, and other multipurpose tools.