Recent advances in shelf life prediction models for monitoring food quality

Rapid determination of total colony counts and prediction of shelf life of dried tofu using LF-NMR

Dried tofu is a type of bean food that is popular among Chinese people. However, because dried tofu is usually exposed to air during storage or shelf life, this may lead to a rapid increase in colony counts and spoilage, resulting in shortened shelf life. The traditional method for measuring total colony counts is the plate counting method, which is complex and time consuming. Therefore, it is particularly important to explore a method that can quickly, accurately, and non-destructively determine the total colony counts of dried tofu and predict its shelf life. In this study, the samples were measured by low-field nuclear magnetic resonance (LF-NMR) to obtain transverse relaxation data. Then, the total colony counts in dried tofu was determined by plate counting method, and it was used as a reference value. The backpropagation artificial neural network (BP-ANN) was used to analyze the transverse relaxation data. The results show that the BP-ANN model could quickly and accurately predict total colony counts. In addition, the total colony counts predicted by BP-ANN were used to predict the shelf life. Comparing the predicted shelf life with the actual shelf life of dried tofu. The results show that the relative error between them is less than 10%. Thus, the shelf life model established by the BP-ANN predicted value has a certain reliability. This study provides some references for rapid and nondestructive determination of total colony counts and shelf life prediction of dried tofu.

"Reference sample comparison method": A new voltammetric electronic tongue method and its application in assessing the shelf life of fresh milk

Shelf life is a critical comprehensive indicator of food quality. Voltammetric electronic tongue (V-Et), is well-suited for assessing food shelf life, due to its capable of capturing food overall fingerprints. This study designed a "reference sample comparison method" for V-Et to assess the shelf life of fresh milk. Quality differences between milk samples of different shelf lives and reference samples were quantified by differential degree (Dd) values. A new "one-to-one" model of milk shelf life was established based on Dd values, and significantly improved predictive accuracy by 11.14 %-17.17 % and 14.86 %-44.47 % in overall quality shelf life assessment compared to "many-to-one" models based on SVM and DFA. Even in the more sophisticated evaluation of microbial safety and sensory quality shelf life, it attained relative errors of 13.57 % and 7.68 %, respectively. All these findings showed the significant potential of the "reference sample comparison method" in assessing food shelf life with V-Et.

Application of Convolutional Neural Networks and Recurrent Neural Networks in Food Safety

This review explores the application of convolutional neural networks (CNNs) and recurrent neural networks (RNNs) in food safety detection and risk prediction. This paper highlights the advantages of CNNs in image processing and feature recognition, as well as the powerful capabilities of RNNs (especially their variant LSTM) in time series data modeling. This paper also makes a comparative analysis in many aspects: Firstly, the advantages and disadvantages of traditional food safety detection and risk prediction methods are compared with deep learning technologies such as CNNs and RNNs. Secondly, the similarities and differences between CNNs and fully connected neural networks in processing image data are analyzed. Furthermore, the advantages and disadvantages of RNNs and traditional statistical modeling methods in processing time series data are discussed. Finally, the application directions of CNNs in food safety detection and RNNs in food safety risk prediction are compared. This paper also discusses combining these deep learning models with technologies such as the Internet of Things (IoT), blockchain, and federated learning to improve the accuracy and efficiency of food safety detection and risk warning. Finally, this paper mentions the limitations of RNNs and CNNs in the field of food safety, as well as the challenges in the interpretability of the model, and suggests the use of interpretable artificial intelligence (XAI) technology to improve the transparency of the model.

Artificial neural network-based shelf life prediction approach in the food storage process: A review

The prediction of food shelf life has become a vital tool for distributors and consumers, enabling them to determine storage and optimal edible time, thus avoiding unexpected food waste. Artificial neural network (ANN) have emerged as an effective, fast and accurate method for modeling, simulating and predicting shelf life in food. ANNs are capable of tackling nonlinear, complex and ill-defined problems between the variables without prior knowledge. ANN model exhibited excellent fit performance evidenced by low root mean squared error and high correlation coefficient. The low relative error between actual values and predicted values from the ANN model demonstrates its high accuracy. This paper describes the modeling of ANN in food quality prediction, encompassing commonly used ANN architectures, ANN simulation techniques, and criteria for evaluating ANN model performance. The review focuses on the application of ANN for modeling nonlinear food quality during storage, including dairy, meat, aquatic, fruits, and vegetables products. The future prospects of ANN development mainly focus on optimal models and learning algorithm selection, multiple model fusion, self-learning and self-correcting shelf-life prediction model development, and the potential utilization of deep learning techniques.

Chitosan and inulin synergized with Lactiplantibacillus plantarum LPP95 to improve the quality characteristics of low-salt pickled tuber mustard

Low-salt pickled vegetables are in line with a healthier diet, yet ensuring consistent quality of such products is challenging. In this study, low-salt tuber mustard pickles fermented with Lactiplantibacillus plantarum LPP95 in the presence of chitosan and inulin were analyzed over a 30-day period, and quality changes were evaluated. Total acid productions along with high bacterial counts (106 CFU/mL) were observed in the initial 20 days during indoor storage temperature, in which the reduced fiber aperture was found significantly lead to an increase in crispness (16.94 ± 1.87 N) and the maintenance of a low nitrate content (1.23 ± 0.01 mg/kg). Moreover, the combined pickling treatment resulted in higher malic acid content, lower tartaric acid content, and a decrease in the content of bitter amino acids (e.g., isoleucine and leucine), thus leading to an increase in the proportion of sweet amino acids. Additionally, combined pickling led to the production of unique volatile flavor compounds, especially the distinct spicy flavor compounds isothiocyanates. Moreover, the combined pickling treatment resulted in an increase in the abundance of Lactiplantibacillus and promoted microbial diversity within the fermentation system. Thus, the synergistic effect among chitosan, inulin, and L. plantarum LPP95 significantly enhanced the quality of pickles. The study offers a promising strategy to standardize the quality of low-salt fermented vegetables.

Research Progress of Machine Learning in Extending and Regulating the Shelf Life of Fruits and Vegetables

Fruits and vegetables are valued for their flavor and high nutritional content, but their perishability and seasonality present challenges for storage and marketing. To address these, it is essential to accurately monitor their quality and predict shelf life. Unlike traditional methods, machine learning efficiently handles large datasets, identifies complex patterns, and builds predictive models to estimate food shelf life. These models can be continuously refined with new data, improving accuracy and robustness over time. This article discusses key machine learning methods for predicting shelf life and quality control of fruits and vegetables, with a focus on storage conditions, physicochemical properties, and non-destructive testing. It emphasizes advances such as dataset expansion, model optimization, multi-model fusion, and integration of deep learning and non-destructive testing. These developments aim to reduce resource waste, provide theoretical basis and technical guidance for the formation of modern intelligent agricultural supply chains, promote sustainable green development of the food industry, and foster interdisciplinary integration in the field of artificial intelligence.

Development of machine learning-based shelf-life prediction models for multiple marine fish species and construction of a real-time prediction platform

At least 10 million tons of seafood products are spoiled or damaged during transportation or storage every year worldwide. Monitoring the freshness of seafood in real time has become especially important. In this study, four machine learning algorithms were used for the first time to develop a multi-objective model that can simultaneously predict the shelf-life of five marine fish species at multiple storage temperatures using 14 features such as species, temperature, total viable count, K-value, total volatile basic‑nitrogen, sensory and E-nose-GC-Ms/Ms. as inputs. Among them, the radial basis function model performed the best, and the absolute errors of all test samples were <0.5. With the optimal model as the base layer, a real-time prediction platform was developed to meet the needs of practical applications. This study successfully realized multi-objective real-time prediction with accurate prediction results, providing scientific basis and technical support for food safety and quality.

Analysis of the lipidomic profile of vegetable oils and animal fats and changes during aging by UPLC-Q-exactive orbitrap mass spectrometry

Vegetable oil and animal fat residues are common evidence in the cases of homicide, arson, theft, and other crimes. However, the lipid composition and content changes during aging on complex carriers remain unclear. Therefore, this study dynamically monitored the lipid composition and content changes during aging of 13 different types of vegetable oils and animal fats on five different carriers using the UPLC-Q-Exactive Orbitrap MS method. A total of 6 subclasses of 93 lipids including lysophosphatidylcholine (2 species), phosphatidylcholine (2 species), diglyceride (5 species), triglyceride (81 species), acylGlcCampesterol ester (2 species), and acylGlcSitosterol ester (1 species), were first identified in fresh vegetable oils and animal fats. By comparing the LC-MS/MS chromatograms of fresh vegetable oils and animal fats, it was found that there were significant differences between the chromatograms of vegetable oils and animal fats, but it was difficult to distinguish between the chromatograms of vegetable oils or animal fats. After aging at 60 °C for 200 days, there was a significant decrease in the content of diglyceride, triglyceride, acylGlcCampesterol ester, and acylGlcSitosterol ester, while the content of lysophosphatidylcholine and phosphatidylcholine initially increased and then decreased. Furthermore, statistical analysis of lipid differences between vegetable oils and animal fats was performed using cluster heat maps, volcanic maps, PCA, and OPLS-DA. On average, 33 significantly different lipids were screened (VIP > 1, p < 0.05), which could serve as potential biomarkers for distinguishing vegetable oils and animal fats. It was found that the potential biomarkers still existed during aging of vegetable oils and animal fats (100 and 200 days). This research provides important reference information for the identification of vegetable oil and animal fat residues in complex carriers at crime scenes.

Colorimetric indicator films based on carboxymethyl cellulose and anthocyanins as a visual indicator for shrimp freshness tracking

This study aimed to evaluate the response efficiency of colorimetric indicator films based on carboxymethyl cellulose (CMC) incorporated with different anthocyanins [Karanda alone (CMC/AK), butterfly pea alone (CMC/AB), and a mixture of anthocyanins from Karanda and butterfly pea (CMC/AK75/AB25)] for tracking shrimp freshness during storage at different temperatures and times (4 °C for 8 days and 25 °C for 30 h). The mathematical models were also applied to predict their freshness and shelf life. The CMC/AK75/AB25 indicator film was the most sensitive and clearly changed color, which could be distinguished by the naked eye. Color changes indicated the shrimp deterioration processes: dark purple (fresh), purplish gray or gray (semi-fresh), and olive green or brown (spoilage). During shrimp storage at temperatures of 4 and 25 °C, the pH reached 7.52 and 8.14, TVB-N 35.98 and 72.72 mg/100 g, and TVC 5.75 and 7.88 log CFU/g, respectively, indicating shrimp had completely deteriorated. Furthermore, there was a positive correlation between the ΔE value of the indicator film and both TVB-N and TVC. These findings suggest that the CMC/AK75/AB25 indicator film could serve as a real-time visual indicator for tracking shrimp freshness and could enhance the guarantee of shrimp safety.

Innovative eco-friendly hydroxyethylcellulose matrix-based composite for enhanced gas separation: Insights from performance and structural characterization

With increasing concern for the environment, the demand for carbon dioxide separation, a key contributor to global warming, has escalated. Therefore, this paper focuses on carbon dioxide separation by creating an hydroxyethyl cellulose (HEC)(C2H6O2)x*(C6H7O2(OH)3)n/silver tetra fluoroborate (AgBF4)/aluminum nitrate (Al(NO3)3) composite film, demonstrating excellent separation performance with a permeance of 1.0 GPU and a selectivity of 100. Silver ions enhance the solubility of carbon dioxide, aiding in its separation, and we determined the optimal aluminum composition to stabilize the silver ions. To analyze this, we examined the cross-sections using SEM, confirming a selective layer of 1.7 μm for carbon dioxide separation. Furthermore, TGA, FT-IR, and NMR analyses were conducted to investigate the interaction between the polymer and additives. This revealed that the increased polymer chain due to the interaction between Ag and HEC, along with stabilized Ag facilitated by the addition of Al, maximized the interaction with carbon dioxide via the empty s-orbital. Additionally, SEM-EDX, UV-vis, XRD, XPS analyses were employed to elucidate the movement of ions within the membrane. These results provide insights into the performance of membranes based on cellulose polymer and offer valuable insights for future applications in gas separation technologies.

Aldehyde group pendant-grafted pectin-based injectable hydrogel

Periodate oxidation has been the widely accepted route for obtaining aldehyde group-functionalized polysaccharides but significantly influenced the various physicochemical properties due to the ring opening of the backbone of polysaccharides. The present study, for the first time, presents a novel method for the preparation of aldehyde group-functionalized polysaccharides that could retain the ring structure and the consequent rigidity of the backbone. Pectin was collected as the representative of polysaccharides and modified with cyclopropyl formaldehyde to obtain pectin aldehyde (AP), which was further crosslinked by DL-lysine (LYS) via the Schiff base reaction to prepare injectable hydrogel. The feasibility of the functionalization was proved by FT-IR and 1H NMR techniques. The obtained hydrogel showed acceptable mechanical properties, self-healing ability, syringeability, and sustained-release performance. Also, as-prepared injectable hydrogel presented great biocompatibility with a cell proliferation rate of 96 %, and the drug-loaded hydrogel exhibited clear inhibition of cancer cell proliferation. Overall, the present study showed a new method for the preparation of aldehyde group-functionalized polysaccharides, and the drug-loaded hydrogel has potential in drug release applications.