Application of Bayesian modelling to assess food quality & safety status and identify risky food in China market

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.

Examination of the relationship between agricultural carbon emission efficiency and food quality and safety: from the perspective of environmental regulation

An important breakthrough in the coordinated development of China's low-carbon goals and food security strategies is agricultural development oriented toward quality, safety, green, and low carbon. This study integrated command-control and market-incentive environmental regulation (ER), agricultural eco-efficiency (ACEE), and food quality and safety (FQS) into a unified theoretical framework. The unexpected output-oriented Super-SBM model was used to calculate the ACEE of China's provinces and cities from 2011 to 2020 and test the bidirectional causality between ACEE and FQS through the system generalized moment estimation model. A dynamic panel smooth transition (PSTR) model was used to explore the nonlinear impact mechanisms of different types of ERs on ACEE and FQS. The results showed that there was a long-term, two-way causal relationship between ACEE and FQS. The impact of environmental regulations on ACEE and FQS has a nonlinear relationship. Among them, the role of market-incentivized ER is more significant. Therefore, building an interregional coordinated development mechanism, improving the utilization rate of agricultural resources such as fertilizers and pesticides, and coordinating the positive effects of different types of ERs are the keys to improving the ACEE and ensuring the coordinated development of FQS.

Novel risk assessment model of food quality and safety considering physical-chemical and pollutant indexes based on coefficient of variance integrating entropy weight

Food safety is important for sustainable social and economic development and people's health. The traditional single risk assessment model is one-sided to the weight distribution of food safety factors including physical-chemical and pollutant indexes, which cannot comprehensively assess food safety risks. Therefore, a novel food safety risk assessment model combining the coefficient of variation (CV) integrating the entropy weight (EWM) (CV-EWM) is proposed in this paper. The CV and the EWM are used to calculate the objective weight of each index with physical-chemical and pollutant indexes effecting food safety, respectively. Then, the weights determined by the EWM and the CV are coupled by the Lagrange multiplier method. The ratio of the square root of the product of two weights and the weighted sum of the square root of the product are regarded as the combined weight. Thus, the CV-EWM risk assessment model is constructed to comprehensively assess the food safety risk. Moreover, the Spearman rank correlation coefficient method is used to test the compatibility of the risk assessment model. Finally, the proposed risk assessment model is applied to evaluate the quality and safety risk of sterilized milk. By analyzing the attribute weight and comprehensive risk value of physical-chemical and pollutant indexes effecting the sterilized milk quality, the results show that this proposed model can scientifically obtain the weight of physical-chemical and pollutant indexes to objectively and reasonably evaluate the overall risk of food, which has certain practical value for discovering the influencing factors of risk occurrence to risk prevention and control of food quality and safety.

CSGNN: Contamination Warning and Control of Food Quality via Contrastive Self-Supervised Learning-Based Graph Neural Network

Effective contamination warning and control of food quality can significantly reduce the likelihood of food quality safety incidents. Existing food contamination warning models for food quality rely on supervised learning, do not model the complex feature associations between detection samples, and do not consider the unevenness of detection data categories. In this paper, To overcome these limitations, we propose a Contrastive Self-supervised learning-based Graph Neural Network framework (CSGNN) for contamination warning of food quality. Specifically, we structure the graph for detecting correlations between samples and then define the positive and negative instance pairs for contrastive learning based on attribute networks. Further, we use a self-supervised approach to capture the complex relationships between detection samples. Finally, we assessed each sample's contamination level based on the absolute value of the subtraction of the prediction scores from multiple rounds of positive and negative instances obtained by the CSGNN. Moreover, we conducted a sample study on a batch of dairy product detection data in a Chinese province. The experimental results show that CSGNN outperforms other baseline models in contamination assessment of food quality, with AUC and recall of unqualified samples reaching 0.9188 and 1.0000, respectively. Meanwhile, our framework provides interpretable contamination classification for food detection. This study provides an efficient early warning method with precise and hierarchical contamination classification for contamination warning of food quality work.

A Bayesian Approach to Predict Food Fraud Type and Point of Adulteration

Primary and secondary food processing had been identified as areas vulnerable to fraud. Besides the food processing area, other stages within the food supply chain are also vulnerable to fraud. This study aims to develop a Bayesian network (BN) model to predict food fraud type and point of adulteration i.e., the occurrence of fraudulent activity. The BN model was developed using GeNie Modeler (BayesFusion, LLC) based on 715 notifications (1979-2018) from Food Adulteration Incidents Registry (FAIR) database. Types of food fraud were linked to six explanatory variables such as food categories, year, adulterants (chemicals, ingredients, non-food, microbiological, physical, and others), reporting country, point of adulteration, and point of detection. The BN model was validated using 80 notifications from 2019 to determine the predictive accuracy of food fraud type and point of adulteration. Mislabelling (20.7%), artificial enhancement (17.2%), and substitution (16.4%) were the most commonly reported types of fraud. Beverages (21.4%), dairy (14.3%), and meat (14.0%) received the highest fraud notifications. Adulterants such as chemicals (21.7%) (e.g., formaldehyde, methanol, bleaching agent) and cheaper, expired or rotten ingredients (13.7%) were often used to adulterate food. Manufacturing (63.9%) was identified as the main point of adulteration followed by the retailer (13.4%) and distribution (9.9%).

A review of Canadian and international food safety systems: Issues and recommendations for the future

In January 2019, the Safe Food for Canadians Act/Safe Food for Canadians regulations (heretofore identified as SFCR) came into force across Canada and brought a more streamlined process to food safety practice in Canada. Food trade and production processes have evolved rapidly in recent decades, as Canada imports and exports food products; therefore it is critically important to remain aware of the latest advances responding to a range of challenges and opportunities in the food safety value chain. Looking through the optics of the recent SFCR framework, this paper places the spotlight on leading domestic and international research and practices to help strengthen food safety policies of the future. By shedding some light on new research, we also draw attention to international developments that are noteworthy, and place those in context as to how new Canadian food safety policy and regulation can be further advanced. The paper will benchmark Canada through a review study of food safety best practices by juxtaposing (i) stated aspirations with, (ii) actual performance in leading Organization for Economic Cooperation and Development (OECD) jurisdictions.

Differential game evolution of food quality safety based on market supply and demand

Frequent outbreaks of food quality and safety problems have seriously damaged the interests of consumers and reduced their confidence in China's food safety. In this study based on market supply and demand, we design a differential game model between food supplier and food retailer by considering different decision-making situations. We also analyze the optimal revenue of the food supplier and food retailer on food quality efforts, the overall return of the supply chain, the level of food quality and safety, and their evolutionary characteristics. Results of the analysis indicate the following. (a) From the situation of decentralized decision-making to the situation of decision-making under the incentive strategy, a Pareto improvement occurs in the food quality and safety strategy of food supplier, food retailer, and even the entire food supply chain. (b) The optimal revenues of the supplier and retailer, overall supply chain revenue, and efforts of the supplier and retailer are all affected by changes in market supply and demand, resulting in drastic fluctuations. On the whole, food quality tends to improve over time and will fluctuate slightly due to changes in market supply and demand. (c) If the market supply is stable when supply exceeds demand and the market demand turns from a downward trend to an upward trend, then food quality safety risk will be higher than in other periods.

Ranking Factors of Infant Formula Milk Powder Using Improved Entropy Weight Based on HDT Method and Its Application of Food Safety

Food safety is about everyone’s health. Through risk assessment and early warning of food safety, food-related safety issues can be identified as early as possible and take timely precautions. However, the detection data of food safety are complex and non-linear, so it is necessary to find the relationship and hierarchical representation of factors affecting food safety. This paper presents an improved entropy weight based on Hasse diagram technology (HDT) method to analyze the influencing factors of food safety. The entropy weight method was used to calculate the weight of each factor index, and the relationship matrix was obtained. Then, the data of infant milk powder in China were analyzed hierarchically by the HDT method. Thus, we can obtain the multi-level structure that affects food safety. It provides an effective basis for early warning of food safety, can help government regulators to strengthen management, and urge enterprises to produce food safely.

Synthesis of fluorescent pink emitting copper nanoparticles and sensitive detection of α-naphthaleneacetic acid

Detecting NAA in food has drawn intense attention as it has imposed significant threat to people's health and the growth of food industry. Over the past few years, great importance has been attached to the application of copper nanomaterials as fluorescent probe to food and environmental detection. Here, the simple, rapid, cost effective and water soluble fluorescent copper nanoparticles were synthesized with chemical reduction sonochemical assisted method for highly selective and sensitive detection of α-naphthaleneacetic acid (NAA) by using 2-mercaptobenzothiazole (MBT) as a protecting agent and polyvinylpyrrolidone (PVP) as a stabilizing agent (MBT-PVP CuNPs). The resultant CuNPs has a spherical shape with an average diameter of 10-15 nm and strong fluorescent pink emission characteristic peak at 580 nm upon 334 nm excitation. Interestingly, upon the addition of NAA, the fluorescence of MBT-PVP CuNPs can be effectively quenched for the reason that NAA could interact with MBT via hydrogen bonding and conform copper-NAA clathrate with Cu⁺ via coordination bond, which shows a good linearity in the range of NAA from 0.5 to 50 μM and with a detection limit of 9.6 nM. Moreover, the prepared probe has good selectivity for NAA detection over other co-existing molecules. It is worth mentioning that this method has been successfully applied to authentic comestible sample analysis and obtained satisfying and promising results, which indicates that this strategy is likely to have a promising application potential for NAA detection in the field of food safety.

Association of Internet Use with Attitudes Toward Food Safety in China: A Cross-Sectional Study

A growing body of research has shown that people’s attitudes toward food safety is affected by their availability and accessibility to food risk information. In the digital era, the Internet has become the most important channel for information acquisition. However, empirical evidence related to the impact of Internet use on people’s attitudes towards food safety is inadequate. In this study, by employing the Chinese Social Survey for 2013 and 2015, we have investigated the current situation of food safety perceptions and evaluations among Chinese residents and the association between Internet use and individuals’ food safety evaluations. Empirical results indicate that there is a significant negative correlation between Internet use and people’s food safety evaluation in China. Furthermore, heterogeneity analysis shows that Internet use has a stronger negative correlation with food safety evaluation for those lacking rational judgment regarding Internet information. Specifically, the negative correlation between Internet use and food safety evaluations is more obvious among rural residents, young people, and less educated residents. Finally, propensity score matching (PSM) is applied to conduct a robustness check. This paper provides new evidence for studies on the relationship between Internet use and an individuals’ food safety cognition, as well as additional policy enlightenment for food safety risk management in the digital age.