A radio frequency identification and sensor-based system for the transportation of food

The damage caused by the degeneration of the quality of perishable products usually results in a great loss to transportation enterprises. To improve the delivery system for perishable products, a real-time monitoring and online decision support system with Radio frequency identification (RFID), a sensor network and a decision rule base has been developed in this study. First of all, the value degeneration process is described, using several mathematical models for handing different ways of perishing. Based on the mathematical models, and data from RFID and the sensor network, the quality of the goods can be predicted by the forecast module. When something abnormal occurs, the warning function will send an alarm signal to the users, then, the rule-based decision module will provide the user with suggestions as how to cope with the abnormality. The results from the simulation have shown that the monitoring and decision support system is an efficient tool for reducing the transportation losses of perishable products for the enterprises in cold chain.     

基于物联网的冷链食品安全监控系统的设计与实施

为实现冷链食品的安全管理与预警,设计了基于物联网技术的冷链食品安全监控系统.该系统通过传感器、射频识别、全球定位系统等物联网技术,实现冷链食品信息的自动采集、传输和处理,从而实现冷链食品的安全监控及预警管理.鉴于该系统的推广还面临许多问题,应加快物联网标准体系建设,加快RFID及传感器等关键技术的开发研究,形成具有自主知识产权的物联网技术核心,高度重视物联网发展带来的安全问题,积极引导行业示范应用,以推动基于物联网技术的食品安全监控系统的快速发展.     

Application of RFID technologies in the temperature mapping of the pineapple supply chain

Current temperature tracking systems lack the convenience and accuracy demanded by the real conditions of a fast-paced produce supply chain. In recent years RFID technology has been suggested to be an enhanced method for temperature tracking because of its many benefits, such as using little instrumentation, offering the quick readings necessary for real-time decision making, and allowing the capture of long-duration temperature profiles. However its limitation lies in that probeless systems fail to provide accurate temperature readings in some of the critical points of the pallet and the load. The objective of this work was to study the use of RFID in temperature monitoring by comparing the performance of RFID temperature tags versus conventional temperature tracking methods, as well as RFID temperature tags with probe versus RFID temperature tags without probes and their utilization along the supply chain. Therefore, the temperature mapping of a shipping trial comprising pallets of crownless pineapples instrumented using different RFID temperature dataloggers and traditional temperature dataloggers and packed in two kinds of packages (corrugated boxes and reusable plastic containers) inside a container was performed. The results showed that RFID temperature tags are analogous with regards to accuracy to the conventional methods, but have a superior performance because they allow quick instrumentation and data recovery, and the possibility of accessing the sensor program and data at any point of the supply chain without line of sight. In addition, the use of RFID tags with probe was justified by its role in determining the efficiency of the pre-cooling operations and low temperature abuse tracking during transportation and refrigerated storage; while the RFID tags without probe proved useful for high temperature abuse monitoring during transportation and refrigerated storage. The creation of a RFID sensor with a probe, able to record both ambient and pulp temperatures simultaneously is suggested. Presented at Food Processing Automation Conference, American Society of Agricultural and Biological Engineering (ASABE), Providence, RI, USA, June 28–29 2008.     

Is Food Safety Compatible with Food Waste Prevention and Sustainability of the Food Chain?

In a context where the sustainability of food chains and food waste prevention are subjects of interest for public authorities and professionals, it is important to assess if these new objectives of food policy are compatible with food safety. The objective of this work was to develop a global model for a ready-to-eat meat product that provides three different outputs, i.e. energy consumption, percentage of spoiled products and exposure levels of Listeria monocytogenes. First a cold chain model was developed. The cold chain model was then coupled with (i) predictive microbiology models and (ii) energy consumption models for cold equipments. Various scenarios were tested for assessing the consequences of potential changes in cold chain equipment on safety, food waste and energy cost. This global approach could help policy makers in decision making.     

基于HACCP的海产品供应链冷链物流 质量安全控制

目的针对海产品供应链冷链物流质量安全控制难点,应用HACCP体系,以鱼贝类海产品为例,制定HACCP危害分析表和实施计划表。方法从养殖及捕捞、清洗整理、海产品冷却、冷冻储存及运输、加工、搬运和装卸等各个环节进行全过程控制。从生物性污染、化学性污染和物理性污染3个方面确定出鱼贝类供应链冷链物流中的关键控制点和关键限值,主要监控致病菌、重金属、化学药物残留等因素。结果从监控对象、方法、频率、人员方面建立具体监控措施、纠偏措施及验证方法,并制定鱼贝类海产品较详细的危害分析表和实施计划表。结论本研究为其他水产品的供应链冷链物流HACCP质量控制体系的建立提供案例,确保海产品冷链物流中的质量安全,为阳江市海产品企业在冷链物流中的质量安全体系控制提供参考。     

基于RGB-D弹性可形变物体跟踪识别控制披萨厨师机器人方法研究

以披萨厨师机器人为研究对象,提出了一种基于RGB-D传感器所提供的实时点云数据对弹性形变的3D无纹理对象进行跟踪的方法。着重分析了视觉分割的时间一致性和实时性问题;通过有限元分析的方法建立了带有轮廓加权的同向旋转FEM模型;论述了注册点云数据方法,提出了跟踪合成数据与披萨面坯实际图像的算法,采用模拟开放框架架构模拟器,验证了算法的有效性。     

A data-driven prediction of lifetime resilience of dairy cows using commercial sensor data collected during first lactation

Reliable prediction of lifetime resilience early in life can contribute to improved management decisions of dairy farmers. Several studies have shown that time series sensor data can be used to predict lifetime resilience rankings. However, such predictions generally require the translation of sensor data into biologically meaningful sensor features, which involve proper feature definitions and a lot of preprocessing. The objective of this study was to investigate the hypothesis that data-driven random forest algorithms can equal or improve the prediction of lifetime resilience scores compared with ordinal logistic regression, and that these algorithms require considerably less effort for data preprocessing. We studied this by developing prediction models that forecast lifetime resilience of a cow early in her productive life using sensor data from the first lactation. We used an existing data set from a Dutch experimental herd, with data of culled cows for which birth dates, insemination dates, calving dates, culling dates, and health treatments were available to calculate lifetime resilience scores. Moreover, 4 types of first-lactation sensor data, converted to daily aggregated values, were available: milk yield, body weight, activity, and rumination. For each sensor, 14 sensor features were calculated, of which part were based on absolute daily values and part on relative to herd average values. First, we predicted lifetime resilience rank with stepwise logistic regression using sensor features as predictors and a P-value of <0.2 as the cut-off. Next, we applied a random forest with the 6 features that remained in the final logistic regression model. We then applied a random forest with all sensor features, and finally applied a random forest with daily aggregated values as features. All models were validated with stratified 10-fold cross-validation with 90% of the records in the training set and 10% in the validation set. Model performances expressed in percentage of correctly classified cows (accuracy) and percentage of cows being critically misclassified (i.e., high as low and vice versa) ± standard deviation were 45.1 ± 8.1% and 10.8% with the ordinal logistic regression model, 45.7 ± 8.4% and 16.0% with the random forest using the same 6 features as the logistic regression model, 48.4 ± 6.7% and 10.0% for the random forest with all sensor features, and 50.5 ± 6.3% and 8.4% for the random forest with daily sensor values. This random forest also revealed that data collected in early and late stages of first lactation seem to be of particular importance in the prediction compared with that in mid lactation. Accuracies of the models were not significantly different, but the percentage of critically misclassified cows was significantly higher for the second model than for the other models. We concluded that a data-driven random forest algorithm with daily aggregated sensor data as input can be used for the prediction of lifetime resilience classification with an overall accuracy of ~50%, and provides at least as good prediction as models with sensor features as input.     

An RFID application in the food supply chain: A case study of convenience stores in Taiwan

Food hazards can appear at any stage of global food supply chains, making it essential to define critical control points to capture the data about ingredients, manufacture and dates-certain (sell-by, use-by), etc., and provide it in a transparent manner to supply chain participants and consumers. The government of Taiwan has appointed a non-profit research organization to conduct a pilot project to launch a potential national-wide food traceability system to increase the intangible value of purchased food and to enhance food safety. This paper discusses a financially viable business model for a Radio Frequency Identification (RFID) application to a food traceability system. We conduct a case study of RFID implementation in the chain of convenience stores in Taiwan. The Taiwanese experiment may have implications for policy-makers, industry and public health officials elsewhere.     

基于CFD的建模技术在食品冷链物流中的应用

随着消费者对食品新鲜度的不懈追求以及对食品安全问题的日益重视,新的保鲜技术逐渐被发掘,其中食品冷链物流是食品保鲜保质的一个非常重要的环节。本文分析了建模技术在冷链物流过程中的独特优势,并对确定性模型在食品冷链物流的储藏、运输、陈列销售和售后终端贮藏四个环节运用,尤其是计算流体动力学(CFD)的广泛和成功应用;阐述了确定性模型的简化模型、随机性模型的建立在食品冷链物流中的应用进展并进行了深入分析;最后针对今后我国冷链物流的主要研究问题做出总结,以及对于后期建模技术的研究任务提出具体建议,为实现我国冷链物流行业的快速发展以及保障生鲜食品安全提供参考方法和理论指导。     

Quantitative evaluation and prediction for preservation quality of cold shocked cucumber based on entropy

To evaluate and predict preservation quality of cold shocked cucumber and study the effects of cold shock parameters on the preservation quality, several entropy-based models were proposed. Cucumbers were cold shocked at different temperatures (0, 3, 6 °C) for different durations (20, 40, 60 min), and their preservation quality was evaluated by the proposed models. Results show that, the evaluation model can objectively evaluate preservation quality of cold shocked cucumber, and cold shocked at 3 °C for 40 min gets optimal preservation effect. Cold shock treatments at 0 °C and 3 °C improve preservation quality of cucumber effectively, while that at 6 °C fails. Therefore, entropy change caused by cold shock treatment should be higher than a certain critical value to improve preservation quality of cucumber effectively, and the duration is crucial for preservation quality when meeting this condition. The composite entropy change (S*) shows effect of both temperature and duration and characterizes cold shock intensity, and proposed prediction model of cold shock preservation quality can predict preservation quality of cucumber cold shocked at different temperatures and durations well.Industrial relevanceFresh fruits and vegetables contain rich essential substances to our bodies and play an active role in improving people's health. Since it has obvious seasonal regional characteristics on the fruits and vegetables production, pretreatment is very important for prolonging their storage periods. Cold shock treatment for many fruits and vegetables indicate that this method can effectively improve their preservation quality and have broad application space.This study lies in providing a series of methods based on entropy to characterize the cold shock intensity to fruits and vegetables, carrying out objective quantitative evaluation and prediction for preservation quality of the cold shock treatment, and based on which, the influence mechanism of cold shock intensity (temperature and duration) on preservation quality of fruits and vegetables was analyzed. The results will contribute to better design and optimization of the cold shock process for postharvest fruits storage.     

SCALE TRANSLATIONS OF FIRMNESS TESTS ON FRUITS

In many fruits and vegetables, it is desired to replace destructive firmness measurement methods by nondestructive ones. The inevitable question is to what degree do two firmness measurement methods agree? The present article proposes a new approach for method comparison in firmness tests of fruits, by optimal translation of the readings taken on the scale of one test, to the scale of another test and vice versa. The proposed scale translation mode is based on minimizing the sum of squares of the differences between the absolute values of the Fast Fourier Transform (FFT) series, derived from the readings of the compared measurement methods. The line taken is illustrated by a comparative study on a large sample of Red Delicious apples, assessing the performance of a nondestructive fruit firmness sensor versus the conventional destructive test which measures the applied piercing force on the fruit by a penetrometer.     

Machine learning to quantify techno-functional properties - A case study for gel stiffness with pea ingredients

Mildly refined ingredients are included more easily in food products when selected based on techno-functional properties instead of composition. We assess different machine learning methods that quantitatively link relevant techno-functional properties to the composition and processing history of the ingredient in a case study using the gel stiffness (Young's modulus) by conventionally and mildly refined ingredients of yellow pea. Linear (multiple, log transformed and polynomial) and non-linear models (spline regression, decision trees, and neural networks) were explored. The final model selection was based on 1) the statistical model metrics (RMSE, R², and MAE) of the training and independent test set and 2) expert knowledge to evaluate the plausibility of the model predictions. In this case, neural networks can describe the gel stiffness of yellow pea ingredients most accurately. The approach that we follow can be applied to other techno-functional properties to improve the chain sustainability while ensuring the full functionality of the products.     

Searching for new mathematical growth model approaches for Listeria monocytogenes

ABSTRACT:  Different secondary modeling approaches for the estimation of Listeria monocytogenes growth rate as a function of temperature (4 to 30 °C), citric acid (0% to 0.4% w/v), and ascorbic acid (0% to 0.4% w/v) are presented. Response surface (RS) and square-root (SR) models are proposed together with different artificial neural networks (ANN) based on product functions units (PU), sigmoidal functions units (SU), and a novel approach based on the use of hybrid functions units (PSU), which results from a combination of PU and SU. In this study, a significantly better goodness-of-fit was obtained in the case of the ANN models presented, reflected by the lower SEP values obtained (< 24.23 for both training and generalization datasets). Among these models, the SU model provided the best generalization capacity, displaying lower RMSE and SEP values, with fewer parameters compared to the PU and PSU models. The bias factor (B_f) and accuracy factor (A_f) of the mathematical validation dataset were above 1 in all cases, providing fail-safe predictions. The balance between generalization properties and the ease of use is the main consideration when applying secondary modeling approaches to achieve accurate predictions about the behavior of microorganisms.     

On the design of optimal dynamic experiments for parameter estimation of a Ratkowsky-type growth kinetics at suboptimal temperatures

It is generally known that accurate model building, i.e., proper model structure selection and reliable parameter estimation, constitutes an essential matter in the field of predictive microbiology, in particular, when integrating these predictive models in food safety systems. In this context, Versyck et al. (1999) have introduced the methodology of optimal experimental design techniques for parameter estimation within the field. Optimal experimental design focuses on the development of optimal input profiles such that the resulting rich (i.e., highly informative) experimental data enable unique model parameter estimation. As a case study, Versyck et al. (1999) [Versyck, K., Bernaerts, K., Geeraerd, A.H., Van Impe, J.F., 1999. Introducing optimal experimental design in predictive modeling: a motivating example. Int. J. Food Microbiol., 51(1), 39-51] have elaborated the estimation of Bigelow inactivation kinetics parameters (in a numerical way). Opposed to the classic (static) experimental approach in predictive modelling, an optimal dynamic experimental setup is presented. In this paper, the methodology of optimal experimental design or parameter estimation is applied to obtain uncorrelated estimates of the square root model parameters [Ratkowsky, D.A., Olley, J., McMeekin, T.A., Ball, A., 1982. Relationship between temperature and growth rate of bacterial cultures. J. Bacteriol. 149, 1-5] describing the effect of suboptimal growth temperatures on the maximum specific growth rate of microorganisms. These estimates are the direct result of fitting a primary growth model to cell density measurements as a function of time. Apart from the design of an optimal time-varying temperature profile based on a sensitivity study of the model output, an important contribution of this publication is a first experimental validation of this innovative dynamic experimental approach for uncorrelated parameter identification. An optimal step temperature profile, within the range of model validity and practical feasibility, is developed for Escherichia coli K12 and successfully applied in practice. The presented experimental validation result illustrates the large potential of the dynamic experimental approach in the context of uncorrelated parameter estimation. Based on the experimental validation result, additional remarks are formulated related to future research in the field of optimal experimental design.     

Moving from a compliance‐based to an integrity‐based organizational climate in the food supply chain

Compliance is the act or status of complying with an imperative regulatory or normative requirement, that is, compliance means working within boundaries defined by contractual, social, or cultural standards. The aim of this narrative review is to use the food supply chain as a lens of enquiry to distinguish between compliance‐based and integrity‐based organizational climates and frame and rationalize why deviant behavior arises and how it can be identified. Contemporary theory is explored and critiqued using case studies to contextualize the challenge of organizations promoting supply chain compliance and at the same time recognizing the need for deviant behavior to occur in order to drive innovation and continuous improvement within food supply chains. Deviant behavior can be perceived as either positive in terms of driving continuous improvement or destructive where this behavior has a negative impact on the organization. Although multiple cultural maturity models seek to characterize positive food safety culture and climate, there is minimal research that focuses on the characterization of deviant negative behavior or the development of early warning systems designed to pinpoint signals, traits, or characteristics of this behavior such as low staff morale, theft, property destruction, or absenteeism. The use of cultural maturity models and assessment tools is of value in assisting organizations to translate from a rule, instrumental, or compliance‐based organizational climate to an ethically strong organizational climate that focuses on integrity, building trust, and values and a new cultural maturity model is proposed and explored.     

Mathematical models for the trimethylamine (TMA) formation on packed cod fish fillets at different temperatures

The microbial formation of trimethylamine (TMA) can be used as a quality indicator compound to predict the freshness of fish during its shelf life. In a supply chain with fluctuating temperatures, mathematical models will be valuable tools to simulate this formation as a function of temperature and time. These models are essential to link sensor data on the formation of TMA to the actual freshness of fish. Existing models for the formation of TMA in fish needed improvements and secondary models for the effect of temperature on the formation of TMA are lacking in the literature. Three different approaches were evaluated on their ability to simulate the experimental observed TMA formation at 4 different temperatures (0, 5, 10 and 15 °C). In the first approach the existing models were improved and the temperature effect was modelled by an empirical model using four parameters. This model is able to simulate the TMA formation at static temperatures. Since TMA is produced on fresh cod fillets by the micro-organisms Shewanella putrefaciens and Photobacterium phosphoreum the microbial Baranyi–Roberts model was initially used for modelling the TMA formation, but this model was found to be too complex (too many correlated parameters that could not be estimated). In the third approach it was seen that a simplified Baranyi–Roberts model with only three parameters could be used to predict the TMA formation with equal accuracy. The influence of the temperature on the parameter μ_max was modelled using the extended square root model of Ratkowsky and the differences in TMA formation profiles of different batches could be described by the batch specific parameter N₀ representing the initial quality. The presented dynamic model is valuable in predicting the formation of TMA in a fresh fish supply chain with dynamic temperatures. This model has the potential to be used to link sensor data of TMA in the headspace to the actual freshness status of the fish.     

Modelling: one word for many activities and uses

Modelling in food microbiology relies on the development and use of mathematical equations to describe biological processes. These models can be used to perform various tasks from quantitatively describing a phenomenon, testing significant kinetic differences, quantitatively investigate mechanisms and correlations, designing experiments and sampling plans, or predicting phenomena within a food chain to enable optimal control. It is important to clearly identify what one wants to realize, and depending on the purpose of the model, select the most appropriate approach for modelling. In this paper various applications are illustrated and for each application an example is given to highlight the broad use of models and model results in food microbiology.     

Bruise detection on red bayberry (Myrica rubra Sieb. & Zucc.) using fractal analysis and support vector machine

A new method to sort red bayberries based on the presence of bruises was proposed. Principal component-support vector machine (PC-SVM) and support vector machine (SVM) models combined with fractal analysis were developed and compared with classification models based on RGB intensity values. The results of this study show the classification models based on fractal parameters achieved 100% total accuracy rate, but the models based on RGB values was only 85.29%. In addition, the performance of the SVM model in terms of iteration time and the number of support vectors was better than the PC-SVM model. Therefore, the SVM model based on fractal analysis is recommended for detecting bruises on red bayberries.     

Risk assessment strategies as a tool in the application of the Appropriate Level of Protection (ALOP) and Food Safety Objective (FSO) by risk managers

In the course of the last decade, the Appropriate Level of Protection (ALOP), the Food Safety Objective (FSO) and their associated metrics have been proposed by the World Trade Organization and Codex Alimentarius as a means for competent authorities to ultimately translate governmental public health policy regarding food safety into risk-based targets for the food industry. The industry needs to meet these targets through the effective choice of control measures that are part of its operational food safety management system. The aim of this study was to put the practical application of ALOP and FSO to the test in the case of Salmonella in chicken meat in the Netherlands. Two different risk assessment approaches were applied to derive potential ALOP and FSO values, a ‘top-down’ approach based on epidemiological data and a ‘bottom-up’ approach based on food supply chain data. To this end, two stochastic models specific to the Dutch situation were built. Comparisons between 23 countries in Europe were also made using the top-down model. The mean estimated current Level Of Protection values were similar for the two approaches applied, with the bottom-up model yielding 87 cases per 100,000 inhabitants per year (95% CI: 0.03, 904) and the top-down model 71 (95% CI: 9.9, 155). The estimated FSO values on the other hand were considerably different with the mean ‘top down’ FSO being − 4.6 log CFU/g (95% CI: − 5.4, − 4.1) and the mean ‘bottom-up’ FSO − 6.0 log CFU/g (95% CI: − 8.1, − 2.9) reflecting major differences in the output distributions of this parameter obtained with the two approaches. Significant differences were observed between current LOP values for different EU countries, although it was not clear whether this was due to actual differences in the factors influencing the risk of salmonellosis or due to the quality of the available data.     

Microbiological predictive modeling and risk analysis based on the one-step kinetic integrated Wiener process

The actual growth-monitoring data of microbial hazards in food are characterized by uncertainty, accumulation, discreteness, and nonlinearity, and thus it is difficult to accurately predict and analyze food safety microbiological risks in real time. Hence, we propose an approach of microbiological predictive modeling and risk analysis based on the one-step kinetic integrated Wiener process (OS-WP). First, the microbial tertiary prediction model was directly constructed through one-step kinetic analysis. Then, the WP was integrated with a tertiary model for predictive modeling of the actual microbial stochastic growth. Second, an indicator, “remaining safety life” (RSL), was introduced to analyze the potential microbiological risk on the basis of the established prediction models. Finally, the maximum likelihood estimation was used obtaining the model parameters online, and for calculating the RSL value in real time. The OS-WP approach was applied to a case study of the mixed mildew hazard during wheat storage. For different datasets, the root mean square error (RMSE) of the microbiological predictive model was less than 1.5; the relative RMSE of the RSL prediction reached 6.77%; the running time was less than 0.6 s. The result showed that the proposed approach is effective and feasible in modeling the actual growth of microbial hazards in food and can achieve online risk analysis. It can provide valuable microbiological early warning information to risk-management and decision-making departments for ensuring food safety.