Validating an artificial neural network model of Leuconostoc mesenteroides in vacuum packaged sliced cooked meat products for shelf-life estimation

Machine Learning Prediction of Leuconostoc spp. Growth Inducing Spoilage in Cooked Deli Foods Considering the Effect of Glycine and Sodium Acetate

To control spoilage by lactic acid bacteria (Leuconostoc spp.) in cooked deli food, various combinations of environmental and/or intrinsic factors have been employed based on hurdle technology. Since many factors and their combinations greatly influence Leuconostoc spp. growth, this study aimed to develop a machine learning model based on the experimentally obtained growth kinetic data using extreme gradient boosting tree algorithm to quantitatively and flexibly predict Leuconostoc spp. growth. In particular, the effects of sodium acetate (0-1.5%) and glycine (0-1.5%), which are frequently used food additives in the Japanese food industry, on the growth of Leuconostoc spp. in cooked deli foods were examined with a combination of temperature (5-25 °C) and pH (5.0-6.0) conditions. The developed machine learning model to predict the number of Leuconostoc spp. over time successfully demonstrates comparable accuracy in culture media to the conventional Baranyi model-based prediction. Furthermore, while the accuracy of the prediction by the machine learning model for cooked deli foods such as potato salad, Japanese simmered hijiki, and unohana evaluated by the proportion of relative error within the acceptable prediction range was 98%, the accuracy of the conventional Baranyi model-based prediction was 89%. The developed machine learning model successfully and flexibly predicted the growth of Leuconostoc spp. in various cooked deli foods incorporating the effect of food additives, with an accuracy comparable to or better than that of the conventional kinetic-based model.

Modeling and Optimization of Process Parameters for Nutritional Enhancement in Enzymatic Milled Rice by Multiple Linear Regression (MLR) and Artificial Neural Network (ANN)

This study involves information about the concentrations of nutrients (proteins, phenolic compounds, free amino acids, minerals (Ca, P, and Iron), hardness) in milled rice processed with enzymes; xylanase and cellulase produced by Aspergillus awamori, MTCC 9166 and Trichoderma reese, MTCC164. Brown rice was processed with 60-100% enzyme (40 mL buffer -undiluted) for 30 to 150 min at 30 °C to 50 °C followed by polishing for 20-100 s at a safe moisture level. Multiple linear regression (MLR) and artificial neural network (ANN) models were used for process optimization of enzymes. The MLR correlation coefficient (R2) varied between 0.87-0.90, and the sum of square (SSE) was placed within 0.008-8.25. While the ANN R2 (correlation coefficient) varied between 0.97 and 0.9999(1), MSE changed from 0.005 to 6.13 representing that the ANN method has better execution across MLR. The optimized cellulase process parameters (87.2% concentration, 80.1 min process time, 33.95 °C temperature and 21.8 s milling time) and xylanase process parameters (85.7% enzyme crude, 77.1 min process time, 35 °C temperature and 20 s) facilitated the increase of Ca (70%), P (64%), Iron (17%), free amino acids (34%), phenolic compounds (78%) and protein (84%) and decreased hardness (20%) in milled rice. Scanning electron micrographs showed an increased rupture attributing to enzymes action on milled rice.

A mathematical modeling approach to the quantification of lactic acid bacteria in vacuum-packaged samples of cooked meat: Combining the TaqMan-based quantitative PCR method with the plate-count method

The TaqMan-based quantitative Polymerase Chain Reaction (qPCR) method and the Plate Count (PC) method are both used in combination with primary and secondary mathematical modeling, to describe the growth curves of Leuconostoc mesenteroides and Weissella viridescens in vacuum-packaged meat products during storage under different isothermal conditions. Vacuum-Packaged Morcilla (VPM), a typical cooked blood sausage, is used as a representative meat product, with the aim of improving shelf-life prediction methods for those sorts of meat products. The standard curves constructed by qPCR showed good linearity between the cycle threshold (C_T) and log₁₀ CFU/g, demonstrating the high precision and the reproducible results of the qPCR method. The curves were used for the quantification of L. mesenteroides and W. viridescens in artificially inoculated VPM samples under isothermal storage (5, 8, 13 and 18 °C). Primally, both the qPCR and the PC methods were compared, and a linear regression analysis demonstrated a statistically significant linear correlation between the methods. Secondly, the Baranyi and Roberts model was fitted to the growth curve data to estimate the kinetic parameters of L. mesenteroides and W. viridescens under isothermal conditions, and secondary models were used to establish the dependence of the maximum specific growth rate on the temperature. The results proved that primary and secondary models were adequate for describing the growth curves of both methods in relation to both bacteria. In conclusion, the results of all the experiments proved that the qPCR method in combination with the PC method can be used to construct microbial growth kinetics and that primary and secondary mathematical modeling can be successfully applied to describe the growth of L. mesenteroides and W. viridescens in vacuum-packaged morcilla and, by extension, other cooked meat products with similar characteristics.

Growth behavior comparison of Listeria monocytogenes between Type strains and beef isolates in raw beef

This study was conducted to compare the growth parameters of Listeria monocytogenes between beef isolates and Type strains in raw beef. Beef was artificially inoculated with 3 Log CFU/g levels and growth was measured during storage at various temperatures (5-25 °C) using conventional plating methods. The R2 value for lag time (λ) and specific growth rate (μ) were determined using modified-Gompertz model, which were greater than 0.98 at all storage temperature except at 5 °C. B f , A f , and RMSE showed acceptable ranges, showed that the models are suitable for the modeling the growth of L. monocytogenes. At all temperatures, the λ of L. monocytogenes beef isolates was shorter than that of the L. monocytogenes Type strains, and the μ of beef isolates was higher than that of Type strains. These results showed that growth pattern prediction of beef inoculated with L. monocytogenes beef isolates gives more actual results than with Type strains.

Shelf Life of Food Products: From Open Labeling to Real-Time Measurements

The labels currently used on food and beverage products only provide consumers with a rough guide to their expected shelf lives because they assume that a product only experiences a limited range of predefined handling and storage conditions. These static labels do not take into consideration conditions that might shorten a product's shelf life (such as temperature abuse), which can lead to problems associated with food safety and waste. Advances in shelf-life estimation have the potential to improve the safety, reliability, and sustainability of the food supply. Selection of appropriate kinetic models and data-analysis techniques is essential to predict shelf life, to account for variability in environmental conditions, and to allow real-time monitoring. Novel analytical tools to determine safety and quality attributes in situ coupled with modern tracking technologies and appropriate predictive tools have the potential to provide accurate estimations of the remaining shelf life of a food product in real time. This review summarizes the necessary steps to attain a transition from open labeling to real-time shelf-life measurements.

A radial basis function neural network approach to determine the survival of Listeria monocytogenes in Katiki, a traditional Greek soft cheese

A radial basis function neural network was developed to determine the kinetic behavior of Listeria monocytogenes in Katiki, a traditional white acid-curd soft spreadable cheese. The applicability of the neural network approach was compared with the reparameterized Gompertz, the modified Weibull, and the Geeraerd primary models. Model performance was assessed with the root mean square error of the residuals of the model (RMSE), the regression coefficient (R2), and the F test. Commercially prepared cheese samples were artificially inoculated with a five-strain cocktail of L. monocytogenes, with an initial concentration of 10(6) CFU g(-1) and stored at 5, 10, 15, and 20 degrees C for 40 days. At each storage temperature, a pathogen viability loss profile was evident and included a shoulder, a log-linear phase, and a tailing phase. The developed neural network described the survival of L. monocytogenes equally well or slightly better than did the three primary models. The performance indices for the training subset of the network were R2 = 0.993 and RMSE = 0.214. The relevant mean values for all storage temperatures were R2 = 0.981, 0.986, and 0.985 and RMSE = 0.344, 0.256, and 0.262 for the reparameterized Gompertz, modified Weibull, and Geeraerd models, respectively. The results of the F test indicated that none of the primary models were able to describe accurately the survival of the pathogen at 5 degrees C, whereas with the neural network all fvalues were significant. The neural network and primary models all were validated under constant temperature storage conditions (12 and 17 degrees C). First or second order polynomial models were used to relate the inactivation parameters to temperature, whereas the neural network was used a one-step modeling approach. Comparison of the prediction capability was based on bias and accuracy factors and on the goodness-of-fit index. The prediction performance of the neural network approach was equal to that of the primary models at both validation temperatures. The results of this work could increase the knowledge basis for the applicability of neural networks as an alternative tool in predictive microbiology.

Use of artificial neural networks and a gamma-concept-based approach to model growth of and bacteriocin production by Streptococcus macedonicus ACA-DC 198 under simulated conditions of Kasseri cheese production

Growth of and bacteriocin production by Streptococcus macedonicus ACA-DC 198 were assessed and modeled under conditions simulating Kasseri cheese production. Controlled fermentations were performed in milk supplemented with yeast extract at different combinations of temperature (25, 40, and 55 degrees C), constant pH (pHs 5 and 6), and added NaCl (at concentrations of 0, 2, and 4%, wt/vol). The data obtained were used to construct two types of predictive models, namely, a modeling approach based on the gamma concept, as well as a model based on artificial neural networks (ANNs). The latter computational methods were used on 36 control fermentations to quantify the complex relationships between the conditions applied (temperature, pH, and NaCl) and population behavior and to calculate the associated biokinetic parameters, i.e., maximum specific growth and cell count decrease rates and specific bacteriocin production. The functions obtained were able to estimate these biokinetic parameters for four validation fermentation experiments and obtained good agreement between modeled and experimental values. Overall, these experiments show that both methods can be successfully used to unravel complex kinetic patterns within biological data of this kind and to predict population kinetics. Whereas ANNs yield a better correlation between experimental and predicted results, the gamma-concept-based model is more suitable for biological interpretation. Also, while the gamma-concept-based model has not been designed for modeling of other biokinetic parameters than the specific growth rate, ANNs are able to deal with any parameter of relevance, including specific bacteriocin production.