Porphyrin fluorescence imaging for real-time monitoring and visualization of the freshness of beef stored at different temperatures.

This study presents a novel fluorescence imaging method for the real-time monitoring of beef quality deterioration and freshness. The fluorescence property of porphyrin in the form of heme can be used to characterize quality changes in beef during storage. Therefore, a fluorescence imaging system with an excitation light source of 440 nm and a CCD camera with a specific wavelength filter of 595 nm was constructed, and the porphyrin fluorescence images of beef samples stored at different temperatures were then collected. The quantitative model for predicting the microbial freshness indicator (TVC) of beef was built with the support vector machine regression (SVR) algorithm and produced satisfactory results with Rc2 and Rp2 of 0.858 and 0.812, respectively. The classification model based on the support vector machine (SVM) algorithm classified beef freshness into "fresh" and "spoiled", with calibration and prediction accuracy of 100 % and 90.9 %, respectively.

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.

ANN-based food shelf life prediction methods are reviewed.This paper discusses application of ANN in the food storage process.BPNN is the mainstream ANN architecture used for the prediction of food quality.ANNs are useful for prediction of outputs with high accuracy.Future trends of ANN in the agri-supply chain are evaluated.

A novel method for real-time prediction of the shelf life of pork at different storage temperatures using front-face fluorescence excitation-emission matrices.

This study presents a novel method for predicting the shelf life of pork in real-time based on front-face fluorescence excitation-emission matrices (EEMs). The total viable count (TVC) of bacteria was used as the indicator of microbial spoilage in the pork samples. Modified Gompertz and square root equations were used to establish models for the trends in microbial growth and for predicting the shelf life, the R2 values of the fitting equation at different temperatures were all greater than 0.95. The fluorescence intensity ratio of oxidation product to tryptophan (FOX/Trp) was highly correlated with the quality deterioration of pork and was therefore used to establish a quantitative model of TVC values by linear regression with Rc2 and Rp2 values of 0.914 and 0.906, respectively. The mean absolute errors between the remaining shelf life predicted by fluorescence EEMs and the measured values at three storage temperatures were less than 1 day.

Preparation and characterization of intelligent packaging film for visual inspection of tilapia fillets freshness using cyanidin and bacterial cellulose.

An intelligent pH-sensitive film was developed by incorporating cyanidin-3-glucoside (C3G) into bacterial cellulose (BC), and its application as a freshness indicator for tilapia fillets was investigated. The physical properties of the film were characterized using Fourier-transform infrared spectroscopy (FTIR), scanning electron microscopy (SEM), and X-ray diffraction (XRD). The results demonstrated the mechanical properties of the film were significantly changed due to higher crystallinity induced by C3G. XRD and FTIR analysis showed the increased crystallinity and transmittance intensity of the BC-C3G film. Moreover, this film exhibited distinctive color changes from red to green when exposed to buffers with a pH of 3 to 10. In accordance with changes in total volatile basic nitrogen (TVB-N) and total viable count (TVC) of tilapia fillets, the indicator demonstrated visualized color changes as rose-red (fresh), purple (still suitable), and lavender (spoiled) during storage at both 25 °C and 4 °C. The results suggest that this film has great potential to be used as an intelligent indicator to monitor the freshness of fish.

Mathematical model of postharvest variation in tomato color based on optimized response surface methodology.

BACKGROUND: Manual inspection and instrumentation form the traditional approach to determining tomato color but these methods only determine tomato color at a given moment and cannot predict dynamically how tomato color varies during storage and transportation. Such methods thus cannot help suppliers and retailers establish good management practices for the flexible control of tomato maturity, accurate judgment of market positioning in the industry, or during distribution and marketing. To address this shortcoming, this work first investigates how tomato color parameters (a* and h°) evolve through the various stages of maturity (green, turn, and light red) under different storage conditions. Based on experimental results, it develops an optimized response-surface model (RSM) by using differential evolution to predict how tomato color varies during storage. RESULTS: Tomatoes are more likely to change color at high temperatures and under conditions of high humidity. Temperature affects tomato color more strongly than humidity. The accuracy of the RSM was confirmed by a good agreement with experiments. All determination coefficients R2 of the RSMs for a* and h° are greater than 0.91. The mean absolute errors for a* and h° are 3.8112 and 5.6500, respectively. The root mean square errors for a* and h° are 4.6840 and 6.9198, respectively. CONCLUSION: This research reveals how storage temperature and humidity affect the postharvest variations in tomato color and thus establishes a dynamic model for predicting tomato color. The proposed RSM provides a reliable theoretical foundation for dynamic, nondestructive monitoring of tomato ripeness in the cold chain. © 2021 Society of Chemical Industry.

Comparison of freshness prediction method for salmon fillet during different storage temperatures.

BACKGROUND: Many new forecasting models have been applied to fish freshness prediction like support vector regression (SVR) and radial basis function neural network (RBFNN). In this study, RBFNN, SVR, and Arrhenius models were established and compared for predicting and evaluating the quality of salmon fillets during storage at different temperatures, based on thiobarbituric acid (TBA), total volatile basic nitrogen (TVB-N), total viable counts (TVCs), K value, and sensory assessment (SA). RESULTS: The TBA, TVB-N, TVC, and K values increased during storage whereas SA decreased. Residuals of the three models are random and irregular, indicating that these models were suitable for predicting the freshness of salmon fillets. The RBFNN predicted quality of salmon fillets stored at different temperatures with relative errors all within ±5% (except for the TVC value at day 6). Relative errors of the SVR model for predicting TVB-N and K value were within 10%, while the relative errors of the Arrhenius model fluctuated greatly (ranging from ±0.46 to ±38.29%) and most of it exceeded 10%. RBFNN model had the best predictive performance by comparing the residual and relative errors of the three models. CONCLUSION: RBFNN is a promising method for predicting the freshness of salmon fillets stored at -2 to 10 °C in the cold chain. © 2021 Society of Chemical Industry.

Non-destructive determination of chemical and microbial spoilage indicators of beef for freshness evaluation using front-face synchronous fluorescence spectroscopy.

We investigated the potential of front-face synchronous fluorescence spectroscopy (△λ = 75 nm) to non-destructively evaluate beef freshness and quality decline during chilled storage. The total volatile basic nitrogen (TVB-N), thiobarbituric acid reactive substances (TBARS) and total viable count (TVC) values were used as standard freshness indicators. The fluorescent substances, including amino acids, collagen and conjugated Schiff bases, were highly correlated with the chemical and microbial deterioration of the beef. Quantitative models for simultaneously predicting the three freshness indicators were built combined with partial least squares (PLS) algorithm and showed good reliability. For TVB-N and TBARS values, Rc2 and Rp2 were both above 0.900, and for TVC values Rc2 and Rp2 were 0.912 and 0.871, respectively. The qualitative model established by partial least squares discriminant analysis (PLS-DA) algorithm could accurately classify beef samples as fresh, acceptable or spoiled. The accuracy of the calibration and validation sets were 92.54% and 86.96%, respectively.