Accurate prediction of salmon freshness under temperature fluctuations using the convolutional neural network long short-term memory model
Introduction
Salmon is delicious, nutritious and rich in protein, but it is easy to spoil and deteriorate. According to reports, every year 30% of aquatic products cannot be consumed due to spoilage and deterioration, and this loss accounts for 25% of the total agricultural losses(Ghaly et al., 2010). For these aquatic products, freshness is one of the most important indicators to evaluate their quality. Studying the changing law of freshness during some storage conditions, and predicting the freshness or shelf life of aquatic products are the current research hotspots(Jedermann et al., 2017).
Freshness is generally affected by the activities of microorganisms, chemistry and enzymes(Ocaño-Higuera et al., 2011; Wu et al., 2019b). During the process, temperature is the most important factor affecting the growth of microorganisms and enzymes(Jay et al., 2008). Most freshness prediction models are established based on microbial kinetics under some temperature conditions. In the process of establishing microbial kinetic models, current researchers have used the knowledge of mathematics, statistics, and microbiology to simulate microbial metabolism(Baranyi and Roberts, 1995; Liu et al., 2021; Nielsen and Villadsen, 1992). At present, the microbial kinetic models can be divided into first-level model, second-level model and expert system(Buchanan, 1993; Ren et al., 2022). The first-level model mainly describes the relationship between microbial growth and time, including Gompertz equation(Baranyi and Roberts, 1995; Ren et al., 2022), logistic equation(Dalgaard, 1995), etc. The second-level model describes the impact of environmental factors on the growth of microorganisms, such as the Arrhenius equation(Guo et al., 2018; Peleg et al., 2012).
However, these kinetic models have some disadvantages. Although these models can obtain good prediction results at a fixed temperature, they cannot adapt to the real storage environment of aquatic products, because temperature fluctuations are almost inevitable during the cold chain transportation and storage of aquatic products. When the temperature fluctuates, the kinetic model is difficult to adapt to the complex and changeable environment factors, because the kinetic equation often has limited parameters, fixed expressions and other defects, so it is urgent to use new theory to predict the freshness.
Some researchers have applied new algorithms for risk assessment of food safety(Lin et al., 2021). Some deep learning and neural network models have been proved to be feasible to apply to food safety early warning(Geng et al., 2021a, 2021b). Therefore, In order to solve the above problems, this paper proposed a new idea based on deep learning to predict freshness. Deep learning is a special neural network that contains multiple hidden layers of multi-layer perceptrons(Bengio et al., 2017; LeCun et al., 2015). Deep learning can combine underlying feature functions to form a complex, multi-layer, and nonlinear deep neural network to perform high-level representation of data. The network can solve data feature expressions that cannot be represented by traditional mathematical equations (LeCun et al., 2015). In addition, deep learning has the advantages of automatic extraction of data features and strong anti-interference ability, which can effectively improve the shortcomings of microbial kinetic equations.
Therefore, the purpose of this paper is to establish a prediction model through deep learning to predict the freshness of salmon under temperature fluctuations. Total viable counts (TVC) was measured as an indicator of freshness and a deep learning model called CNN_LSTM was proposed to predict freshness. In order to highlight the advantages of deep learning model, several typical microbial dynamics models have also been built and compared. The result showed that this method could solve the temperature fluctuating fitting that couldn't be done by traditional kinetic models, and realize the prediction of salmon freshness under arbitrary temperature conditions.
Section snippets
Samples preparation
Salmon was purchased from Huangsha Aquatic Product Market, Guangzhou. The salmon meat was cut into 3 cm × 3 cm × 2 cm salmon slices and placed in the laboratory refrigerators. In order to more comprehensively evaluate the change trend of TVC in salmon meat, the constant temperature and variable temperature storage experiments were designed separately, and different storage time and different temperature conditions were designed. In the constant temperature experiment, four fixed temperatures of
Chemical results and analysis
When measuring TVC, the constant temperature data was shown in Fig. 4(a) and the variable temperature data was shown in Fig. 4(b)-4(f). From Fig. 4 (a), we could see that microbial growth was significantly affected by temperature. According to seafood standards, if the TVC exceeded 6 lgCFU/g, seafood cannot be eaten raw(Atanassova et al., 2008; Sørheim et al., 1996). So we could find that salmon could not be eaten stored at 20 °C for more than 2 days, 4 °C for more than 6 days, and 2 °C for
Discussion
It could be seen that CNN_LSTM had a great advantage in predicting freshness when temperature conditions changed. This was because deep learning had very powerful feature extraction and data fitting capabilities. On one hand, deep learning relied heavily on data, and the quantity and quality of data directly determined the performance of the model. Since this experiment only measured the TVC when the temperature changed among −18 °C, 4 °C, and 20 °C, the prediction results of this model between
Conclusion
A novel model named CNN_LSTM was proposed to predict freshness under temperature fluctuations in this paper. The model not only had a strong nonlinear fitting ability, but also could explore the internal correlation between the storage temperature before and after. Under constant temperature conditions, the model could obtain better prediction results than logistic equation, Gompertz equation and Arhenius equation. Under variable temperature conditions, the model could predict TVC under
Data availability
The data used to support the findings of this study are available from the corresponding author upon request.
Credit author statement
Ting Wu conceived and designed the experiments; Ling Yang and Ningxia Chen analyzed the data; Ting Wu and Jiajia Lu wrote and finalized the manuscript.
Declaration of competing interest
Ting Wu, JiaJia Lu, Juan Zou, Ningxia Chen and Ling Yang declare no conflict of interest.
Acknowledgments
This study was jointly supported by Guangzhou Science and Technology Plan Project (201903010063, 202002030154); Natural Science Foundation of Guangdong Province (2020A1515010834). Department of Education of Guangdong Province Bureau(2020ZDZX1060).
References (32)
- et al.
Microbiological quality of sushi from sushi bars and retailers
J. Food Protect.
(2008) - et al.
Mathematics of predictive food microbiology
Int. J. Food Microbiol.
(1995) Predictive food microbiology
Trends Food Sci. Technol.
(1993)Modelling of microbial activity and prediction of shelf life for packed fresh fish
Int. J. Food Microbiol.
(1995)- et al.
Early warning and control of food safety risk using an improved AHC-RBF neural network integrating AHP-EW
J. Food Eng.
(2021) - et al.
Challenges and opportunities in remote monitoring of perishable products
Food Packag. Shelf Life
(2017) - et al.
Minimum growth temperatures for food-poisoning, fecal-indicator, and psychrophilic microorganisms
Adv. Food Res.
(1964) - et al.
Modelling of microbial kinetics
Chem. Eng. Sci.
(1992) - et al.
Freshness assessment of ray fish stored in ice by biochemical, chemical and physical methods
Food Chem.
(2011) - et al.
Ensuring the quality of meat in cold chain logistics: a comprehensive review
Trends Food Sci. Technol.
(2022)
Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network
Phys. Nonlinear Phenom.
Effects of modified gas atmosphere packaging on pork loin colour, display life and drip loss
Meat Sci.
Hyperparameter optimization for machine learning models based on Bayesian optimization
J. Electron. Sci.Technol.
Novel techniques for evaluating freshness quality attributes of fish: a review of recent developments
Trends Food Sci. Technol.
Understanding of a convolutional neural network
Deep Learning
Cited by (9)
Leafy vegetable freshness identification using hyperspectral imaging with deep learning approaches
2024, Infrared Physics and TechnologyEnhancing fish freshness prediction using NasNet-LSTM
2024, Journal of Food Composition and AnalysisITF-WPI: Image and text based cross-modal feature fusion model for wolfberry pest recognition
2023, Computers and Electronics in AgricultureEvaluation of vegetable sauerkraut quality during storage based on convolution neural network
2023, Food Research InternationalCitation Excerpt :Among them, Inception V3 produced the best image recognition accuracy. T. Wu, Lu, Zou, Chen, and Yang (2022) proposed a novel model named convolutional neural network_ long short-term memory (CNN_LSTM). The advantage of this model is that it can accurately predict salmon freshness within a range of temperature fluctuations.