Nondestructive Prediction of Tilapia Fillet Freshness During Storage at Different Temperatures by Integrating an Electronic Nose and Tongue with Radial Basis Function Neural Networks

Development of machine learning-based shelf-life prediction models for multiple marine fish species and construction of a real-time prediction platform

At least 10 million tons of seafood products are spoiled or damaged during transportation or storage every year worldwide. Monitoring the freshness of seafood in real time has become especially important. In this study, four machine learning algorithms were used for the first time to develop a multi-objective model that can simultaneously predict the shelf-life of five marine fish species at multiple storage temperatures using 14 features such as species, temperature, total viable count, K-value, total volatile basic‑nitrogen, sensory and E-nose-GC-Ms/Ms. as inputs. Among them, the radial basis function model performed the best, and the absolute errors of all test samples were <0.5. With the optimal model as the base layer, a real-time prediction platform was developed to meet the needs of practical applications. This study successfully realized multi-objective real-time prediction with accurate prediction results, providing scientific basis and technical support for food safety and quality.

Non-destructive prediction of TVB-N using color-texture features of UV-induced fluorescence image for freeze-thaw treated frozen-whole-round tilapia

BACKGROUND

The investigation of UV-induced fluorescence imaging coupled with machine learning was conducted to non-destructively detect the total volatile basic nitrogen (TVB-N) of frozen-whole-round tilapia (FWRT) during freezing and thawing. The UV-induced fluorescence images of FWRT at the wavelength of 365 nm were acquired by self-developed fluorescence image acquisition system. In total, 169 color and texture features based on RGB, hue-saturation-intensity and L*a*b* color spaces and gray level co-occurrence matrix were extracted, respectively. Successive projections algorithm (SPA) was employed to select the optimal 16 features to achieve feature dimension reduction modeling. With full and extracted features as input, the models of partial least squares regression (PLSR), least-squares support vector machine (LSSVM) and convolutional neural network (CNN) were established for TVB-N prediction.

RESULTS

Results indicated that the full features-based CNN performed better than SPA based prediction models (SPA-PLSR and SPA-LSSVM). The CNN model was determined to be the optimal with an RP2 value of 0.9779, RMSEP value of 1.1502 × 10-2  g N kg-1 and RPD value of 6.721 for TVB-N content predictiin.

CONCLUSION

The CNN method based on UV fluorescence imaging technology has potential for quality and safety detection of FWRT. © 2023 Society of Chemical Industry.

Establishment of a quality evaluation system of sweet potato starch using multivariate statistics

Background

The quality of starch greatly affects the quality of processed products. There are many indexes for quality evaluation of starch. Currently, amylose content is considered the chief index in the quality evaluation of sweet potato starch, which is entirely based on tradition (experience) method. The existing evaluation standards lack quality evaluation standards for sweet potato starch.

Purpose

To screen reasonable evaluation indexes of sweet potato starch, and establish a scientific and systematic evaluation system of sweet potato starch.

Methods

Twenty-two components and quality indexes of sweet potato starch were measured. The evaluation indexes of sweet potato starch were screened based on a statistical description, correlation analysis, and principal component analysis (PCA), and a quality evaluation model of sweet potato starch for brewing was established based on analytic hierarchy process. The calculated values of the model were verified by linear fitting with standardized sensory evaluation values.

Results

The coefficient of variation of total starch content (%), amylose content (%), amylopectin content (%), L* value, ΔE, water absorption capacity (g/g), and pasting temperature was less than 6%, while the coefficient of variation of other indexes was larger. In addition, there were different degrees of correlation among the indexes. PCA was used to identify interrelated variables, and the first six principal components together account for 82.26% of the total variability. Then, seven core indexes — setback (cp), rate of regression (%), ratio of amylose to amylopectin (%), gel strength (kgf/cm2), a* value, ash content (%), and solubility (%) — were selected from the six principal components according to the load value of the rotation matrix. These seven core indexes replaced the original 22 indexes to simplify the evaluation of sweet potato starch. The quality evaluation model of sweet potato starch was Y = 0.034X2 + 0.321X6 + 0.141X8 + 0.08X17 + 0.023X19 + 0.08X21 + 0.321X22.

Conclusion

The comprehensive evaluation system of sweet potato starch can accurately predict the quality of sweet potato starch. The development of such a system is of great significance to the post-harvest processing of high-starch sweet potato and the breeding of high-quality and high-starch sweet potato varieties.

Recent Progress in Amine Gas Sensors for Food Quality Monitoring: Novel Architectures for Sensing Materials and Systems

The increasing demand for food production has necessitated the development of sensitive and reliable methods of analysis, which allow for the optimization of storage and distribution while ensuring food safety. Methods to quantify and monitor volatile and biogenic amines are key to minimizing the waste of high-protein foods and to enable the safe consumption of fresh products. Novel materials and device designs have allowed the development of portable and reliable sensors that make use of different transduction methods for amine detection and food quality monitoring. Herein, we review the past decade's advances in volatile amine sensors for food quality monitoring. First, the role of volatile and biogenic amines as a food-quality index is presented. Moreover, a comprehensive overview of the distinct amine gas sensors is provided according to the transduction method, operation strategies, and distinct materials (e.g., metal oxide semiconductors, conjugated polymers, carbon nanotubes, graphene and its derivatives, transition metal dichalcogenides, metal organic frameworks, MXenes, quantum dots, and dyes, among others) employed in each case. These include chemoresistive, fluorometric, colorimetric, and microgravimetric sensors. Emphasis is also given to sensor arrays that record the food quality fingerprints and wireless devices that operate as radiofrequency identification (RFID) tags. Finally, challenges and future opportunities on the development of new amine sensors are presented aiming to encourage further research and technological development of reliable, integrated, and remotely accessible devices for food-quality monitoring.

Effect of acrolein, a lipid oxidation product, on the formation of the heterocyclic aromatic amine 2-amino-1-methyl-6-phenylimidazo[4,5-b]pyridine (PhIP) in model systems and roasted tilapia fish patties

•

Acrolein was able to contribute to PhIP formation.

•

Acrolein facilitated Strecker degradation of phenylalanine.

•

Acrolein increased the formation of some key intermediates of PhIP.

•

Acrolein reacted with phenylalanine, creatinine, and PhIP to form adducts.

•

The oxidation of tilapia fish increased the PhIP formation in the roasted fish patties.

The effect of acrolein on the formation of the 2-amino-1-methyl-6-phenylimidazo[4,5-b]pyridine (PhIP) was investigated in a chemical model. Acrolein was found to increase PhIP formation at each tested addition level. 0–0.2 mmol of acrolein increased PhIP formation dose-dependently, while high levels of acrolein (>0.2 mmol) did not further increase PhIP formation. Mechanistic study showed that acrolein addition decreased the residue of phenylalanine and creatinine, but increased the content of some key intermediates. Further analysis indicated that acrolein can react with phenylalanine, creatinine, and PhIP to form adducts. These results suggested that acrolein was able to contribute to PhIP formation as a consequence of its comprehensive ability to facilitate Strecker degradation of phenylalanine and react with phenylalanine, creatinine, and PhIP. In addition, oxidation of the tilapia fish increased the PhIP formation in the roasted fish patties, further supporting the potential contribution role of lipid oxidation products to the formation of PhIP.

E-Senses, Panel Tests and Wearable Sensors: A Teamwork for Food Quality Assessment and Prediction of Consumer’s Choices

At present, food quality is of utmost importance, not only to comply with commercial regulations, but also to meet the expectations of consumers; this aspect includes sensory features capable of triggering emotions through the citizen’s perception. To date, key parameters for food quality assessment have been sought through analytical methods alone or in combination with a panel test, but the evaluation of panelists’ reactions via psychophysiological markers is now becoming increasingly popular. As such, the present review investigates recent applications of traditional and novel methods to the specific field. These include electronic senses (e-nose, e-tongue, and e-eye), sensory analysis, and wearables for emotion recognition. Given the advantages and limitations highlighted throughout the review for each approach (both traditional and innovative ones), it was possible to conclude that a synergy between traditional and innovative approaches could be the best way to optimally manage the trade-off between the accuracy of the information and feasibility of the investigation. This evidence could help in better planning future investigations in the field of food sciences, providing more reliable, objective, and unbiased results, but it also has important implications in the field of neuromarketing related to edible compounds.

Analysis of Alternative Shelf Life-Extending Protocols and Their Effect on the Preservation of Seafood Products

Seafood is essential to a healthy and varied diet due to its highly nutritious characteristics. However, seafood products are highly perishable, which results in financial losses and quality concerns for consumers and the industry. Due to changes in consumer concerns, demand for healthy products has increased. New trends focusing on reducing synthetic preservatives require innovation and the application of additional or alternative strategies to extend the shelf life of this type of product. Currently, refrigeration and freezing storage are the most common methods for fish preservation. However, refrigeration alone cannot provide long shelf-life periods for fish, and freezing worsens sensorial characteristics and consumer interest. Therefore, the need to preserve seafood for long periods without exposing it to freezing temperatures exists. This review focuses on the application of other approaches to seafood products, such as biodegradable films and coating technology; superchilling; irradiation; high-pressure processing; hyperbaric storage; and biopreservation with lactic acid bacteria, bacteriocins, or bacteriophages. The efficiency of these techniques is discussed based on their impact on microbiological quality, sensorial degradation, and overall preservation of the product’s nutritional properties. Although these techniques are already known, their use in the industrial processing of seafood is not widespread. Thus, the novelty of this review is the aggregation of recent studies on shelf life extension approaches, which provide useful information for the selection of the most appropriate technology and procedures and industrial innovation. Despite the fact that all techniques inhibit or delay bacterial proliferation and product decay, an undesirable sensory impact may occur depending on the treatment conditions. Although no technique appears to replace refrigeration, the implementation of additional treatments in the seafood processing operation could reduce the need for freezing, extending the shelf life of fresh unfrozen products.

Prediction in the Dynamics and Spoilage of Shewanella putrefaciens in Bigeye Tuna (Thunnus obesus) by Gas Sensors Stored at Different Refrigeration Temperatures

Shewanella putrefaciens have a faster growth rate and strong spoilage potential at low temperatures for aquatic products. This study developed a nondestructive method for predicting the kinetic growth and spoilage of S. putrefaciens in bigeye tuna during cold storage at 4, 7 and 10 °C by electronic nose. According to the responses of electronic nose sensor P30/2, the fitted primary kinetic models (Gompertz and logistic models) and secondary model (square root function model) were able to better simulate the dynamic growth of S. putrefaciens, with high R² and low RMSE values in the range of 0.96–0.99 and 0.021–0.061, respectively. A partial least squares (PLS) regression model based on both electronic nose sensor response values and electrical conductivity (EC) values predicted spoilage of S. putrefaciens in bigeye tuna more accurately than the PLS model based on sensor signal values only. In addition, SPME/GC-MS analysis suggested that 1-octen-3-ol, 2-nonanone, 2-heptanone, dimethyl disulfide and methylamine, N, N-dimethyl- are the key VOCs of tuna inoculated with S. putrefaciens.

Detection of decomposition in mahi-mahi, croaker, red snapper, and weakfish using an electronic-nose sensor and chemometric modeling

This study evaluated an electronic-nose (e-nose) sensor in combination with support vector machine (SVM) modeling for predicting the decomposition state of four types of fish fillets: mahi-mahi, croaker, red snapper, and weakfish. The National Seafood Sensory Expert scored fillets were thawed, 10-g portions were weighed into glass jars which were then sealed, and the jars were held at approximately 30°C to allow volatile components to be trapped and available for analysis. The measurement of the sample vial headspace was performed with an e-nose device consisting of nanocomposite, metal oxide semiconductor (MOS), electrochemical, and photoionization sensors. Classification models were then trained based on the sensory grade of each fillet, and the e-nose companion chemometric software identified that eight MOS were the most informative for determining a sensory pass from sensory fail sample. For SVM, the cross-validation (CV) correct classification rates for mahi-mahi, croaker, red snapper, and weakfish were 100%, 100%, 97%, and 97%, respectively. When the SVM prediction performances of the eight MOS were evaluated using a calibration-independent test set of samples, correct classification rates of 93-100% were observed. Based on these results, the e-nose measurements coupled with SVM models were found to be potentially promising for predicting the spoilage of these four fish species. PRACTICAL APPLICATION: This report describes the application of an electronic-nose sensor as a potential rapid and low-cost screening method for fish spoilage. It could provide regulators and stakeholders with a practical tool to rapidly and accurately assess fish decomposition.

Application of Artificial Intelligence in Food Industry—a Guideline

Artificial intelligence (AI) has embodied the recent technology in the food industry over the past few decades due to the rising of food demands in line with the increasing of the world population. The capability of the said intelligent systems in various tasks such as food quality determination, control tools, classification of food, and prediction purposes has intensified their demand in the food industry. Therefore, this paper reviews those diverse applications in comparing their advantages, limitations, and formulations as a guideline for selecting the most appropriate methods in enhancing future AI- and food industry–related developments. Furthermore, the integration of this system with other devices such as electronic nose, electronic tongue, computer vision system, and near infrared spectroscopy (NIR) is also emphasized, all of which will benefit both the industry players and consumers.

Relationship between Micromolecules and Quality Changes of Tilapia Fillets after Partial Freezing Treatment with Polyphenols

The study investigated the main characteristic micromolecular changes in tilapia fillets after partial freezing treatment with polyphenols by ultrahigh-performance liquid chromatography-quadrupole time-of-flight mass spectrometry (UHPLC-Q-TOF-MS) analysis. A total of 2121 metabolite ion features were identified. The result suggested that procyanidin treatment increased the sweet, salty, and thick peptides' contents and suppressed the formation of bitter peptides. The levels of cis-4-octenedioic acid, 2-amino-heptanoic acid, indoleacrylic acid, and 2-amino-3-methyl-1-butanol in polyphenol treatments were significantly lower compared to those in the control group (P < 0.05), which delayed the formation of micromolecule of acids and alcohols associated with spoilage and inhibited the protein and lipid oxidation and degradation. Polyphenol treatments suppressed the formation of biogenic amines (lower levels of spermidine and 1-naphthylacetylspermine) and reduced fillet quality deterioration. It provided critical novel insights into the understanding of the molecular mechanism for inhibiting the quality deterioration of fillets treated with polyphenols during storage.

Intelligent pH indicator films containing anthocyanins extracted from blueberry peel for monitoring tilapia fillet freshness

BACKGROUND

Fish spoilage leads to an increase in the pH value of the fish. A colorimetric pH indicator can be used to monitor fish spoilage and has been exploited in intelligent packaging because of its simplicity, practicality and low cost. The aim of this study was to develop two pH-indicator films comprising starch (S), tara gum (TG), polyvinyl alcohol (PVA) and anthocyanins extracted from blueberry peel and the films were then used to monitor the freshness of tilapia fillets during storage at 25 and 4 °C.

RESULTS

The ultraviolet-visible (UV-visible) spectra and color of anthocyanins changed within pH 2-10. Fourier-transform infrared spectroscopy, UV-visible spectrophotometry and scanning electron microscopy certified that blueberry peel extract (BPE) had been introduced into the S/PVA and TG/PVA matrices. Visual color changes in the films occurred at pH 2-8. A freshness application test was conducted in tilapia fillets stored at 4 and 25 °C, and visual color changes in the films were observed. The TG/PVA/BPE film had a greater color difference (ΔE) from pink and transparent to dark yellow at 25 °C and to dark purple at 4 °C than ΔE of S/PVA/BPE film, which sufficiently correlated with the change of total volatile base nitrogen (TVB-N) and total aerobic counts (TACs) of fillets.

CONCLUSION

It can be concluded that the color changes of TG/PVA/BPE films were corresponded with TVB-N and TAC values of tilapia fillets, which presented great potential as a visual package label to monitor fish freshness at ambient and chilled temperatures. © 2020 Society of Chemical Industry.

Paper-Based Enzyme Biosensor for One-Step Detection of Hypoxanthine in Fresh and Degraded Fish

Food freshness monitoring, which can reflect the quality of the product at the time of use, remains a great challenge for consumers and the food industry. Herein, we report the development of a cost-effective enzyme-based paper biosensor, which can monitor fish freshness and predict spoilage. The biosensor measures the release of hypoxanthine (HX), an indicator of meat and fish degradation, using the enzymatic conversion of HX by xanthine oxidase (XOD). We demonstrate that the entrapment of XOD and an organic dye, nitro blue tetrazolium chloride (NBT), within a sol-gel biohybrid enables their stabilization on paper and promotes the enzymatic reaction with further retention of the reaction products within the cellulosic network . Linearity in the micromolar concentration range with a detection limit of 3.7 μM for HX is obtained. The biosensor has high selectivity toward HX and is manufactured in few steps from inexpensive widely available materials. The applicability of the biosensor is demonstrated by following fish degradation over time and measuring HX concentrations ranging from 117 (±9) to 198 (±5) μM within 24 h of degradation, at levels that are comparable with those measured by a commercial enzymatic kit for HX detection. As compared to the commercial kit, our biosensors are more cost-effective, do not require addition of exogenous reagents and are portable, having all of the reagents needed for analysis embedded within the sensing platform. This proof-of-concept work demonstrates that the paper-based HX biosensor has potential as a robust reagentless device for real-time monitoring of food freshness and for other applications in which HX plays an important role.

A comprehensive review on freshness of fish and assessment: Analytical methods and recent innovations

Fish, a highly nutritious, containing a good amount of protein and fatty acids, has TMA and TVB-N present as major factors responsible for quality deterioration during storage and maintaining of fish freshness. Freshness is one of the most important parameters in the fish market. There are many methods of estimating fish freshness, out of which some are very costly while others are not user-friendly. However, with more technological innovations, there have been efforts to make a more reliable method of calculating and analyzing freshness. Parameters chosen for assessing the freshness are sensory, physical, chemical and microbiological including the recent trends such as SDS-PAGE, fast protein liquid chromatography, hyper Spectral Imaging Technique, etc. focused on reducing time, destruction and labor. Traditional and recent methods of evaluation of freshness along with their comparison based on several parameters are needed to link them and making it convenient for upcoming researchers to have a detailed study for having a universal indicator for assessing the freshness of fish. Information in the present article has all the methods of assessing the fish freshness been discussed in detail. There has also been focus on bringing the readers knowledge about the comprehensive information related to recent developments. The recommended limit for different indicators signifies the time period for which the particular fish can be stored and it depends upon several factors like species, surrounding environment and enzymatic and non-enzymatic actions. Based on these demands, this paper is uniquely worked upon to review the different literature which brought all the discussions from the past including the recent innovations in assessing the freshness of different fishes with the help of various indicators as well as a complete study of spoilage and toxicity mechanism leading to deterioration in quality, making it easy for the reader and researchers to have quick glance over the trends and innovations.

Discrimination of Grape Seeds Using Laser-Induced Breakdown Spectroscopy in Combination with Region Selection and Supervised Classification Methods

The wine-making industry generates a considerable amount of grape pomace. Grape seeds, as an important part of pomace, are rich in bioactive compounds and can be reutilized to produce useful derivatives. The nutritional properties of grape seeds are largely influenced by the cultivar, which calls for effective identification. In the present work, the spectral profiles of grape seeds belonging to three different cultivars were collected by laser-induced breakdown spectroscopy (LIBS). Three conventional supervised classification methods and a deep learning method, a one-dimensional convolutional neural network (CNN), were applied to establish discriminant models to explore the relationship between spectral responses and cultivar information. Interval partial least squares (iPLS) algorithm was successfully used to extract the spectral region (402.74–426.87 nm) relevant for elemental composition in grape seeds. By comparing the discriminant models based on the full spectra and the selected spectral regions, the CNN model based on the full spectra achieved the optimal overall performance, with classification accuracy of 100% and 96.7% for the calibration and prediction sets, respectively. This work demonstrated the reliability of LIBS as a rapid and accurate approach for identifying grape seeds and will assist in the utilization of certain genotypes with desirable nutritional properties essential for production rather than their being discarded as waste.

Emerging trends of advanced sensor based instruments for meat, poultry and fish quality- a review

Meat and fish chemical composition and sensory attributes are markers of quality that require innovative assessment methods as existing ones are rather technical, laborious, and expensive. Emerging trends of advanced technology instruments have been lauded in the pharmaceutical, cosmetic and food industries for their high sensitivity, customizability, rapidness and affordability. Common among these, are the electronic tongue (e-tongue) and electronic nose (e-nose) but their use for meat and fish quality, remains scanty and scattered. This paper aims to systematically discuss the developing trends, principles and the recent use of e-tongue and e-nose for quality measurements in fish and meat. From over 90 research papers, it was observed that an arsenal of chemometric tools have been pivotal in applying these instruments for rapid quantitative, qualitative and predictive analysis of some physical properties, chemical properties, storability and the authentication of meat and fish. Both instruments require no reagent (waste free analytical procedure) and have been lauded for precision and*accuracy but e-nose may be better suited for meat and fish assessments. Unlike the e-tongue, e-nose requires no liquid sample preparation and portable versions are promising for rapid remote analysis of meat and fish samples that can save cost on transferring carcass to laboratories.

An on-package colorimetric sensing label based on a sol-gel matrix for fish freshness monitoring

Fish freshness monitoring is important for consumers. This study aims to develop an colorimetric sensing label based on bromocresol green (BCG) and a sol-gel matrix layer coated onto filter paper to monitor fish freshness. Characterization results showed that the sol-gel layer was successfully coated, and the coating yield was 14.25%. The fish freshness could be detected clearly by the naked eye as the color of the sensing label changed. A Hue Saturation Value (HSV) model was used to correlate the response of the sensing label to the freshness of fish samples. Hue (H) values showed a linear response to the total volatile basic nitrogen (TVB-N) concentration in the range of 16.4-23.11 mg/100 g at room temperature, and in the range of 9.28-24.12 mg/100 g at a chilled temperature. The sensing label was applied to other types of fish, and showed an intense color change during the spoilage trial.

Effect of Cell-Free Supernatant from Aeromonas sobria on the Spoilage of Shewanella putrefaciens in Pacific White Shrimp (Litopenaeus vannamei) with the Influence of Temperature Fluctuation

The objective of this study was to evaluate the effect of cell-free supernatant (CFS) from Aeromonas sobria on the growth and spoilage potential of Shewanella putrefaciens in Pacific white shrimp (Litopenaeus vannamei) during cold chain logistics, including transportation, retailing, and domestic storage. It was shown that the quality of shrimps deteriorated in the cold chain logistics over time. The temperature fluctuation during the experimental period favored the growth of S. putrefaciens, increased the total volatile basic nitrogen (TVB-N) and biogenic amine value, and decreased the sensory quality of shrimps. The application of CFS resulted in the decline on the growth of S. putrefaciens after the early stationary phase stored at a cold condition. It is concluded that the application of CFS can inhibit microbial growth and the spoilage potential of S. putrefaciens and offset the quality deterioration of shrimp exposed to temperature fluctuation during cold chain logistics.