Combining the genetic algorithm and successive projection algorithm for the selection of feature wavelengths to evaluate exudative characteristics in frozen–thawed fish muscle

Fusing hyperspectral imaging and electronic nose data to predict moisture content in Penaeus vannamei during solar drying

The control of moisture content (MC) is essential in the drying of shrimp, directly impacting its quality and shelf life. This study aimed to develop an accurate method for determining shrimp MC by integrating hyperspectral imaging (HSI) with electronic nose (E-nose) technology. We employed three different data fusion approaches: pixel-, feature-, and decision-fusion, to combine HSI and E nose data for the prediction of shrimp MC. We developed partial least squares regression (PLSR) models for each method and compared their performance in terms of prediction accuracy. The decision fusion approach outperformed the other methods, producing the highest determination coefficients for both calibration (0.9595) and validation sets (0.9448). Corresponding root-mean square errors were the lowest for the calibration set (0.0370) and validation set (0.0443), indicating high prediction precision. Additionally, this approach achieved a relative percent deviation of 3.94, the highest among the methods tested. The findings suggest that the decision fusion of HSI and E nose data through a PLSR model is an effective, accurate, and efficient method for evaluating shrimp MC. The demonstrated capability of this approach makes it a valuable tool for quality control and market monitoring of dried shrimp products.

TROLLOPE: A novel sequence-based stacked approach for the accelerated discovery of linear T-cell epitopes of hepatitis C virus

Hepatitis C virus (HCV) infection is a concerning health issue that causes chronic liver diseases. Despite many successful therapeutic outcomes, no effective HCV vaccines are currently available. Focusing on T cell activity, the primary effector for HCV clearance, T cell epitopes of HCV (TCE-HCV) are considered promising elements to accelerate HCV vaccine efficacy. Thus, accurate and rapid identification of TCE-HCVs is recommended to obtain more efficient therapy for chronic HCV infection. In this study, a novel sequence-based stacked approach, termed TROLLOPE, is proposed to accurately identify TCE-HCVs from sequence information. Specifically, we employed 12 different sequence-based feature descriptors from heterogeneous perspectives, such as physicochemical properties, composition-transition-distribution information and composition information. These descriptors were used in cooperation with 12 popular machine learning (ML) algorithms to create 144 base-classifiers. To maximize the utility of these base-classifiers, we used a feature selection strategy to determine a collection of potential base-classifiers and integrated them to develop the meta-classifier. Comprehensive experiments based on both cross-validation and independent tests demonstrated the superior predictive performance of TROLLOPE compared with conventional ML classifiers, with cross-validation and independent test accuracies of 0.745 and 0.747, respectively. Finally, a user-friendly online web server of TROLLOPE (http://pmlabqsar.pythonanywhere.com/TROLLOPE) has been developed to serve research efforts in the large-scale identification of potential TCE-HCVs for follow-up experimental verification.

Variable selection in the chemometric treatment of food data: A tutorial review

Food analysis covers aspects of quality and detection of possible frauds to ensure the integrity of the food. The arsenal of analytical instruments available for food analysis is broad and allows the generation of a large volume of information per sample. But this instrumental information may not yet give the desired answer; it must be processed to provide a final answer for decision making. The possibility of discarding non-informative and/or redundant signals can lead to models of better accuracy, robustness, and chemical interpretability, in line with the principle of parsimony. Thus, in this tutorial review, we cover aspects of variable selection in food analysis, including definitions, theoretical aspects of variable selection, and case studies showing the advantages of variable selection-based models concerning the use of a wide range of non-informative and redundant instrumental information in the analysis of food matrices.

A novel method for selecting the set optimal wavelength combination in multi-spectral transmission image

In the process of detecting heterogeneity in breast tissue based on multi-spectral transmission imaging, the detection accuracy will be affected due to the high redundancy degree of information between bands. In order to select the reasonable wavelength combination, this paper uses various nonlinear transformations to convert the multi-spectral images into spectral data for the first time, so as to select the set optimal wavelength combination based on the successive projections algorithm (SPA). Firstly, we design the collection experiment of 4-wavelength multi-spectral image. And then, K-SVD dictionary learning method, texture extraction method and gray correlation analysis method are used to obtain the feature spectral information. Finally, the set optimal wavelength combination is selected based on SPA. The experimental results show that random forest (RF) classification model and Faster-RCNN recognition models effectively verify that the combination of wavelengths 1,2,4 selected has the highest accuracy in the heterogeneous detection. In conclusion, this paper uses modulation-frame accumulation technique to improve the quality of multi-spectral transmission images. And based on the RF and Faster-RCNN models, the effectiveness of SPA-based optimal wavelength combination method proposed is verified, which will provide a new idea of feature wavelength selection for screening early breast masses through multi-spectral transmission imaging.

MEMS-based linear micromirror array with a high filling factor for spatial light modulation

A smart digital micromirror device (DMD) was employed to realize the on-chip scanning in versatile hyperspectral imaging (HSI) systems in our previous research. However, the rotation manner around the diagonal of the DMD makes the imaging subsystem and the spectral dispersion subsystem unable to be in the same horizontal surface. This leads to the difficulty in designing the opto-mechanical structures, system assembly and adjustment of the light path to a certain extent. On the other hand, the HSI system also needs a larger space to accommodate the two subsystems simultaneously since either of them has to incline against the horizontal surface. Moreover, there exists the interference of the reflected light between the adjacent micromirrors during the scanning process performed by the DMD, causing the loss of optical information about the object. Here, a novel linear micromirror array (MMA) based on the microelectromechanical system process that rotates around one lateral axis of the micromirror is developed, which is helpful to simplify the optical system of HSI and obtain more optical information about the detected target. The MMA has 32 independent linear micromirrors across an aperture of 5mm×6.5mm, under which there are dimple structures and a common bottom electrode. Finally, the MMA with a 98.6% filling factor is successfully fabricated by employing the bulk micromachining process. The experimental results show that the maximum rotational angle is 5.1° at a direct current driving voltage of 30 V. The proposed micromirror array is promising to replace the DMD and shows potential as a spatial light modulator in the fields of hyperspectral imaging, optical communication, and so on.

Fresh Mushroom Preservation Techniques

The production and consumption of fresh mushrooms has experienced a significant increase in recent decades. This trend has been driven mainly by their nutritional value and by the presence of bioactive and nutraceutical components that are associated with health benefits, which has led some to consider them a functional food. Mushrooms represent an attractive food for vegetarian and vegan consumers due to their high contents of high-biological-value proteins and vitamin D. However, due to their high respiratory rate, high water content, and lack of a cuticular structure, mushrooms rapidly lose quality and have a short shelf life after harvest, which limits their commercialization in the fresh state. Several traditional preservation methods are used to maintain their quality and extend their shelf life. This article reviews some preservation methods that are commonly used to preserve fresh mushrooms and promising new preservation techniques, highlighting the use of new packaging systems and regulations aimed at the development of more sustainable packaging.

Artificial Intelligence Empowered Multispectral Vision Based System for Non-Contact Monitoring of Large Yellow Croaker (Larimichthys crocea) Fillets

A non-contact method was proposed to monitor the freshness (based on TVB-N and TBA values) of large yellow croaker fillets (Larimichthys crocea) by using a visible and near-infrared hyperspectral imaging system (400-1000 nm). In this work, the quantitative calibration models were built by using feed-forward neural networks (FNN) and partial least squares regression (PLSR). In addition, it was established that using a regression coefficient on the data can be further compressed by selecting optimal wavelengths (35 for TVB-N and 18 for TBA). The results validated that FNN has higher prediction accuracies than PLSR for both cases using full and selected reflectance spectra. Moreover, our FNN based model has showcased excellent performance even with selected reflectance spectra with rp = 0.978, R2p = 0.981, and RMSEP = 2.292 for TVB-N, and rp = 0.957, R2p = 0.916, and RMSEP = 0.341 for TBA, respectively. This optimal FNN model was then utilized for pixel-wise visualization maps of TVB-N and TBA contents in fillets.

Using near-infrared spectroscopy to determine intramuscular fat and fatty acids of beef applying different prediction approaches

This study aimed to predict fat and fatty acids (FA) contents in beef using near-infrared spectroscopy and prediction models based on partial least squares (PLS) and support vector machine regression in radial kernel (R-SVR). Fat and FA were assessed in 200 longissimus thoracis samples, and spectra were collected in reflectance mode from ground meat. The analyses were performed for PLS and R-SVR with and without wavelength selection based on genetic algorithms (GAs). The GA application improved the error prediction by 15% and 68% for PLS and R-SVR, respectively. Models based on GA plus R-SMV showed a prediction ability for fat and FA with an average coefficient of determination of 0.92 and ratio performance deviation of 4.8.

Evaluating drying feature differences between ginger slices and splits during microwave-vacuum drying by hyperspectral imaging technique

This study aimed to investigate the difference between ginger slices (vertically cut) and splits (horizontally cut) during microwave-vacuum drying (MVD) procedures. MVD ginger slices showed a higher shrinkage rate and a higher hardness value, with a more porous structure of the surface layer. MVD ginger splits had higher rehydration rates at the first 15 min of the rehydration. Nine optimal wavelengths were selected by regression coefficients (RC) from the partial least squares regression (PLSR) model based on the raw data. A simplified PLSR model based on optimal wavelengths showed a good performance with a coefficient of determination in prediction (Rp2) of 0.973 and a root mean square error in prediction (RMSEP) of 4.63%. Texture features of grey level co-occurrence matrix (GLCM) of moisture prediction maps demonstrated a more uniform moisture distribution in MVD ginger slices than that in splits in the original geometry.

Effects of tissue pre-degassing followed by ultrasound-assisted freezing on freezing efficiency and quality attributes of radishes

The rapid freezing technique for porous foods using tissue pre-degassing followed by ultrasound-assisted freezing (UF) was developed, and its effects on quality attributes of radishes including tissue air volume, hardness, total calcium contents, bonded calcium contents, retention rates of bonded calcium and microstructures were investigated. To evaluate the freezing efficiency, parameters including total freezing time, phase transition time, and the increases of freezing rate and phase transition rate were determined. Besides, multivariate statistical analyses including principal component analysis (PCA) and hierarchical cluster analysis (HCA) were performed to visualize and further analyze the quality differences of radishes under different treatments. Results suggested that decreasing tissue air volumes can significantly shorten the phase transition time of UF. Samples treated by pre-degassing for 5 min at -0.09 MPa followed by UF (D_-0.09MPa^5min-UF) showed the freezing rate and phase transition rate increased by 28.8% and 29.8%, respectively, as compared with the same pre-degassed samples frozen by immersion freezing (D_-0.09MPa^5min-IF). Retention rates of bonded calcium positively correlated with the sample hardness, announcing the importance of bonded calcium maintenance during radish freezing. Both PCA and HCA indicated that D_-0.09MPa^5min-UF endowed radishes with quality attributes more similar to the fresh ones, which was further verified by microstructure analysis, showing remarkably alleviated plasma membrane puncture, cell separation and deformation in D_-0.09MPa^5min-UF samples. The current study proved that the technique of tissue pre-degassing followed by UF could effectively improve the freezing efficiency and quality attributes of frozen radishes, and thus have great potentials in rapid freezing of porous foods.

Diagnosis of the Severity of Fusarium Head Blight of Wheat Ears on the Basis of Image and Spectral Feature Fusion

Fusarium head blight (FHB), one of the most prevalent and damaging infection diseases of wheat, affects quality and safety of associated food. In this study, to realize the early accurate monitoring of FHB, a diagnostic model of disease severity was proposed based on the fusion features of image and spectral features. First, the hyperspectral image of FHB infected in the range of the 400-1000 nm spectrum was collected, and the color parameters of wheat ear and spot region were segmented based on image features. Twelve sensitive bands were extracted using the successive projection algorithm, gray-scale co-occurrence matrix, and RGB color model. Four texture features were extracted from each feature band image as texture variables, and nine color feature variables were extracted from R, G, and B component images. Texture features with high correlation and color features were selected to participate in the final model building parameters via correlation analysis. Finally, the particle swarm optimization support vector machine (PSO-SVM) algorithm was used to build the model based on the diagnosis model of disease severity of FHB with different combinations of characteristic variables. The experimental results showed that the PSO-SVM model based on spectral and color feature fusion was optimal. Moreover, the accuracy of the training and prediction set was 95% and 92%, respectively. The method based on fusion features of image and spectral features can accurately and effectively diagnose the severity of FHB, thereby providing a technical basis for the timely and effective control of FHB and precise application of a pesticide.

Prediction of monounsaturated and polyunsaturated fatty acids of various processed pork meats using improved hyperspectral imaging technique

Freezing, heating, and pickling are common processes for pork meats. Unsaturated fatty acids including monounsaturated fatty acids and polyunsaturated fatty acids are indispensable nutrition beneficial to human's health and growth. However, Unsaturated fatty acids are affected by processing methods. Hyperspectral imaging is a novel technique widely used for food quality and safety evaluation. In the current study, the contents of monounsaturated and polyunsaturated fatty acids were assessed by Hyperspectral imaging. Optimal wavelengths were selected by the regression coefficients curves of partial least squares regression models. The least-squares support vector machine models established achieved a better coefficient of determination in the Monte Carlo validation set than the partial least squares regression models developed and the R²_MV values for the least squares - support vector machine models based on selected optimal wavelengths were higher than 0.81. Finally, colour maps of the contents of monounsaturated and polyunsaturated fatty acids were developed.

Systematic discovery about NIR spectral assignment from chemical structural property to natural chemical compounds

Spectra-structure interrelationship is still the weakness of NIR spectral assignment. In this paper, a comprehensive investigation from chemical structural property to natural chemical compounds was carried out for NIR spectral assignment. Surprisingly, we discovered that NIR absorption frequency of the skeleton structure with sp² hybridization is higher than one with sp³ hybridization. Specifically, substituent was another vital factor to be explored, the first theory discovery demonstrated that the absorption intensity of methyl substituted benzene at 2330 nm has a linear relationship with the number of substituted methyl C-H. The greater the number of electrons given to the substituents, the larger the displacement distance of absorption bands is. In addition, the steric hindrance caused by the substituent could regularly reduce the intensity of NIR absorption bands. Furthermore, the characteristic bands and group attribution of 29 natural chemical compounds from 4 types have been systematic assigned. These meaningful discoveries provide guidance for NIR spectral assignment from chemical structural property to natural chemical compounds.

DMD-based hyperspectral imaging system with tunable spatial and spectral resolution

Pushbroom hyperspectral imaging (HSI) has been used in many areas from air to land. However, its inherent operational drawback of the bulky slit leads to a limited field of view (FOV) and high energy consumption. Accordingly, a new and versatile HSI system is proposed by employing a smart digital micromirror device (DMD) to replace the mechanical scanning component. Moreover, tunable spatial and spectral resolution is implemented through adjusting the on-chip scanning linewidth and adopting the pixel fusion method, respectively. Meanwhile, three scanning modes including rough scanning, fine scanning, and regional scanning are achieved. These multiple choices increase the system's flexibility, universality, and intelligence, which is attractive for practically different applications, especially for military and remote sensing fields in need of a large FOV, and medical and food fields in need of tunable resolution for various samples.

Optimal Wavelength Selection for Hyperspectral Imaging Evaluation on Vegetable Soybean Moisture Content during Drying

Hyperspectral imaging technology is a promising technique for nondestructive quality evaluation of dried products. In order to realize real-time, online inspection of quality of dried products, it is necessary to determine a few important wavelengths from hyperspectral images for developing a multispectral imaging system. This study presents a binary firework algorithm (BFWA) for selecting the optimal wavelengths from hyperspectral images for moisture evaluation of dried soybean. Hyperspectral images over the spectral region 400–1000 nm, were acquired for 270 dried soybean samples, and mean reflectance was calculated from hyperspectral images for each wavelength. After selecting 12 important wavelengths using BFWA, a moisture prediction model was developed using partial least squares regression (PLSR). The PLSR model with BFWA achieved a prediction accuracy of R p = 0.966 and R M S E P = 5.105 % , which is better than those of successive projections algorithm ( R p = 0.932 and R M S E P = 7.329 % ), and the uninformative viable elimination algorithm ( R p = 0.928 and R M S E P = 7.416 % ). The results obtained by BFWA were more stable, with a smaller standard deviation of R p and R M S E P than those of the genetic algorithm. The BFWA method provides an effective mean for optimal wavelength selection to predict the quality of soybeans during drying.

Nondestructive Identification of Salmon Adulteration with Water Based on Hyperspectral Data

For the identification of salmon adulteration with water injection, a nondestructive identification method based on hyperspectral images was proposed. The hyperspectral images of salmon fillets in visible and near-infrared ranges (390–1050 nm) were obtained with a system. The original hyperspectral data were processed through the principal-component analysis (PCA). According to the image quality and PCA parameters, a second principal-component (PC2) image was selected as the feature image, and the wavelengths corresponding to the local extremum values of feature image weighting coefficients were extracted as feature wavelengths, which were 454.9, 512.3, and 569.1 nm. On this basis, the color combined with spectra at feature wavelengths, texture combined with spectra at feature wavelengths, and color-texture combined with spectra at feature wavelengths were independently set as the input, for the modeling of salmon adulteration identification based on the self-organizing feature map (SOM) network. The distances between neighboring neurons and feature weights of the models were analyzed to realize the visualization of identification results. The results showed that the SOM-based model, with texture-color combined with fusion features of spectra at feature wavelengths as the input, was evaluated to possess the best performance and identification accuracy is as high as 96.7%.

Principles and recent applications of novel non-thermal processing technologies for the fish industry-a review

Thermal treatment is a traditional method for food processing, which can kill microorganisms but also lead to physicochemical and sensory quality damage, especially to temperature-sensitive foods. Nowadays consumers' increasing interest in microbial safety products with premium appearance, flavor, great nutritional value and extended shelf-life has promoted the development of emerging non-thermal food processing technologies as alternative or substitution to traditional thermal methods. Fish is an important and world-favored food but has a short shelf-life due to its extremely perishable characteristic, and the microbial spoilage and oxidative process happen rapidly just from the moment of capture, making it dependent heavily on post-harvest preservation. The applications of novel non-thermal food processing technologies, including high pressure processing (HPP), ultrasound (US), pulsed electric fields (PEF), pulsed light (PL), cold plasma (CP) and ozone can extend the shelf-life by microbial inactivation and also keep good sensory quality attributes of fish, which is of high interest for the fish industry. This review presents the principles, developments of emerging non-thermal food processing technologies, and also their applications in fish industry, with the main focus on microbial inactivation and sensory quality. The promising results showed great potential to keep microbial safety while maintaining organoleptic attributes of fish products. What's more, the strengths and weaknesses of these technologies are also discussed. The combination of different food processing technologies or with advanced packaging methods can improve antimicrobial efficacy while not significantly affect other quality properties under optimized treatment.

Evaluation of Fourier transform infrared spectroscopy and multispectral imaging as means of estimating the microbiological spoilage of farmed sea bream

The objective of the present study was the evaluation of Fourier transform infrared (FTIR) spectroscopy and multispectral imaging (MSI), in tandem with multivariate data analysis, as means of estimating the microbiological quality of sea bream. Farmed whole ungutted fish were stored aerobically at 0, 4 and 8 °C. At regular time intervals, fish samples (i.e. cut portions) were analysed microbiologically, while FTIR and MSI measurements also were acquired at both the skin and flesh sides of the samples. Partial least squares regression (PLSR) models were calibrated to provide quantitative estimations of the microbiological status of fish based on spectral data, in a temperature-independent manner. The PLSR model based on the FTIR data of fish skin exhibited good performance when externally validated, with the coefficient of determination (R²) and the root mean square error (RMSE) being 0.727 and 0.717, respectively. Hence, FTIR spectroscopy appears to be promising for the rapid and non-invasive monitoring of the microbiological spoilage of whole sea bream. Contrarily, the MSI models' performance was unsatisfactory, delimitating their potential exploitation in whole fish quality assessment. Model optimization results concerning fish flesh indicated that MSI may be propitious in skinned fish products, with its definite competence warranting further investigation.

Developments of mathematical models for simulating vacuum cooling processes for food products - a review

Vacuum cooling is a rapid cooling method widely used in cooling some food products. Simulating the vacuum cooling process with mathematical models helps to acquire a more intuitive understanding and optimize the whole cooling process. However, there is no review summarizing the mathematical models of vacuum cooling. In this review, heat and mass transfer process during vacuum cooling, types of mathematical models for vacuum cooling, and numerical methods including finite difference method, finite element method and finite volume method used for process simulation are introduced in details. The food products used in numerical simulation study of vacuum cooling generally include liquid food, vegetables and cooked meat. The ranges of application of various numerical methods are also discussed. Moreover, heat and mass transfer coefficients have a great influence on the accuracy of the model, and are generally provided by the literature. The investigations presented in this review invariably demonstrate that mathematical modeling can provide good prediction of key information of vacuum cooling process, and has a great potential to improve vacuum cooling process in the food industry. However, more efforts are still needed to realize the industrial translation of laboratory results.

Synthesis and antimicrobial activities of novel sorbic and benzoic acid amide derivatives

A series of sorbic and benzoic acid amide derivatives were synthesized by conjugating sorbic acid (SAAD, a₁-a₇) or benzoic acid (BAAD b₁-b₆) with amino acid esters and their antimicrobial activities were investigated against Escherichia coli, Bacillus subtilis and Staphylococcus aureus, mixed bacteria from rancid milk, Saccharomyces cerevisiae, and Aspergillus niger. The antimicrobial activity of sorbic acid amides was better than that of benzoic acid amides. The minimum inhibitory concentrations (MIC) of compound isopropyl N-[1-oxo-2, 4-hexadien-1-yl]-L-phenylalaninate (a₇) were 0.17 mM against B. subtilis, and 0.50 mM against S. aureus, while the MIC values of sorbic acid were more than 2 mM respectively. Also, compound a₇ displayed pH-independent antimicrobial activity in the range of pH 5.0-9.0 and was effective at pH 9.0. These results demonstrated that the conjugation of sorbic acid with amino acid esters led to significant improvement of in vitro antimicrobial attributes, but little effect was observed for benzoic acid amide derivatives.