Use of spectroscopic data for automation in food processing industry

Nondestructive Detection of Codling Moth Infestation in Apples Using Pixel-Based NIR Hyperspectral Imaging with Machine Learning and Feature Selection

Codling moth (CM) (Cydia pomonella L.), a devastating pest, creates a serious issue for apple production and marketing in apple-producing countries. Therefore, effective nondestructive early detection of external and internal defects in CM-infested apples could remarkably prevent postharvest losses and improve the quality of the final product. In this study, near-infrared (NIR) hyperspectral reflectance imaging in the wavelength range of 900–1700 nm was applied to detect CM infestation at the pixel level for three organic apple cultivars, namely Gala, Fuji and Granny Smith. An effective region of interest (ROI) acquisition procedure along with different machine learning and data processing methods were used to build robust and high accuracy classification models. Optimal wavelength selection was implemented using sequential stepwise selection methods to build multispectral imaging models for fast and effective classification purposes. The results showed that the infested and healthy samples were classified at pixel level with up to 97.4% total accuracy for validation dataset using a gradient tree boosting (GTB) ensemble classifier, among others. The feature selection algorithm obtained a maximum accuracy of 91.6% with only 22 selected wavelengths. These findings indicate the high potential of NIR hyperspectral imaging (HSI) in detecting and classifying latent CM infestation in apples of different cultivars.

Fast and Green Method to Control Frauds of Geographical Origin in Traded Cuttlefish Using a Portable Infrared Reflective Instrument

An appropriate seafood origin identification is essential for labelling regulation but also economic and ecological issues. Near infrared (NIRS) reflectance spectroscopy was employed to assess the origins of cuttlefish caught from five fishing FAO areas (Adriatic Sea, northeastern and eastern central Atlantic Oceans, and eastern Indian and western central Pacific Oceans). A total of 727 cuttlefishes of the family Sepiidae (Sepia officinalis and Sepiella inermis) were collected with a portable spectrophotometer (902–1680 nm) in a wholesale fish plant. NIR spectra were treated with standard normal variate, detrending, smoothing, and second derivative before performing chemometric approaches. The random forest feature selection procedure was executed to select the most significative wavelengths. The geographical origin classification models were constructed on the most informative bands, applying support vector machine (SVM) and K nearest neighbors algorithms (KNN). The SVM showed the best performance of geographical classification through the hold-out validation according to the overall accuracy (0.92), balanced accuracy (from 0.83 to 1.00), sensitivity (from 0.67 to 1.00), and specificity (from 0.88 to 1.00). Thus, being one of the first studies on cuttlefish traceability using NIRS, the results suggest that this represents a rapid, green, and non-destructive method to support on-site, practical inspection to authenticate geographical origin and to contrast fraudulent activities of cuttlefish mislabeled as local.

Hyperspectral Imaging (HSI) Technology for the Non-Destructive Freshness Assessment of Pearl Gentian Grouper under Different Storage Conditions

This study used visible/near-infrared hyperspectral imaging (HSI) technology combined with chemometric methods to assess the freshness of pearl gentian grouper. The partial least square discrimination analysis (PLS-DA) and competitive adaptive reweighted sampling-PLS-DA (CARS-PLS-DA) models were used to classify fresh, refrigerated, and frozen–thawed fish. The PLS-DA model achieved better classification of fresh, refrigerated, and frozen–thawed fish with the accuracy of 100%, 96.43%, and 96.43%, respectively. Further, the PLS regression (PLSR) and CARS-PLS regression (CARS-PLSR) models were used to predict the storage time of fish under different storage conditions, and the prediction accuracy was assessed using the prediction correlation coefficients (R_p²), root mean squared error of prediction (RMSEP), and residual predictive deviation (RPD). For the prediction of storage time, the CARS-PLS model presented the better result of room temperature (R_p² = 0.948, RMSEP = 0.255, RPD = 4.380) and refrigeration (R_p² = 0.9319, RMSEP = 1.188, RPD = 3.857), while the better prediction of freeze was by obtained by the PLSR model (R_p² = 0.9250, RMSEP = 2.910, RPD = 3.469). Finally, the visualization of storage time based on the PLSR model under different storage conditions were realized. This study confirmed the potential of HSI as a rapid and non-invasive technique to identify fish freshness.

Determination of Adenosine and Cordycepin Concentrations in Cordyceps militaris Fruiting Bodies Using Near-Infrared Spectroscopy

Near-infrared (NIRS) spectroscopy, coupled with partial least squares regression, was used to predict adenosine and cordycepin concentrations in fruiting bodies of Cordyceps militaris. The fruiting body samples were prepared in four different sample formats, which were intact fruiting bodies, chopped fruiting bodies, dried powder, and dried crude extract. The actual amount of the adenosine and cordycepin concentrations in fresh fruiting bodies was analyzed by high-performance liquid chromatography. Results showed that the prediction models developed from the chopped samples provided excellent accuracy in both parameters with minimal sample preparation. These optimum models provided a coefficient of determination of prediction, standard error of prediction, bias, and residual predictive deviation, which were respectively 0.95, 16.60 mg kg^-1, -8.57 mg kg^-1, and 5.04 for adenosine prediction, and 0.98, 181.56 mg kg^-1, -1.05 mg kg^-1, and 8.9 for cordycepin prediction. The accuracy and performance of the model were determined by ISO12099:2017(E). It was found that these two equations can be considered to be acceptable at a probability level of 95% confidence. The NIRS technique, therefore, has the potential to be an objective method for determining the adenosine and cordycepin concentrations in C. militaris fruiting bodies.

Overview on Untargeted Methods to Combat Food Frauds: A Focus on Fishery Products

Authenticity and traceability of food products are of primary importance at all levels of the production process, from raw materials to finished products. Authentication is also a key aspect for accurate labeling of food, which is required to help consumers in selecting appropriate types of food products. With the aim of guaranteeing the authenticity of foods, various methodological approaches have been devised over the past years, mainly based on either targeted or untargeted analyses. In this review, a brief overview of current analytical methods tailored to authenticity studies, with special regard to fishery products, is provided. Focus is placed on untargeted methods that are attracting the interest of the analytical community thanks to their rapidity and high throughput; such methods enable a fast collection of “fingerprinting signals” referred to each authentic food, subsequently stored into large database for the construction of specific information repositories. In the present case, methods capable of detecting fish adulteration/substitution and involving sensory, physicochemical, DNA-based, chromatographic, and spectroscopic measurements, combined with chemometric tools, are illustrated and commented on.

Formulations for microprojection/microneedle vaccine delivery: Structure, strength and release profiles

To develop novel methods for vaccine delivery, the skin is viewed as a high potential target, due to the abundance of immune cells that reside therein. One method, the use of dissolving microneedle technologies, has the potential to achieve this, with a range of formulations now being employed. Within this paper we assemble a range of methods (including FT-FIR using synchrotron radiation, nanoindentation and skin delivery assays) to systematically examine the effect of key bulking agents/excipients - sugars/polyols - on the material form, structure, strength, failure properties, diffusion and dissolution for dissolving microdevices. We investigated concentrations of mannitol, sucrose, trehalose and sorbitol from 1:1 to 30:1 with carboxymethylcellulose (CMC), although mannitol did not form our micro-structures so was discounted early in the study. The other formulations showed a variety of crystalline (sorbitol) and amorphous (sucrose, trehalose) structures, when investigated using Fourier transform far infra-red (FT-FIR) with synchrotron radiation. The crystalline structures had a higher elastic modulus than the amorphous formulations (8-12GPa compared to 0.05-11GPa), with sorbitol formulations showing a bimodal distribution of results including both amorphous and crystalline behaviour. In skin, diffusion properties were similar among all formulations with dissolution occurring within 5s for our small projection array structures (~100μm in length). Overall, slight variations in formulation can significantly change the ability of our projections to perform their required function, making the choice of bulking/vaccine stabilising agents of great importance for these devices.

Using FT-NIR spectroscopy technique to determine arginine content in fermented Cordyceps sinensis mycelium

This research investigated the feasibility of using Fourier transform near-infrared (FT-NIR) spectral technique for determining arginine content in fermented Cordyceps sinensis (C. sinensis) mycelium. Three different models were carried out to predict the arginine content. Wavenumber selection methods such as competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA) were used to identify the most important wavenumbers and reduce the high dimensionality of the raw spectral data. Only a few wavenumbers were selected by CARS and CARS-SPA as the optimal wavenumbers, respectively. Among the prediction models, CARS-least squares-support vector machine (CARS-LS-SVM) model performed best with the highest values of the coefficient of determination of prediction (Rp(2)=0.8370) and residual predictive deviation (RPD=2.4741), the lowest value of root mean square error of prediction (RMSEP=0.0841). Moreover, the number of the input variables was forty-five, which only accounts for 2.04% of that of the full wavenumbers. The results showed that FT-NIR spectral technique has the potential to be an objective and non-destructive method to detect arginine content in fermented C. sinensis mycelium.

Discrimination of organic coffee via Fourier transform infrared-photoacoustic spectroscopy

BACKGROUND

Procedures for the evaluation of the origin and quality of ground and roasted coffee are constantly needed for the associated industry due to complexity of the related market. Conventional Fourier transform infrared (FTIR) spectroscopy can be used for detecting changes in functional groups of compounds, such as coffee. However, dispersion, reflection and non-homogeneity of the sample matrix can cause problems resulting in low spectral quality. On the other hand, sample preparation frequently takes place in a destructive way. To overcome these difficulties, in this work a photoacoustic cell has been adapted as a detector in a FTIR spectrophotometer to perform a study of roasted and ground coffee from three varieties of Coffea arabica grown by organic and conventional methods.

RESULTS

Comparison between spectra of coffee recorded by FTIR-photoacoustic spectrometry (PAS) and by FTIR spectrophotometry showed a better resolution of the former method, which, aided by principal components analysis, allowed the identification of some absorption bands that allow the discrimination between organic and conventional coffee.

CONCLUSION

The results obtained provide information about the spectral behavior of coffee powder which can be useful for establishing discrimination criteria. It has been demonstrated that FTIR-PAS can be a useful experimental tool for the characterization of coffee.