Monitoring of whey quality with NIR spectroscopy—A feasibility study

Identification of informative spectral ranges for predicting major chemical constituents in corn using NIR spectroscopy

Many studies have been conducted using NIR spectroscopy to predict corn constituents; however, a systematic investigation of the spectral sub-regions under the scope of overtones and combinations has not been performed. In this study, the corn spectra were divided into second overtones (1100-1388 nm), first overtones (1390-1852 nm), and combinations (1852-2498 nm). Then, using variable importance in projection and genetic algorithm, each region was inspected sequentially to identify the most informative sub-region for each attribute to improve interpretability. The identified spectral subsets were further tuned to select the most influential bands for each attribute. The sub-regions in combinations bands was most informative for predicting water (1908-2108 nm, 2 bands), oil (2176-2304 nm, 6 bands), and protein (2130-2190 nm, 3 bands), whereas the first overtones region was the best for predicting starch (1452-1770 nm, 5 bands). Results provided valuable information for potential hardware and software improvements.

NIR Spectroscopy Oranges Origin Identification Framework Based on Machine Learning

Research on the identification model of orange origin based on machine learning in Near infrared (NIR) spectroscopy. According to the characteristics of NIR spectral data, a complete general framework for origin identification is proposed. It includes steps such as data preprocessing, feature selection, model building and cross validation. Compare multiple preprocessing algorithms and multiple machine learning algorithms under the framework. Based on NIR spectroscopy to identify the origin of orange, a good identification result was obtained. Improve the accuracy of orange origin identification and obtained the best origin identification accuracy of 92.8%.

Role of Pascalization in Milk Processing and Preservation: A Potential Alternative towards Sustainable Food Processing

Renewed technology has created a demand for foods which are natural in taste, minimally processed, and safe for consumption. Although thermal processing, such as pasteurization and sterilization, effectively limits pathogenic bacteria, it alters the aroma, flavor, and structural properties of milk and milk products. Nonthermal technologies have been used as an alternative to traditional thermal processing technology and have the ability to provide safe and healthy dairy products without affecting their nutritional composition and organoleptic properties. Other than nonthermal technologies, infrared spectroscopy is a nondestructive technique and may also be used for predicting the shelf life and microbial loads in milk. This review explains the role of pascalization or nonthermal techniques such as high-pressure processing (HPP), pulsed electric field (PEF), ultrasound (US), ultraviolet (UV), cold plasma treatment, membrane filtration, micro fluidization, and infrared spectroscopy in milk processing and preservation.

Prediction of α-Lactalbumin and β-Lactoglobulin Composition of Aqueous Whey Solutions Using Fourier Transform Mid-Infrared Spectroscopy and Near-Infrared Spectroscopy

Characterization and quantification of individual whey proteins are of crucial importance to many industrial dairy processes. Labor intensive wet-chemical methods are still being used for this purpose, but a rapid quantification method for individual whey proteins is highly desired. This work investigate the utility of Fourier transform mid-infrared spectroscopy and Fourier transform near-infrared spectroscopy for rapid quantification of the two main whey proteins (β-lactoglobulin and α-lactalbumin) in complex aqueous whey solutions simulating production process streams. MIR and NIR spectra obtained on whey samples with known and varying amounts of the proteins of interest and are used to develop partial least squares prediction models. Selection of informative wavelength regions allowed for prediction of β-lactoglobulin and α-lactalbumin concentrations with very high precision and accuracy (root mean square error of cross-validation, or RMSECV, of 0.6% and R² of 0.99 for NIR), demonstrating the potential of being implemented for rapid in-line monitoring of protein composition in industrial whey streams. Two-dimensional MIR-NIR correlation spectroscopy is used to identify the most informative parts of the NIR spectra in relation to protein secondary structure. In addition multivariate curve resolution is applied to the MIR data to resolve mixture spectra and to elucidate the spectral ranges that were most useful in distinguishing between the two whey proteins. The study concludes that NIR spectroscopy has potential for accurate in-line protein quantification and overall secondary protein structure quantification which open new possibilities for in-line industrial applications.

Rapid spectral analysis of agro-products using an optimal strategy: dynamic backward interval PLS-competitive adaptive reweighted sampling

A novel strategy of variable selection approach named dynamic backward interval partial least squares-competitive adaptive reweighted sampling (DBiPLS-CARS) was proposed in this study. Near-infrared data sets of three different agro-products, namely corn, crop processing lamina, and plant leaf samples, were collected to investigate the performance of the proposed method. Weak relevant variables were first removed by DBiPLS and a refined selection of the remaining variables was then conducted by CARS. The Monte Carlo uninformative variable elimination (MCUVE) was used as a classical beforehand uninformative variable elimination method for comparison. Results showed that DBiPLS can select informative variables more continuously than MCUVE. Some synergistic variables which may be omitted by MCUVE can be retained by DBiPLS. By contrast, MCUVE can hardly avoid the disturbance of certain weak relevant variables as a result of its calculation based on the full spectrum regression. Therefore, DBiPLS exhibited the advantage of removing the weak relevant variables before CARS, and simultaneously improved the prediction performance of CARS.

Proximate composition determination in goat cheese whey by near infrared spectroscopy (NIRS)

BACKGROUND

In Brazil, over the last few years there has been an increase in the production and consumption of goat cheeses. In addition, there was also a demand to create options to use the whey extracted during the production of cheeses. Whey can be used as an ingredient in the development of many products. Therefore, knowing its composition is a matter of utmost importance, considering that the reference methods of food analysis require time, trained labor and expensive reagents for its execution.

METHODS

Goat whey samples produced in winter and summer were submitted to proximate composition analysis (moisture, total solids, ashes, proteins, fat and carbohydrates by difference) using reference methods and near infrared spectroscopy (NIRS). The spectral data was preprocessed by baseline correction and the Savitzky-Golay derivative. The models were built using Partial Least Square Regression (PLSR) with raw and preprocessed data for each dependent variable (proximate composition parameter).

RESULTS

The average whey composition values obtained using the referenced methods were in accordance with the consulted literature. The composition did not differ significantly (p > 0.05) between the summer and winter whey samples. The PLSR models were made available using the following figures of merit: coefficients of determination of the calibration and prediction models (R 2cal and R 2pred, respectively) and the Root Mean Squared Error Calibration and Prediction (RMSEC and RMSEP, respectively). The best models used raw data for fat and protein determinations and the values obtained by NIRS for both parameters were consistent with their referenced methods. Consequently, NIRS can be used to determine fat and protein in goat whey.

Near infra-red spectroscopy quantitative modelling of bivalve protein, lipid and glycogen composition using single-species versus multi-species calibration and validation sets

Near infrared spectroscopy (NIRS) quantitative modelling was used to measure the protein, lipid and glycogen composition of five marine bivalve species (Saccostrea glomerata, Ostrea angasi, Crassostrea gigas, Mytilus galloprovincialis and Anadara trapezia) from multiple locations and seasons. Predictive models were produced for each component using individual species and aggregated sample populations for the three oyster species (S. glomerata, O. angasi and C. gigas) and for all five bivalve species. Whole animal tissues were freeze dried, ground to >20μm and scanned by NIRS. Protein, lipid and glycogen composition were determined by traditional chemical analyses and calibration models developed to allow rapid NIRS-measurement of these components in the five bivalve species. Calibration modelling was performed using wavelet selection, genetic algorithms and partial least squares analysis. Model quality was assessed using RPIQ and RMESP. For protein composition, single species model results had RPIQ values between 2.4 and 3.5 and RMSEP between 8.6 and 18%, the three oyster model had an RPIQ of 2.6 and an RMSEP of 10.8% and the five bivalve species had an RPIQ of 3.6 and RMSEP of 8.7% respectively. For lipid composition, single species models achieved RPIQ values between 2.9 and 5.3 with RMSEP between 9.1 and 11.2%, the oyster model had an RPIQ of 3.6 and RMSEP of 6.8 and the five bivalve model had an RPIQ of 5.2 and RMSEP of 6.8% respectively. For glycogen composition, the single species models had RPIQs between 3.8 and 18.9 with RMSEP between 3.5 and 9.2%, the oyster model had an RPIQ of 5.5 and RMSEP of 7.1% and the five bivalve model had an RPIQ of 4 and RMSEP of 7.6% respectively. Comparison between individual species models and aggregated models for three oyster species and five bivalve species for each component indicate that aggregating data from like species produces high quality models with robust and reliable quantitative application. The benefit of aggregated multi-species models include a greater range of bivalve composition, greater application to different bivalve species and reduced need to extensively sample individual species, that is required for obtain robust single species NIRS models.