Rapid and Nondestructive Quantification of Trimethylamine by FT-NIR Coupled with Chemometric Techniques

Application of colorimetric sensor array coupled with machine-learning approaches for the discrimination of grains based on freshness

BACKGROUND

Volatile organic compounds (VOCs) in grain fluctuate depending on the degree of grain freshness. A new colorimetric sensor array (CSA) was developed as capture probes for the quantification of VOCs in grains in this work, and it was designed to monitor the variation of grain VOCs. CSA spectral data acquisition using visible-near-infrared spectroscopy and image processing of CSA's image imformation by computer were used comparatively. Then, machine-learning-based models - for example, synergistic interval partial least squares, genetic algorithm, competitive adaptive reweighted sampling (CARS) algorithm, and ant colony optimization (ACO) algorithm - were introduced to optimize variables. Moreover, principal component analysis, and linear discriminant analysis (LDA), and K-nearest neighbors (KNN) were used for the classification. Ultimately, quantitative models for detecting grain freshness are developed using various variable selection strategies.

RESULTS

Compared with the pattern recognition results of image processing, visible-near-infrared spectroscopy could better separate the grains with different freshness from principal component analysis, and the prediction set of LDA models could correctly identify 100% of rice, 96.88% of paddy, and 97.9% of soybeans. In addition, compared with CARS and ACO, the LDA model and KNN model based on genetic algorithms show the best prediction performance. The prediction set could correctly identify 100% of rice and paddy samples and 95.83% of soybean samples.

CONCLUSION

The method developed could be used for non-destructive detection of grain freshness. © 2023 Society of Chemical Industry.

Rapid and non-destructive freshness evaluation of squid by FTIR coupled with chemometric techniques

BACKGROUND

Freshness is an important quality of squid with respect to determining the market price. The methods of evaluation of freshness fail to be widely used as a result of the lack of rapidity and quantitation. In the present study, a rapid and non-destructive quantification of squid freshness by Fourier transform infrared spectroscopy (FTIR) spectra combined with chemometric techniques was performed.

RESULTS

The relatively linear content change of trimethylamine (TMA-N) and dimethylamine (DMA-N) of squid during storage at 4 °C indicated their feasibility as a freshness indicator, as also confirmed by sensory evaluation. The spectral changes were mainly caused by the degradation of proteins and the production of amines by two-dimensional infrared correlation spectroscopy, among which TMA-N, DMA-N and putrescine were the main amines. The successive projections algorithm (SPA) was employed to select the sensitive wavenumbers to freshness for modeling prediction including partial least-squares regression, support vector regression (SVR) and back-propagation artificial neural network. Generally, the SPA-SVR model of the selected characteristic wavenumber showed a higher prediction accuracy for DMA-N (R² _P  = 0.951; RMSE_P  = 0.218), whereas both SPA-SVR (R² _P  = 0.929; RMSE_P  = 2.602) and Full-SVR (R² _P  = 0.941; RMSE_P  = 2.492) models had a higher predictive ability of TMA-N.

CONCLUSION

The results of the present study demonstrate that FTIR spectroscopy coupled with multivariate calibration shows significant potential for the prediction of freshness in squid. © 2021 Society of Chemical Industry.

Freshness Identification of Oysters Based on Colorimetric Sensor Array Combined with Image Processing and Visible Near-Infrared Spectroscopy

Volatile organic compounds (VOCs) could be used as an indicator of the freshness of oysters. However, traditional characterization methods for VOCs have some disadvantages, such as having a high instrument cost, cumbersome pretreatment, and being time consuming. In this work, a fast and non-destructive method based on colorimetric sensor array (CSA) and visible near-infrared spectroscopy (VNIRS) was established to identify the freshness of oysters. Firstly, four color-sensitive dyes, which were sensitive to VOCs of oysters, were selected, and they were printed on a silica gel plate to obtain a CSA. Secondly, a charge coupled device (CCD) camera was used to obtain the “before” and “after” image of CSA. Thirdly, VNIS system obtained the reflected spectrum data of the CSA, which can not only obtain the color change information before and after the reaction of the CSA with the VOCs of oysters, but also reflect the changes in the internal structure of color-sensitive materials after the reaction of oysters’ VOCs. The pattern recognition results of VNIS data showed that the fresh oysters and stale oysters could be separated directly from the principal component analysis (PCA) score plot, and linear discriminant analysis (LDA) model based on variables selection methods could obtain a good performance for the freshness detection of oysters, and the recognition rate of the calibration set was 100%, while the recognition rate of the prediction set was 97.22%. The result demonstrated that the CSA, combined with VNIRS, showed great potential for VOCS measurement, and this research result provided a fast and nondestructive identification method for the freshness identification of oysters.

Determination of acid value during edible oil storage using a portable NIR spectroscopy system combined with variable selection algorithms based on an MPA-based strategy

BACKGROUND

The acid value is an important indicator for evaluating the quality of edible oil during storage. This study employs a portable near-infrared (NIR) spectroscopy system to determine the acid value during edible oil storage. Four MPA-based variable selection methods, namely competitive adaptive reweighted sampling (CARS), the variable iterative space shrinkage approach (VISSA), iteratively variable subset optimization (IVSO), and bootstrapping soft shrinkage (BOSS) were introduced to optimize the preprocessed NIR spectra. Support vector machine (SVM) models based on characteristic spectra obtained by different selection methods were then established to achieve quantitative detection of the acid value during edible oil storage.

RESULTS

The results revealed that, compared with the full-spectrum SVM model, the SVM models established by the characteristic wavelengths optimized by the variable selection methods based on the MPA strategy exhibit a significant improvement in complexity and generalization performance. Furthermore, compared with the CARS, VISSA, and IVSO methods, the BOSS method obtained the least number of characteristic wavelength variables, and the SVM model established based on the optimized features of this method exhibited the optimal prediction performance. The root mean square error of prediction (RMSEP) was 0.11 mg g-1, the coefficient of determination (Rp2) was 0.92 and the ratio performance deviation (RPD) was 2.82, respectively.

CONCLUSION

The overall results indicate that the variable selection methods based on the MPA strategy can select more targeted characteristic variables. This has good application prospects in NIR spectra feature optimization. © 2020 Society of Chemical Industry.

Determination of Fatty Acid Content of Rice during Storage Based on Feature Fusion of Olfactory Visualization Sensor Data and Near-Infrared Spectra

This study innovatively proposes a feature fusion technique to determine fatty acid content during rice storage. Firstly, a self-developed olfactory visualization sensor was used to capture the odor information of rice samples at different storage periods and a portable spectroscopy system was employed to collect the near-infrared (NIR) spectra during rice storage. Then, principal component analysis (PCA) was performed on the pre-processed olfactory visualization sensor data and the NIR spectra, and the number of the best principal components (PCs) based on the single technique model was optimized during the backpropagation neural network (BPNN) modeling. Finally, the optimal PCs were fused at the feature level, and a BPNN detection model based on the fusion feature was established to achieve rapid measurement of fatty acid content during rice storage. The experimental results showed that the best BPNN model based on the fusion feature had a good predictive performance where the correlation coefficient (R_P) was 0.9265, and the root mean square error (RMSEP) was 1.1005 mg/100 g. The overall results demonstrate that the detection accuracy and generalization performance of the feature fusion model are an improvement on the single-technique data model; and the results of this study can provide a new technical method for high-precision monitoring of grain storage quality.

Histamine Control in Raw and Processed Tuna: A Rapid Tool Based on NIR Spectroscopy

The present study was designed to investigate whether near infrared (NIR) spectroscopy with minimal sample processing could be a suitable technique to rapidly measure histamine levels in raw and processed tuna fish. Calibration models based on orthogonal partial least square regression (OPLSR) were built to predict histamine in the range 10–1000 mg kg⁻¹ using the 1000–2500 nm NIR spectra of artificially-contaminated fish. The two models were then validated using a new set of naturally contaminated samples in which histamine content was determined by conventional high-performance liquid chromatography (HPLC) analysis. As for calibration results, coefficient of determination (r²) > 0.98, root mean square of estimation (RMSEE) ≤ 5 mg kg⁻¹ and root mean square of cross-validation (RMSECV) ≤ 6 mg kg⁻¹ were achieved. Both models were optimal also in the validation stage, showing r² values > 0.97, root mean square errors of prediction (RMSEP) ≤ 10 mg kg⁻¹ and relative range error (RER) ≥ 25, with better results showed by the model for processed fish. The promising results achieved suggest NIR spectroscopy as an implemental analytical solution in fish industries and markets to effectively determine histamine amounts.

Sensing Technology for Fish Freshness and Safety: A Review

Standard analytical methods for fish freshness assessment are based on the measurement of chemical and physical attributes related to fish appearance, color, meat elasticity or texture, odor, and taste. These methods have plenty of disadvantages, such as being destructive, expensive, and time consuming. All these techniques require highly skilled operators. In the last decade, rapid advances in the development of novel techniques for evaluating food quality attributes have led to the development of non-invasive and non-destructive instrumental techniques, such as biosensors, e-sensors, and spectroscopic methods. The available scientific reports demonstrate that all these new techniques provide a great deal of information with only one test, making them suitable for on-line and/or at-line process control. Moreover, these techniques often require little or no sample preparation and allow sample destruction to be avoided.

Dynamic monitoring of fatty acid value in rice storage based on a portable near-infrared spectroscopy system

The fatty acid value of rice is one of the important indexes to reflect its freshness. A portable near-infrared spectroscopy (NIRS) system was designed and assembled to dynamically monitor fatty acid values in rice storage in this study. First, the near-infrared (NIR) spectra of rice samples in different storage periods were obtained using the portable NIRS system. Then, a weighted multiplicative scatter correction with variable selection (WMSCVS) algorithm was applied to the original spectra for scattering correction, and to compress variable space for achieving characteristic wavelengths. Finally, a partial least square (PLS) regression model was established using the characteristic wavelengths to realize the rapid monitoring of fatty acid values in rice storage. The results showed that the performance of the optimal PLS model based on the features by the WMSCVS algorithm was significantly better than those of the optimal PLS models based on SNV and MSC pre-processing spectra, with the determination coefficient (R_P²) of 0.9615 and the root mean square error of prediction (RMSEP) of 0.3626 in the predictive process. The overall results demonstrate that it is feasible to use the portable NIRS system developed by our team to quickly monitor the fatty acid values in rice storage.

Rapid measurement of fatty acid content during flour storage using a color-sensitive gas sensor array: Comparing the effects of swarm intelligence optimization algorithms on sensor features

The fatty acid content of flour is an important indicator for determining the deterioration of flour. We propose a novel rapid measurement method for fatty acid content during flour storage based on a self-designed color-sensitive gas sensor array. First, a color-sensitive gas sensor array was prepared to capture the odor changes during flour storage. The sensor features were then optimized using genetic algorithm (GA), ant colony optimization (ACO) and particle swarm optimization (PSO). Finally, back propagation neural network (BPNN) models were established to measure the fatty acid content during flour storage. Experimental results showed that the optimization effects of the three algorithms improved in the following order: GA < ACO < PSO, for the sensor features optimization. In the validation set, the determination coefficient of the best PSO-BPNN model was 0.9837. The overall results demonstrate that the models established on the optimized features can realize rapid measurements of fatty acid content during flour storage.

High-precision identification of the actual storage periods of edible oil by FT-NIR spectroscopy combined with chemometric methods

The actual storage period of edible oil is one of the important indicators of edible oil quality. A high-precision identification method based on the near-infrared (NIR) spectroscopy technique for the actual storage period of edible oil is proposed in this study. Firstly, a Fourier transform NIR (FT-NIR) spectrometer was used to collect NIR spectra of edible oil samples in different storage periods, and the obtained spectra were pretreated by standard normal transformation (SNV). Then, the characteristics of the pretreated spectra were analyzed by principal component analysis (PCA), and the spatial distribution of edible oil samples in different storage periods was visually presented using a PCA score plot. Finally, three pattern recognition methods, which were K-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM), were compared to establish a qualitative identification model of edible oil in different storage periods. The results showed that the recognition performance of the SVM model was significantly superior to that of the KNN and RF models, especially in terms of generalization performance, and the SVM model had a recognition rate of 100% when predicting independent samples in the prediction set. It is suggested that FT-NIR spectroscopy combined with appropriate chemometric methods is feasible to realize fast and high-precision identification of actual storage periods of edible oil and provided an effective analysis tool for edible oil storage quality detection.

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.