Assessing the temperature influence on the soluble solids content of watermelon juice as measured by visible and near-infrared spectroscopy and chemometrics

Non-destructive assessment of soluble solids content in kiwifruit using hyperspectral imaging coupled with feature engineering

The maturity of kiwifruit is widely gauged by its soluble solids content (SSC), with accurate assessment being essential to guarantee the fruit's quality. Hyperspectral imaging offers a non-destructive alternative to traditional destructive methods for SSC evaluation, though its efficacy is often hindered by the redundancy and external disturbances of spectral images. This study aims to enhance the accuracy of SSC predictions by employing feature engineering to meticulously select optimal spectral features and mitigate disturbance effects. We conducted a comprehensive investigation of four spectral pre-processing and nine spectral feature selection methods, as components of feature engineering, to determine their influence on the performance of a linear regression model based on ordinary least squares (OLS). Additionally, the stacking generalization technique was employed to amalgamate the strengths of the two most effective models derived from feature engineering. Our findings demonstrate a considerable improvement in SSC prediction accuracy post feature engineering. The most effective model, when considering both feature engineering and stacking generalization, achieved an R M S E p of 0.721, a M A P E p of 0.046, and an R P D p of 1.394 in the prediction set. The study confirms that feature engineering, especially the careful selection of spectral features, and the stacking generalization technique are instrumental in bolstering SSC prediction in kiwifruit. This advancement enhances the application of hyperspectral imaging for quality assessment, offering benefits that extend across the agricultural industry.

Improving the prediction performance of soluble solids content (SSC) in kiwifruit by means of near-infrared spectroscopy using slope/bias correction and calibration updating

Soluble solids content (SSC) is particularly important for kiwifruit, as it not only determines its flavor, but also helps assess its maturity. Visible/near-infrared (Vis/NIR) spectroscopy has been widely used to evaluate the SSC of kiwifruit. Still, the local calibration models may be ineffective for new batches of samples with biological variability, which limits the commercial application of this technology. Thus, a calibration model was developed using one batch of fruit and the prediction performance was tested with a different batch, which differs in origin and harvest time. Four calibration models were established with Batch 1 kiwifruit to predict SSC, which were based on full spectra (i.e., partial least squares regression (PLSR) model based on full spectra), continuous effective wavelengths (i.e., changeable size moving window-PLSR (CSMW-PLSR) model), and discrete effective wavelengths (i.e., competitive adaptive reweighted sampling-PLSR (CARS-PLSR) model and PLSR-variable importance in projection (PLSR-VIP) model) respectively. The R_v² values of these four models in the internal validation set were 0.83, 0.92, 0.96, and 0.89, with corresponding RMSEV values of 1.08 %, 0.75 %, 0.56 %, and 0.89 %, and RPD_v values of 2.49, 3.61, 4.80, and 3.02, respectively. Clearly, all four PLSR models performed acceptably in the validation set. However, these models performed very poorly in predicting the Batch 2 samples, with their RMSEP values all exceeding 1.5 %. Although the models could not be used to predict exact SSC, they could still interpret the SSC values of Batch 2 kiwifruit to some extent because the predicted SSC values could fit a specific line. To enable the CSMW-PLSR calibration model to predict the SSC of Batch 2 kiwifruit, the robustness of this model was improved by calibration updating and slope/bias correction (SBC). Different numbers of new samples were randomly selected for updating and SBC, and the minimum number of samples for updating and SBC was finally determined to be 30 and 20, respectively. After calibration updating and SBC, the new models had average R_p², average RMSEP, and average RPD_p values of 0.83 and 0.89, 0.69 % and 0.57 %, and 2.45 and 2.97, respectively, in the prediction set. Overall, the methods proposed in this study can effectively address the issue of poor performance of calibration models in predicting new samples with biological variability and make the models more robust, thus providing important guidance for the maintenance of SSC online detection models in practical applications.

Rapid Assessment of Microbial Quality in Edible Seaweeds Using Sensor Techniques Based on Spectroscopy, Imaging Analysis and Sensors Mimicking Human Senses

The expansion of the seaweed aquaculture sector along with the rapid deterioration of these products escalates the importance of implementing rapid, real-time techniques for their quality assessment. Seaweed samples originating from Scotland and Ireland were stored under various temperature conditions for specific time intervals. Microbiological analysis was performed throughout storage to assess the total viable counts (TVC), while in parallel FT-IR spectroscopy, multispectral imaging (MSI) and electronic nose (e-nose) analyses were conducted. Machine learning models (partial least square regression (PLS-R)) were developed to assess any correlations between sensor and microbiological data. Microbial counts ranged from 1.8 to 9.5 log CFU/g, while the microbial growth rate was affected by origin, harvest year and storage temperature. The models developed using FT-IR data indicated a good prediction performance on the external test dataset. The model developed by combining data from both origins resulted in satisfactory prediction performance, exhibiting enhanced robustness from being origin unaware towards microbiological population prediction. The results of the model developed with the MSI data indicated a relatively good prediction performance on the external test dataset in spite of the high RMSE values, whereas while using e-nose data from both MI and SAMS, a poor prediction performance of the model was reported.

Multilevel LASSO-based NIR temperature-correction modeling for viscosity measurement of bisphenol-A

Temperature variation will affect the prediction accuracy when using the near-infrared (NIR) analytical model to measure the viscosity of bisphenol-A. In order to correct the effect of temperature on the prediction performance of NIR model, a multilevel least-absolute shrinkage and selection operator (LASSO) is proposed in this paper. The multilevel LASSO algorithm combines LASSO with the multilevel simultaneous component analysis (MLSCA) to enhance the robustness of the model under temperature changes and external disturbances. MLSCA is applied to decompose the molecular spectral data into two parts. One part denotes the property caused by temperature, the other means the changes of concentration. LASSO, a sparse regression model, is used to select the variables and perform the regularization to further enhance the robustness and interpretability of the model. Experimental results demonstrate the effectiveness of the proposed model in measuring bisphenol-A viscosity, which provides a more stable prediction result compared with the existing ones without temperature corrections.

Rapid detection of quality of Japanese fermented soy sauce using near-infrared spectroscopy

This study investigated the feasibility of rapidly evaluating the final quality of Japanese fermented soy sauce (shoyu) using NIR spectroscopy and partial least-squares (PLS) regression. In total, 110 shoyu samples that had been entered in the annual soy sauce competition from 2016 to 2018 were collected and analyzed. The transmittance spectra (400-1800 nm) and the transflectance spectra (680-2500 nm) of these samples were acquired and processed by different pre-treatments. PLS regression was applied to the raw and processed spectra to construct models based on a calibration set (76 shoyu samples from 2016 and 2017) and to evaluate these models using a validation set (34 shoyu samples from 2018), according to their values for bias and root mean square error of prediction (RMSEP). The results showed that the models constructed using the full spectra of transflectance performed better than those using transmittance spectra. Comparing the influence of different regions in the transflectance spectra enabled the accuracy of the models to be improved. The model constructed from transflectance spectra from the 1800 to 2500 nm region using pre-treatment of second derivative was superior to the other models, with a bias value of -2 and the lowest RMSEP value of 13 in the validation set. To further narrow the wavelength range, the models constructed using the spectral region from 2050 to 2400 nm also showed a better performance for predicting the sensory quality of soy sauce products. This study has demonstrated that the NIR spectroscopy technique could be used as an alternative routine quality control procedure, which can rapidly and economically classify the quality of soy sauce products.

A Comprehensive Comparative Study for the Authentication of the Kadsura Crude Drug

The stems and roots of Kadsura species have been used as the folk medicine in Traditional Chinese medicine (TCM) and have good traditional efficacy and medicinal application with a long history. Among these species, K. coccinea, K. heteroclita and K. longipedunculata are the most widely distributed species in the regions of south and southwest China. Owing to their similar appearance, the crude drugs are often confusedly used by some folk doctors, even some pharmaceutical factories. To discriminate the crude drugs, haplotype analysis based on cpDNA markers and ITS was firstly employed in this study. Generic delimitation, interspecific interrelationships, and the identification of medicinal materials between K. longipedunculata and K. heteroclita remained unresolved by the existing molecular fragments. The original plant could be identified through the morphological character of flower, fruit and leaf. However, in most situation collectors have no chance to find out these characters due to lack of reproductive organs, and have no experience with the minor difference and transitional variation of leaf morphology. The chemical characterization show that the chemometric of chemical composition owned higher resolution to discriminate three herbs of Kadsura species. In conclusion, this integrative approach involving molecular phylogeny, morphology and chemical characterization could be applied for authentication of the Kadusra. Our study suggests the use of this comprehensive approach for accurate characterization of this closely related taxa as well as identifying the source plant and confused herbs of TCM.

Probabilistic PCR based near-infrared modeling with temperature compensation

Considering that temperature makes a difference to near-infrared spectrum, a probabilistic principle component regression (PPCR) based temperature compensation modeling strategy is investigated under the framework of maximum likelihood estimation. First, a PPCR model is established to extract the dynamic information of the spectra at designated experimental temperature. Then, by decomposing the temperature-induced spectral variation into the shift in horizontal direction and the drift in vertical direction, the quantitative expression between spectral variation and temperature change is derived. Based on the decomposition, the estimation of new latent variables that vary with temperature is derived according to the spectral data set collected at certain temperatures. Finally, for performance evaluation, applications of the theoretical results to bisphenol-A and gasoline-ethanol mixture illustrate the effectiveness and advantages of the developed techniques.

Assessing the influence of temperature on NIRS prediction models for the determination of sodium content in dry-cured ham slices

Temperature fluctuations are a key factor in the development of prediction models using near infrared spectroscopy (NIRS). In the present study, this influence has been investigated and a methodology has been proposed to reduce the effect of sample temperature on NIRS model prediction of the sodium content in dry-cured ham slices. Spectra were taken directly from the slices using a remote measurement probe (for non-contact analysis) at three different temperature ranges: -12 °C to -5°C, -5°C to 10 °C and 10 °C to 20 °C. Local and global temperature compensation methods were established. Partial-least squares (PLS) regression was used as a chemometrics tool to perform the calibrations. The results showed that local models were sensitive to changes in temperature, while a global temperature model using sample spectra over the entire temperature range showed good prediction ability, reducing the error caused by temperature fluctuations to acceptable levels for practical applications.

Discrimination of Transgenic Rice containing the Cry1Ab Protein using Terahertz Spectroscopy and Chemometrics

Spectroscopic techniques combined with chemometrics methods have proven to be effective tools for the discrimination of objects with similar properties. In this work, terahertz time-domain spectroscopy (THz-TDS) combined with discriminate analysis (DA) and principal component analysis (PCA) with derivative pretreatments was performed to differentiate transgenic rice (Hua Hui 1, containing the Cry1Ab protein) from its parent (Ming Hui 63). Both rice samples and the Cry1Ab protein were ground and pressed into pellets for terahertz (THz) measurements. The resulting time-domain spectra were transformed into frequency-domain spectra, and then, the transmittances of the rice and Cry1Ab protein were calculated. By applying the first derivative of the THz spectra in conjunction with the DA model, the discrimination of transgenic from non-transgenic rice was possible with accuracies up to 89.4% and 85.0% for the calibration set and validation set, respectively. The results indicated that THz spectroscopic techniques and chemometrics methods could be new feasible ways to differentiate transgenic rice.