RESUMEN

Fourier transform infrared spectroscopy (FTIRS) can provide rich information on the composition and content of samples, enabling the detection of subtle changes in tissue composition and structure. This study represents the first application of FTIRS to investigate cartilage under microgravity. Simulated microgravity cartilage model was firstly established by tail-suspension (TS) for 7, 14 and 21 days, which would be compared to control samples. A self-developed hollow optical fiber attenuated total reflection (HOF-ATR) probe coupled with a FTIR spectrometer was used for the spectral acquisition of cartilage samples in situ, and one-way analysis of variance (ANOVA) was employed to analyze the changes in the contents of cartilage matrix at different stages. The results indicate that cartilage degenerates in microgravity, the collagen content gradually decreases with the TS time, and the structure of collagen fibers changes. The trends of proteoglycan content and collagen integrity show an initial decrease followed by an increase, ultimately significantly decreasing. The findings provide the basis for the cartilage degeneration in microgravity with TS time, which must be of real significance for space science and health detection.

Asunto(s)

RESUMEN

The near-infrared spectral data is highly high dimensional and contains redundant information, it is necessary to identify the most representative characteristic wavelengths before modeling to improve model accuracy and reliability. At present, there are many methods for selecting the characteristic wavelengths of NIR spectroscopy, but the collinearity among wavelengths is still a main issue that leads to poor model effects. Therefore, this study proposes a three-stage wavelength selection algorithm (Stage III) to reduce redundancy in NIR spectral data and collinearity between wavelength variables, resulting in a simpler and more accurate predictive model. The research uses a public NIR data set of corn samples as its subject. Initially, the wavelengths with the higher correlation coefficients are chosen after calculating the relationship coefficients between every wavelength vector and the concentration vector. On this basis, the correlation coefficients between the vectors of each wavelength point are calculated, and those wavelength points with smaller correlation coefficients with other wavelength points are selected. Ultimately, the stepwise regression analysis selects the wavelengths that provide substantial value to the model as the variables for modeling, leading to the development of a multiple linear regression model. The results show that the model using the three-stage wavelength selection algorithm outperforms those using the full spectrum, Stages I and Stage II, and the coefficient of determination of the test set of the Stage III-MLR model achieved an accuracy of 0.9360. Instead of the successive projections algorithm (SPA), uninformative variable elimination (UVE), and competitive adaptive reweighted sampling (CARS), Stage III is better in the model prediction accuracy. Therefore, the three-stage wavelength selection algorithm is an effective wavelength selection algorithm that can effectively model NIR spectroscopy, reduce the collinearity between the wavelength variables, simplify the complexity of the model, and improve the prediction precision of the model.

RESUMEN

Grape pomace (GP) and pecan shell (PS) are two by-products rich in phenolic compounds (PC), and dietary fiber (DF) that may be considered for the development of functional baked foods. In this study, four formulations with different GP:PS ratios (F1(8%:5%), F2(5%:5%), F3(5%:2%), F4(0%:5%), and control bread (CB)) were elaborated and characterized (physiochemical and phytochemical content). Also, their inner structure (SEM), changes in their FTIR functional group's vibrations, and the bioaccessibility of PC and sugars, including an in vitro glycemic index, were analyzed. Results showed that all GP:PS formulations had higher mineral, protein, DF (total, soluble, and insoluble), and PC content than CB. Additionally, PC and non-starch polysaccharides affected gluten and starch absorbance and pores distribution. In vitro digestion model showed a reduction in the glycemic index for all formulations, compared to CB. These findings highlight the possible health benefits of by-products and their interactions in baked goods.

Asunto(s)

RESUMEN

A rapid method was developed for determining the total flavonoid and protein content in Tartary buckwheat by employing near-infrared spectroscopy (NIRS) and various machine learning algorithms, including partial least squares regression (PLSR), support vector regression (SVR), and backpropagation neural network (BPNN). The RAW-SPA-CV-SVR model exhibited superior predictive accuracy for both Tartary and common buckwheat, with a high coefficient of determination (R2p = 0.9811) and a root mean squared error of prediction (RMSEP = 0.1071) for flavonoids, outperforming both PLSR and BPNN models. Additionally, the MMN-SPA-PSO-SVR model demonstrated exceptional performance in predicting protein content (R2p = 0.9247, RMSEP = 0.3906), enhancing the effectiveness of the MMN preprocessing technique for preserving the original data distribution. These findings indicate that the proposed methodology could efficiently assess buckwheat adulteration analysis. It can also provide new insights for the development of a promising method for quantifying food adulteration and controlling food quality.

Asunto(s)

RESUMEN

Two isostructural, three-dimensional, interpenetrated amino-functionalized Metal-Organic Frameworks (Co-2AIN-MOF and Cd-2AIN-MOF) based on 2-aminoisonicotinic acid (2AIN) were synthesized, structurally characterized and determined. Based on the PXRD analysis, the solvent exchange hardly changed their framework structure, and the samples fully activated by methanol can be achieved and examined by infrared spectroscopy. Due to the presence of the carbonyl group and free amino groups in the pore of the framework, the NH3 uptakes of Co-2AIN-MOF and Cd-2AIN-MOF are 11.70 and 13.81 mmol/g and at 1 bar, respectively. In-situ Infrared spectroscopy and DFT calculations revealed the different adsorption sites and processes between Co-2AIN-MOF and Cd-2AIN-MOF.

RESUMEN

Curcumae Radix (CR) is a widely used traditional Chinese medicine with significant pharmaceutical importance, including enhancing blood circulation and addressing blood stasis. This study aims to establish an integrated and rapid quality assessment method for CR from various botanical origins, based on chemical components, antiplatelet aggregation effects, and Fourier transform near-infrared (FT-NIR) spectroscopy combined with multivariate algorithms. Firstly, ultra-performance liquid chromatography-photodiode array (UPLC-PDA) combined with chemometric analyses was used to examine variations in the chemical profiles of CR. Secondly, the activation effect on blood circulation of CR was assessed using an in vitro antiplatelet aggregation assay. The studies revealed significant variations in chemical profiles and antiplatelet aggregation effects among CR samples from different botanical origins, with constituents such as germacrone, ß-elemene, bisdemethoxycurcumin, demethoxycurcumin, and curcumin showing a positive correlation with antiplatelet aggregation biopotency. Thirdly, FT-NIR spectroscopy was integrated with various machine learning algorithms, including Artificial Neural Network (ANN), K-Nearest Neighbors (KNN), Logistic Regression (LR), Support Vector Machine (SVM), and Subspace K-Nearest Neighbors (Subspace KNN), to classify CR samples from four distinct sources. The result showed that FT-NIR combined with KNN and SVM classification algorithms after SNV and MSC preprocessing successfully distinguished CR samples from four plant sources with an accuracy of 100%. Finally, Quantitative models for active constituents and antiplatelet aggregation bioactivity were developed by optimizing the partial least squares (PLS) model with interval combination optimization (ICO) and competitive adaptive reweighted sampling (CARS) techniques. The CARS-PLS model achieved the best predictive performance across all five components. The coefficient of determination (R2p) and root mean square error (RMSEP) in the independent test sets were 0.9708 and 0.2098, 0.8744 and 0.2065, 0.9511 and 0.0034, 0.9803 and 0.0066, 0.9567 and 0.0172 for germacrone, ß-elemene, bisdemethoxycurcumin, demethoxycurcumin and curcumin, respectively. The ICO-PLS model demonstrated superior predictive capabilities for antiplatelet aggregation biotency, achieving an R2p of 0.9010, and an RMSEP of 0.5370. This study provides a valuable reference for the quality evaluation of CR in a more rapid and comprehensive manner.

Asunto(s)

RESUMEN

Background Visual-motor illusion (VMI) is a cognitive approach used to evoke kinesthetic sensations. Research suggests that VMI can modulate brain activity depending on the specific joint movement observed. This study aimed to identify differences in brain activity when observing video images of joint movements at different intensities of movement in VMI. Methodology The study included 14 healthy adult participants. Two types of video images were used: pure ankle dorsiflexion movements (Standard-VMI) and ankle dorsiflexion movements with added resistance (Power-VMI). The brain activity measurement protocol employed a block design with one set of 15 seconds rest, 30 seconds VMI task, and 30 seconds follow-up. Each participant performed the VMI task twice, alternating between Standard-VMI and Power-VMI. Brain activity was measured using functional near-infrared spectroscopy, focusing on motor-related regions. Subjective impressions were assessed using visual analog scales (VAS) for kinesthetic illusions. Results The results revealed that Power-VMI stimulated significantly greater brain activity in the premotor and supplementary motor cortex, supramarginal gyrus, and superior parietal lobule compared with Standard-VMI. Power-VMI resulted in higher VAS values for kinesthetic illusion than Standard-VMI. Additionally, a positive correlation was observed between brain activity in the superior parietal lobule and the degree of kinesthetic illusion. Conclusions These findings indicate that Power-VMI enhances both motor-related brain areas and motor-sensory illusions, potentially having a greater impact on improving motor function. This study provides valuable insights for developing VMI interventions for rehabilitation, particularly for individuals with paralysis or movement impairments.

RESUMEN

Xixia amber from Henan Province in China has undergone a thorough examination utilizing microscopic observation, infrared spectroscopy, and three-dimensional (3D) fluorescence spectroscopy. This systematic analysis has revealed that there are primarily two varieties of Xixia amber: a light-colored type and a dark-colored type. These can be differentiated based on their coloration, infrared spectra, and distinctive fluorescence attributes. Notably, the infrared spectral profile of Xixia amber features a prominent peak at 1023 cm-1, accompanied by less pronounced peaks at 1088 and 974 cm-1. These spectral characteristics set it apart from amber originating from the Baltic regions, Myanmar, and Fushun. Further distinction is achieved through 3D fluorescence spectra, where Xixia amber exhibits similarities to Burmese and Fushun ambers. Chemical classification via pyrolysis gas chromatography-mass spectrometry (Py-GC-MS) identifies Xixia amber as belonging to Class Ib, characterized by its ordered structure and the absence of succinic acid. This comprehensive study delineates the coloration, infrared spectral properties, photoluminescent behavior, and chemical compositions of Xixia amber, clearly differentiating it from ambers sourced from other geographical locations.

RESUMEN

Forensic entomology plays an important role in medicolegal investigations by using insects, primarily flies, to estimate the time of colonization. This estimation relies on the development of the flies found at the (death) scene and can be affected (and sometimes corrected) by external factors, such as temperature and humidity, and internal factors, such as species and sex. This study leverages infrared (IR) spectroscopy combined with machine learning models-Partial Least Squares Discriminant Analysis (PLS-DA) and eXtreme Gradient Boosting trees Discriminant Analysis (XGBDA)-to differentiate between male and female Cochliomyia macellaria larvae, commonly found on human remains. Significant vibrational differences were detected in the infrared spectra of third instar C. macellaria larvae, with distinct peaks showing variations in relative absorbance between sexes, suggesting differences in biochemical compositions such as cuticular proteins and lipids. The application of PLS-DA and XGBDA yielded high classification accuracies of about 94% and 96%, respectively, with female spectra consistently having higher sensitivity than males. This non-destructive approach offers the potential to refine supplemental post-mortem interval estimations significantly, enhancing the accuracy of forensic analyses.

RESUMEN

OBJECTIVE: Semantic verbal fluency (SVF) engages cognitive functions such as executive function, mental flexibility, and semantic memory. Left frontal and temporal lobes, particularly the left inferior frontal gyrus (IFG), are crucial for SVF. This study investigates SVF and associated neural processing in older adults with mild SVF impairment and the relationship between structural abnormalities in the left IFG and functional activation during SVF in those individuals. METHODS: Fifty-four elderly individuals with modest level of mild cognitive impairment whose global cognition were preserved to normal but exhibited mild SVF impairment were participated. Prefrontal oxyhemoglobin (HbO2) activation and frontal cortical thickness were collected from the participants using functional near-infrared spectroscopy (fNIRS) and brain MRI, respectively. We calculated the ß coefficient of HbO2 activation induced by tasks, and performed correlation analysis between SVF induced HbO2 activation and cortical thickness in frontal areas. RESULTS: We observed increased prefrontal activation during SVF task compared to the resting and control task. The activation distinct to SVF was identified in the midline superior and left superior prefrontal regions (p<0.05). Correlation analysis revealed an inverse relationship between SVF-specific activation and cortical thickness in the left IFG, particularly in pars triangularis (r(54)=-0.304, p=0.025). CONCLUSION: The study contributes to understanding the relationship between reduced cortical thickness in left IFG and increased functional activity in cognitively normal individuals with mild SVF impairment, providing implications on potential compensatory mechanisms for cognitive preservation.

RESUMEN

Through numerical modeling, it has been determined that near infrared spectroscopy with a frequency domain approach can detect neurovascular structures with diameters from 0.5 mm at source-detector distances of 5-8 mm, depending on optical parameters and technical implementation of the method. Among the five classical machine learning methods considered, quadratic discriminant analysis is the most effective for detection. Furthermore, it has been demonstrated that the use of a photomultiplier tube and the registration of both amplitude and phase signal components exhibit the highest sensitivity. Spectroscopy can rival modern ultrasound for detecting arterial vessels. A cross-shaped probe configuration improves sensitivity, and the ratio of reduced scattering coefficient values at different wavelengths is informative for blood-filled vessel detection. These findings are consistent with and significantly extend previous experimental in vivo and in situ studies and could be valuable for intraoperative diagnostic tasks, particularly in neurosurgery.

RESUMEN

OBJECTIVE: We examined whether brain hemodynamic responses, gait, and cognitive performances under single- and dual-task conditions predict falls during longitudinal follow-up in older adults with multiple sclerosis (OAMS) with relapsing-remitting and progressive subtypes. METHODS: Participants with relapsing-remitting (n = 53, mean age = 65.02 ± 4.17 years, %female = 75.5) and progressive (n = 28, mean age = 64.64 ± 4.31 years, %female = 50) multiple sclerosis (MS) subtypes completed a dual-task-walking paradigm and reported falls during longitudinal follow-up using a monthly structured telephone interview. We used functional near-infrared spectroscopy (fNIRS) to assess oxygenated hemoglobin (HbO) in the prefrontal cortex during active walking and while performing a cognitive test under single- and dual-task conditions. RESULTS: Adjusted general estimating equations models indicated that higher HbO under dual-task walking was significantly associated with a reduction in the odds of reporting falls among participants with relapsing-remitting (odds ratio (OR) = 0.472, p = 0.004, 95% confidence interval (CI) = 0.284-0.785), but not progressive (OR = 1.056, p = 0.792, 95% CI = 0.703-1.588) MS. In contrast, faster stride velocity under dual-task walking was significantly associated with a reduction in the odds of reporting falls among progressive (OR = 0.658, p = 0.004, 95% CI = 0.495-0.874), but not relapsing-remitting (OR = 0.998, p = 0.995, 95% CI = 0.523-1.905) MS. CONCLUSION: Findings suggest that higher prefrontal cortex activation levels during dual-task walking, which may represent compensatory reallocation of brain resources, provide protection against falls for OAMS with relapsing-remitting subtype.

RESUMEN

The interlayer electronic coupling is responsible for the electronic structure evolution from monolayer graphene to graphite and for the moiré potential in twisted bilayer graphene. Here we demonstrate that the interlayer transfer integral (hopping parameter) increases nearly 40% with a quite moderate pressure of ∼3.5 GPa, manifested by the resonance peak shift in the infrared spectra of all 2-10 L graphene. A simple model based on the Morse potential enabled us to establish the relationship between the transfer integral and pressure. Our work provides fundamental insights into the dependence of the electronic coupling on the interlayer distance.

RESUMEN

Introduction: Perturbation walking (PW) has been shown to improve gait, however its effect on the cortical control of gait might provide insights on neural mechanisms underlying falls in adults with osteoarthritis. The objective of this study is to investigate the effect of PW on prefrontal cortical (PFC) activation in older women with (OA) and without osteoarthritis (HOA). We hypothesized that there would be an increase in PFC activation during PW relative to comfortable walking (CW) and higher increase in PFC activation during PW in HOA compared to OA. Methods: Twenty community-dwelling older women (66.7 ± 5.41 years old) walked on an instrumented treadmill that provided perturbations at pseudo-random intervals between 5-25 s using a counterbalanced design. Functional Near Infrared Spectroscopy was used to quantify PFC oxygenated hemoglobin (HbO2) and deoxyhemoglobin (Hb) levels, while standing prior to the task as a baseline. A linear mixed effects model was conducted to investigate the effects of cohort (HOA vs OA), task (PW vs CW), and their interaction on HbO2 (µM) and Hb (µM) levels. Results: HbO2 and Hb levels differed significantly between CW and PW tasks for both cohorts (P < 0.001) and demonstrated significant task by cohort interaction (P < 0.05). In addition, we found changes in walking performance (stride time, stride length, stride width and stance time) during and after PW. Spearman correlation demonstrated a strong association between increased stance time, increased body mass index and decreased PFC activation during PW. No other significant results were found. Discussion: This study found increase in PFC activation during PW and gait adaptation after a short bout of PW in HOA and OA. This increase in PFC activation was higher in HOA compared to OA, particularly during PW tasks, and was consistent with theory of limitations in mobility affecting neural activation in older adults. Further work remains to examine how pain, obesity, and mobility impacts cortical control in older adults with and without osteoarthritis.

RESUMEN

The nitrogen content of apple leaves and jujube leaves is an important index to judge the growth and development of apple trees and jujube trees to a certain extent. The prediction performance of the two samples was compared between different models for leaf nitrogen content, respectively. The near-infrared absorption spectra of 287 apple leaf samples and 192 jujube leaf samples were collected. After eliminating the outliers by Mahalanobis distance method, the remaining spectral data were processed by six different preprocessing methods. BP neural network (BP), random forest regression (RF), least partial squares (PLS), K-Nearest Neighbor (KNN), and support vector regression (SVR) were compared to establish prediction models of nitrogen content in apple leaves and jujube leaves. The results showed that the determination coefficient (R2), root mean square error (RMSE) and residual prediction deviation (RPD) of the models established by different combined pretreatment methods were compared among the five methods. Compared with the performance of the other four models, the modeling method of SG + SD + CARS + RF was suitable for the prediction of nitrogen content in apple leaves, and its modeling set R2 was 0.85408, RMSE was 0.082188, and RPD was 2.5864. The validation set R2 is 0.75527, RMSE is 0.099028, RPD is 2.1956. The modeling method of FD + CARS + PLS was suitable for the prediction of nitrogen content in jujube leaves. The modeling set R2 was 0.7954, RMSE was 0.14558, and RPD was 2.4264; the validation set R2 is 0.81348, RMSE is 0.089217, and RPD is 2.4552.In the prediction modeling of apple leaf nitrogen content in the characteristic band, the model quality of RF was better than the other four prediction models. The model quality of PLS in predictive modeling of nitrogen content of jujube leaves in characteristic bands is superior to the other four predictive models, These results provide a reference for the use of near-infrared spectroscopy to determine whether apple trees and jujube trees are deficient in nutrients.

Asunto(s)

RESUMEN

PURPOSE: The end-test torque (ETT) during intermittent maximal effort contractions reflects the highest contraction intensity at which a muscle metabolic steady-state can be attained. This study determined if ETT is the highest intensity at which the contraction phase of intermittent exercise does not limit the matching of microvascular oxygen delivery to muscle oxygen demand. METHODS: Microvascular oxygenation characteristics of the biceps brachii muscle were measured in sixteen young, healthy individuals (8M/8F, 22 ± 3 years, 80.9 ± 20.3 kg) by near-infrared spectroscopy during maximal effort elbow flexion under control conditions (CON) and with complete circulatory occlusion (OCC). RESULTS: Increases in total-[heme] were blunted during OCC compared to CON (225 ± 87 vs. 264 ± 88 µM, p < 0.001) but OCC did not elicit a compensatory increase in deoxygenated-[heme] at any timepoint (108 ± 62 vs. 101 ± 61 µM, p > 0.05). Deoxygenated-[heme] was significantly elevated during contraction, relative to relaxation, above ETT (107 ± 60 vs. 98.8 ± 60.5 µM, p < 0.001), but not at ETT (91.7 ± 54.1 vs. 98.4 ± 62.2 µM, p = 0.174). Total-[heme] was significantly reduced during contraction, relative to relaxation, at all contraction intensities during CON (p < 0.05) and OCC (p < 0.05). CONCLUSION: These data suggest that ETT may reflect the highest contraction intensity at which contraction-induced increases in intramuscular pressures do not limit muscle perfusion to a degree that requires further increases in fractional oxygen extraction (i.e., deoxygenated-[heme]) despite limited microvascular diffusive conductance (i.e., total-[heme]).

RESUMEN

INTRODUCTION: Cannabis sativa L. inflorescences are rich in cannabinoids and terpenes. Traditional chemical analysis methods for cannabinoids and terpenes, such as liquid and gas chromatography (using UV or MS detectors), are expensive and time-consuming. OBJECTIVES: This study explores the use of Fourier transform near-infrared (FT-NIR) spectroscopy combined with chemometric approaches for classifying cannabis chemovars and predicting cannabinoid and terpene concentrations for the first time in freshly harvested (wet) cannabis inflorescence. The study also compares the performance of FT-NIR spectroscopy on wet versus dry cannabis inflorescences. MATERIALS AND METHODS: Spectral data from 187 samples across seven cannabis chemovars were analyzed using partial least squares-discriminant analysis (PLS-DA) and partial least squares-regression (PLS-R) models. RESULTS: The PLS-DA models effectively classified chemovars and major classes using only two latent variables (LVs) with minimal overfitting risk, with sensitivity, specificity, and accuracy values approaching 1. Despite the high water content in wet cannabis inflorescence, the PLS-R models demonstrated good to excellent predictive capabilities for nine cannabinoids and eight terpenes using FT-NIR spectra for the first time, achieving cross-validation and prediction R-squared values greater than 0.7, ratio of performance to interquartile range (RPIQ) exceeding 2, and a RMSECV/RMSEC ratio below 1.24. However, the low-cannabidiolic acid submodel and (-)-Δ9-trans-tetrahydrocannabinol model showed poor predictive performance. Some cannabinoid and terpene prediction models in wet cannabis inflorescence exhibited lower predictive capabilities compared with previously published models for dry cannabis inflorescence. CONCLUSIONS: These findings suggest that FT-NIR spectroscopy can be a viable rapid on-site analytical tool for growers during the inflorescence flowering stage.

RESUMEN

Global outcomes have been reported to be associated with cerebrovascular reactivity (CVR) in the acute phase following moderate and severe traumatic brain injury (TBI). The association of CVR in the acute and chronic phase of injury with patient-reported health-related quality of life metrics (HRQOL) metrics has never been explored. The aim of this study is to examine the association of CVR, as measured by the cerebral oxygen indices (COx and COx_a), in the acute and chronic phase following moderate and severe TBI, with patient reported HRQOL. In this prospective cohort study, performed in a Canadian quaternary care center, the association between continuous acute and chronic phase CVR with patient reported HRQOL outcomes following moderate and severe TBI was examined. The main outcomes of interest of this study were validated measures of patient-reported HRQOL over various domains as measured by both the 12-Item Short-Form Health Survey (SF-12) and a Quality of Life after Brain Injury (QOLIBRI) questionnaire. In the 29 subjects of this cohort, acute phase CVR was found to be significantly more active in those with a favorable Mental Component Summary (MCS) scores of the SF-12 at early follow-up when measured by COx (-0.015 [IQR: -0.067 to 0.032] vs 0.040 [IQR: 0.019 to 0.137] for Favorable first MCS vs Unfavorable respectively; Mann-Whitney U test p-value = 0.046) and COx_a (0.038 [IQR: 0.009 to 0.062] vs 0.112 [IQR: 0.065 to 0.167] for Favorable first MCS vs Unfavorable respectively; Mann-Whitney U test p-value = 0.014). Further, multivariable logistic regression analysis found acute phase COx and COx_a to improve model performance when predicting favorable versus unfavorable early MCS scores over established parameters such as age and measures of injury severity. Associations between outcomes and chronic phase CVR were limited, potentially due to short recording periods. This is the first ever pilot study to identify a relationship between acute phase CVR following moderate-to-severe TBI with mental and cognitive outcomes as experienced by patients. Given the small cohort, these findings will need to be confirmed in a larger multicenter study. This highlights the need for additional examination of the role dysfunctional CVR may play in mental and cognitive outcomes, as well as patient-reported outcomes more generally following TBI.

Asunto(s)

RESUMEN

Near-infrared (NIR) spectroscopy has been widely utilized to predict multi-constituents of corn in agriculture. However, directly extracting constituent information from the NIR spectra is challenging due to many issues such as broad absorption band, overlapping and non-specific nature. To solve these problems and extract implicit features from the raw data of NIR spectra to improve performance of quantitative models, a one-dimensional shallow convolutional neural network (CNN) model based on an eXtreme Gradient Boosting (XGBoost) feature extraction method was proposed in this paper. The leaf node feature information in the XGBoost was encoded and reconstructed to obtain the implicit features of raw data in the NIR spectra. A two-parametric Swish (TSwish or TS) activation function was proposed to improve the performance of CNN, and the elastic net (EN) was also applied to avoid the overfitting problem of the CNN model. Performance of the developed XGBoost-CNN-TS-EN model was evaluated using two public NIR spectroscopy datasets of corn and soil, and the obtained determination coefficients (R2) for moisture, oil, protein, and starch of the corn on test set were 0.993, 0.991, 0.998, and 0.992, respectively, with that of the soil organic matter being 0.992. The XGBoost-CNN-TS-EN model exhibits superior stability, good prediction accuracy, and generalization ability, demonstrating its great potentials for quantitative analysis of multi-constituents in spectroscopic applications.

RESUMEN

A trending problem of Extra Virgin Olive Oil (EVOO) adulteration is investigated using two analytical platforms, involving: (1) Near Infrared (NIR) spectroscopy, resulting in a two-way data set, and (2) Fluorescence Excitation-Emission Matrix (EEFM) spectroscopy, producing three-way data. The related instruments were employed to study genuine and adulterated samples. Each data set was first separately analyzed using the Data Driven-Soft Independent Modeling of Class Analogies (DD-SIMCA) method, based on Principal Component Analysis (for the two-way NIR data) and PARallel FACtor analysis (for the three-way EEFM data). The data sets were then processed together using the multi-block fusion method, based on the concept of Cumulative Analytical Signal (CAS). A comparison of the data processing methods in terms of sensitivity, specificity and selectivity showed the following order of excellence: NIR < EEFM < NIR + EEFM. This finding confirms the effectiveness of multi-block data fusion, which cumulatively improves the model performance.