Partial Regression Research Articles

Prediction of protein content in paddy rice (Oryza sativa L.) combining near-infrared spectroscopy and deep-learning algorithm

Rice is a staple crop in Asia, with more than 400 million tons consumed annually worldwide. The protein content of rice is a major determinant of its unique structural, physical, and nutritional properties. Chemical analysis, a traditional method for measuring rice’s protein content, demands considerable manpower, time, and costs, including preprocessing such as removing the rice husk. Therefore, of the technology is needed to rapidly and nondestructively measure the protein content of paddy rice during harvest and storage stages. In this study, the nondestructive technique for predicting the protein content of rice with husks (paddy rice) was developed using near-infrared spectroscopy and deep learning techniques. The protein content prediction model based on partial least square regression, support vector regression, and deep neural network (DNN) were developed using the near-infrared spectrum in the range of 950 to 2200 nm. 1800 spectra of the paddy rice and 1200 spectra from the brown rice were obtained, and these were used for model development and performance evaluation of the developed model. Various spectral preprocessing techniques was applied. The DNN model showed the best results among three types of rice protein content prediction models. The optimal DNN model for paddy rice was the model with first-order derivative preprocessing and the accuracy was a coefficient of determination for prediction, Rp2 = 0.972 and root mean squared error for prediction, RMSEP = 0.048%. The optimal DNN model for brown rice was the model applied first-order derivative preprocessing with Rp2 = 0.987 and RMSEP = 0.033%. These results demonstrate the commercial feasibility of using near-infrared spectroscopy for the non-destructive prediction of protein content in both husked rice seeds and paddy rice.

In silico insights into the design of novel NR2B-selective NMDA receptor antagonists: QSAR modeling, ADME-toxicity predictions, molecular docking, and molecular dynamics investigations

Based on a structural family of thirty-two NR2B-selective N-Methyl-D-Aspartate receptor (NMDAR) antagonists, two phenylpiperazine derivatives labeled C37 and C39 were conceived thanks to molecular modeling techniques, as novel NMDAR inhibitors exhibiting the highest analgesic activities (of pIC50 order) against neuropathic pain, with excellent ADME-toxicity profiles, and good levels of molecular stability towards the targeted protein of NMDA receptor. Initially, the quantitative structure-activity relationships (QSARs) models were developed using multiple linear regression (MLR), partial least square regression (PLSR), multiple non-linear regression (MNLR), and artificial neural network (ANN) techniques, revealing that analgesic activity was strongly correlated with dipole moment, octanol/water partition coefficient, Oxygen mass percentage, electronegativity, and energy of the lowest unoccupied molecular orbital, whose the correlation coefficients of generated models were: 0.860, 0.758, 0.885 and 0.977, respectively. The predictive capacity of each model was evaluated by an external validation with correlation coefficients of 0.703, 0.851, 0.778, and 0.981 respectively, followed by a cross-validation technique with the leave-one-out procedure (CVLOO) with Q2cv of 0.785, more than Y-randomization test, and applicability domain (AD), in addition to Fisher’s and Student’s statistical tests. Thereafter, ten novel molecules were designed based on MLR QSAR model, then predicted with their ADME-Toxicity profiles and subsequently examined for their similarity to the drug candidates. Finally, two of the most active compounds (C37 and C39) were chosen for molecular docking and molecular dynamics (MD) investigations during 100 ns of MD simulation time in complex with the targeted protein of NMDA receptor (5EWJ.pdb).

Developing a Hyperspectral Remote Sensing-Based Algorithm to Diagnose Potato Moisture for Water-Saving Irrigation

Appropriate water supply is crucial for high-yield and high-quality potato tuber production. However, potatoes are mainly planted in arid and semi-arid regions in China, where the precipitation usually cannot meet the water demand throughout the growth period. In view of the actual situation of water shortage in these areas, to monitor the water status of potato plants timely and accurately and thus precisely control the irrigation are of significance for water-saving management of potatoes. Hyperspectral remote sensing has unique advantages in diagnosing crop water stress. In this paper, the canopy spectral reflectance and plant water content were measured under five irrigation treatments. The spectral parameters that respond to plant water content were selected, and a hyperspectral water diagnosis model for leaf water content (LWC) and aboveground water content (AGWC) of potato plants was established. It was found that potato tuber yield was the highest during the entire growth period under sufficient irrigation, and the plant water content showed a downward trend as the degree of drought intensified. The peak hyperspectral reflectance of potato plant canopies appeared in the red wavelength, where the reflectance varied significantly under different water treatments and decreased with decreasing irrigation. Six models with sensitive bands, first-order derivatives, and moisture spectral indices were established to monitor water content of potato plants. The R2 values of partial least squares regression (PLSR), support vector machine (SVM), and BP neural network (BP) models are 0.8418, 0.9020, and 0.8926, respectively, between LWC and hyperspectral data; and 0.8003, 0.8167, and 0.8671, respectively, between the AGWC and hyperspectral data. These six models can all predict the water content of potato plants, but SVM is the best model for predicting LWC of potato plants. These results are of great significance for guiding precision irrigation of potato plants at different growth stages.

Soil Organic Carbon Prediction Based on Vis–NIR Spectral Classification Data Using GWPCA–FCM Algorithm

Soil visible and near–infrared reflectance spectroscopy is an effective tool for the rapid estimation of soil organic carbon (SOC). The development of spectroscopic technology has increased the application of spectral libraries for SOC research. However, the direct application of spectral libraries for SOC prediction remains challenging due to the high variability in soil types and soil–forming factors. This study aims to address this challenge by improving SOC prediction accuracy through spectral classification. We utilized the European Land Use and Cover Area frame Survey (LUCAS) large–scale spectral library and employed a geographically weighted principal component analysis (GWPCA) combined with a fuzzy c–means (FCM) clustering algorithm to classify the spectra. Subsequently, we used partial least squares regression (PLSR) and the Cubist model for SOC prediction. Additionally, we classified the soil data by land cover types and compared the classification prediction results with those obtained from spectral classification. The results showed that (1) the GWPCA–FCM–Cubist model yielded the best predictions, with an average accuracy of R2 = 0.83 and RPIQ = 2.95, representing improvements of 10.33% and 18.00% in R2 and RPIQ, respectively, compared to unclassified full sample modeling. (2) The accuracy of spectral classification modeling based on GWPCA–FCM was significantly superior to that of land cover type classification modeling. Specifically, there was a 7.64% and 14.22% improvement in R2 and RPIQ, respectively, under PLSR, and a 13.36% and 29.10% improvement in R2 and RPIQ, respectively, under Cubist. (3) Overall, the prediction accuracy of Cubist models was better than that of PLSR models. These findings indicate that the application of GWPCA and FCM clustering in conjunction with the Cubist modeling technique can significantly enhance the prediction accuracy of SOC from large–scale spectral libraries.

Probing Biological Nitrogen Fixation in Legumes Using Raman Spectroscopy

Biological nitrogen fixation (BNF) by symbiotic bacteria plays a vital role in sustainable agriculture. However, current quantification methods are often expensive and impractical. This study explores the potential of Raman spectroscopy, a non-invasive technique, for rapid assessment of BNF activity in soybeans. Raman spectra were obtained from soybean plants grown with and without rhizobia bacteria to identify spectral signatures associated with BNF. δN15 isotope ratio mass spectrometry (IRMS) was used to determine actual BNF percentages. Partial least squares regression (PLSR) was employed to develop a model for BNF quantification based on Raman spectra. The model explained 80% of the variation in BNF activity. To enhance the model’s specificity for BNF detection regardless of nitrogen availability, a subsequent elastic net (Enet) regularisation strategy was implemented. This approach provided insights into key wavenumbers and biochemicals associated with BNF in soybeans.

Hydrops regression after vestibular denervation - longitudinal magnetic resonance study in patients with severe Meniere's disease treated with vestibular neurectomy.

The aim was to evaluate endolymphatic hydrops in patients with severe Ménière's disease (MD) before and after vestibular neurectomy to verify if vestibular denervation results in hydrops regression. Magnetic resonance imaging was performed after intravenous gadolinium injection in twenty patients with unilateral definite MD before and after the vestibular neurectomy. Clinical symptoms and audiovestibular tests were evaluated. Follow-up intervals ranged from 18 to 35 months after the surgery. Endolymphatic hydrops were visualized in all patients in the preoperative scans. After the vestibular neurectomy, all patients presented a complete resolution of vertigo episodes. Regression of the endolymphatic hydrops was observed in 35% and 15% of cases analyzing cochlea and vestibule, respectively. In 71.43% of patients with utricular herniation into the lateral semicircular canal, withdrawal of the hernia was visualized. Asymmetrical contrast enhancement in the cochlea regressed in 17.64% of cases. Analyzing all the parameters collectively, in 60% of patients, partial regression of at least one of the radiological signs was confirmed in the follow-up examination. No progression of the endolymphatic hydrops was visualized after the surgery in either the cochlea or the vestibule. Vestibular neurectomy is an effective treatment, eliminating vertigo attacks and improving the quality of life in patients with MD. Magnetic resonance imaging of the inner ear allows visualization of changes in endolymphatic hydrops degree after treatment. Regression of the endolymphatic hydrops after vestibular neurectomy suggests that vestibular denervation may effectively halt the progression of the endolymphatic space dilatation and result in hydrops regression.

Vagus nerve size determined via ultrasonography is associated with white matter lesions in patients with vascular risk factors.

The cross-sectional area (CSA) of the cervical vagus nerve (VN), as assessed through ultrasonography, might be linked to autonomic nervous system dysfunction. Hypertension is the primary factor associated with cerebral white matter lesions (WMLs), but there is also evidence of a connection with autonomic nervous system dysfunction. However, the associations between WMLs and VN size are unclear. Our objective was to investigate the associations between WMLs and VN size in patients with vascular risk factors. The CSA of the VN was evaluated using carotid ultrasonography in patients with a history of stroke (acute or chronic) and comorbidities (n = 196, 70.2 ± 12.7years). Common carotid artery (CCA) intima-media thickness and interadventitial diameter (IAD) were also measured. The severity of the WMLs was assessed by the Fazekas classification and Scheltens' scale. The CSA of the right VN (2.08 ± 0.65mm2) was significantly greater than that of the CSA of the left VN (1.56 ± 0.44mm2) (P < 0.001). Multiple linear regression analyses revealed that older age, hypertension, increased right CCA IAD, and decreased CSA of the right VN (standardized partial regression coefficient [β] -0.226; P < 0.001) were independently associated with the severity of WMLs (Scheltens' scale). A decreased CSA of the left VN was also associated with the severity of WMLs (β = -0.239; P < 0.001). VN size determined via ultrasonography was associated with the severity of WMLs. While these findings do not establish a causal relationship, they suggest that autonomic nervous system dysfunction is involved in the progression of WMLs.

Characterization and detailed mapping of C by spectral sensor for soils of the Western Plateau of São Paulo

Soil mineralogy and texture are directly related to soil carbon due to the physical properties of the clay surface. Traditional techniques for quantifying carbon in soil are time-consuming and expensive, making large-scale quantification for mapping unfeasible. The alternative is the use of soil sensors, such as diffuse reflectance spectroscopy (DRS), an economical, fast, and accurate technique for predicting carbon stocks. In this sense, this study aimed to (a) investigate the relationship of C with different soil mineralogical, chemical, and physical attributes for different geological and geomorphological compartments; (b) understand which spectral bands are most important for estimating C content; (c) estimate C content from diffuse reflectance spectroscopy using different mathematical techniques and indicate which one is the best for tropical soil conditions; and (d) map C contents in detail. The study area was the Western Plateau of São Paulo (WPSP), which covers approximately 13 million hectares (~ 48% of the State of São Paulo, Brazil). A total of 265 samples were collected in this area. The attributes clay, silt, sand, crystalline and non-crystalline iron, base saturation, soil density, total pore volume, total C, C stock, kaolinite/(kaolinite + gibbsite) and hematite/(hematite + goethite), hematite and goethite contents, and spectral curves were evaluated. The spectra were recorded at 0.5-nm intervals, with an integration time of 2.43 nm s−1 over the 350 to 2500-nm range (350–800 nm—visible—VIS and 801–2500 nm—near-infrared—NIR). The data were subjected to descriptive statistics, Spearman correlation, stepwise analysis, and cluster grouping for characterization purposes; partial least squares regression (PLSR) and random forest (RF) for estimation purposes; and geostatistics analysis for creation of spatial maps. Our results indicate that the highest C contents are associated with more clayey soils, oxidic mineralogy, higher total pore volume, and lower soil density in highly dissected basalt compartments. The random forest algorithm associated with the Vis–NIR spectral range is more efficient for estimating and mapping C contents. This suggests that integrating diffuse reflectance spectroscopy with machine learning techniques holds promise for shaping public policies related to land use, mitigating CO2 emissions, and facilitating the implementation of carbon credit policies in a rapid and economically efficient manner.

Comparative analysis of hyperspectral Image reconstruction using deep learning for agricultural and biological applications

Hyperspectral imaging (HSI) has become a key technology for non-invasive quality evaluation in various fields, offering detailed insights through spatial and spectral data. Despite its efficacy, the complexity and high cost of HSI systems have hindered their widespread adoption. This study addressed these challenges by exploring deep learning-based hyperspectral image reconstruction from RGB (Red, Green, Blue) images, particularly for agricultural products. Specifically, different hyperspectral reconstruction algorithms, such as Hyperspectral Convolutional Neural Network - Dense (HSCNN-D), High-Resolution Network (HRNET), and Multi-Scale Transformer Plus Plus (MST++), were compared to assess the dry matter content of sweet potatoes. Among the tested reconstruction methods, HRNET demonstrated superior performance, achieving the lowest mean relative absolute error (MRAE) of 0.07, root mean square error (RMSE) of 0.03, and the highest peak signal-to-noise ratio (PSNR) of 32.28 decibels (dB). Some key features were selected using the genetic algorithm (GA), and their importance was interpreted using explainable artificial intelligence (XAI). Partial least squares regression (PLSR) models were developed using the RGB, reconstructed, and ground truth (GT) data. The visual and spectra quality of these reconstructed methods was compared with GT data, and predicted maps were generated. The results revealed the prospect of deep learning-based hyperspectral image reconstruction as a cost-effective and efficient quality assessment tool for agricultural and biological applications.

Comparative analysis of modified partial least squares regression and hybrid deep learning models for predicting protein content in Perilla (Perilla frutescens L.) seed meal using NIR spectroscopy

Perilla seed meal (PSM), a byproduct of oil extraction from Perilla frutescens L. seeds, is rich in protein (24.26–42.85%) and holds potential as an economical and sustainable animal feed. Traditional methods for assessing protein content are labor-intensive and costly. This study explores Near-Infrared Reflectance Spectroscopy (NIRS) for the rapid, precise, and non-destructive determination of PSM protein content in 126 samples. We developed and evaluated Modified Partial Least Squares (MPLS) regression and deep learning (DL) models, including 1D-CNN (Convolutional Neural Network), LSTM Long Short-Term Memory), and hybrid architectures incorporating skip connections, inception modules, and spectral derivatives. Model performance was validated externally using parameters such as RSQexternal (R-squared), bias, SEP(C) (Standard Error of Prediction), RPD (Residual Prediction Deviation), slope, SD (Standard Deviation), p-value (≥0.05), and the correlation between reference and predicted values. The 1D CNN-LSTM-Inception derivative 1 model achieved the best performance (RPD: 8.0, RSQexternal: 0.98), followed by the MPLS-based model (RPD: 4.88, RSQexternal: 0.96) and the 1D CNN derivative 1 model (RPD: 3.07, RSQexternal: 0.96). These models provide a reliable and advanced technology for the non-destructive screening of PSM protein content, thus aiding in the rapid identification and selection of superior perilla chemotypes from varied backgrounds.

Soil pH and organic matter: Key edaphic factors in sustaining optimum yield and quality of pomelo fruit

Identifying the soil properties associated with crop yield and quality variation is crucial for developing sustainable agronomic strategies. However, such information on pomelo production is scarce. Hence, forty independent sites in the primary pomelo production areas of Pinghe County were selected to investigate the influence of soil properties on pomelo yield and quality, and to provide reference for future soil management strategies. The results showed positive correlations between pomelo yield and soil pH, along with exchangeable calcium and magnesium, but this comes at the expense of fruit flavor quality. Meanwhile, soil organic matter positively influenced fruit flavor quality. Furthermore, a significant positive effect on fruit nutritional quality was noted across various soil properties, except for organic matter and available phosphorus concentration. A random forest model was used to predict pomelo yield, flavor quality, and nutritional quality based on soil properties and yielded R2 values of 0.50, 0.60, and 0.50, respectively. Partial least squares regression and structural equation modeling identified soil pH and organic matter as pivotal pomelo yield and quality determinants. The categorization of samples into four groups based on differences in pH and organic matter highlighted that integrating soil acidification remediation with organic matter increased is essential for sustainable pomelo production. Overall, this study offers comprehensive insights into the effects of holistic soil management on achieving both high yield and quality in pomelo cultivation. Furthermore, these findings serve as valuable reference for advancing sustainable production practices across large fruit types beyond the pomelo.

Raman spectroscopy as an alternative rapid microbial bioburden test method for continuous, automated detection of contamination in biopharmaceutical drug substance manufacturing.

To investigate an in-line Raman method capable of detecting accidental microbial contamination in pharmaceutical vessels, such as bioreactors producing monoclonal antibodies via cell culture. The Raman method consists of a multivariate model built from Raman spectra collected in-line during reduced-scale bioreactor batches producing a monoclonal antibody, as well as a reduced-scale process with intentional spiking of representative compendial method microorganisms (n=4). The orthogonal partial least squares regression discriminant analysis model (OPLS-DA) Area Under the Curve (AUC), specificity and sensitivity were 0.96, 0.99 and 0.95, respectively. Furthermore, the model successfully detected contamination in an accidentally contaminated manufacturing-scale batch. In all cases, the time to detection (TTD) for Raman was superior compared to offline, traditional microbiological culturing. The Raman OPLS-DA method met acceptance criteria for equivalent decision making to be considered a viable alternative to the compendial method for in-process bioburden testing. The in-line method is automated, non-destructive, and provides a continuous assessment of bioburden compared to an offline compendial method, which is manual, results in loss of product, and in practice is only collected once daily and requires 3-5 days for enumeration.

Development of partial least squares regression with discriminant analysis for software bug prediction

Many prediction models and approaches have been introduced during the past decades that try to forecast bugged code elements based on static source code metrics, change and history metrics, or both. However, there is still no universal best solution to this problem, as most suitable features and models vary from dataset to dataset and depend on the context in which we use them. Therefore, novel approaches and further studies on this topic are highly necessary.In this paper, we employ a chemometric approach – Partial Least Squares with Discriminant Analysis (PLS-DA) – for predicting bug prone Classes in Java programs using static source code metrics. PLS-DA is successfully applied within the field of chemometrics, but to our best knowledge, it has never been used before in the software maintenance domain for predicting bugs. In addition, we have used rigorous statistical treatments and evaluation for representing the software engineering results.We show that our PLS-DA based prediction model achieves superior performances compared to the state-of-the-art approaches (i.e. F-measure of 0.44–0.47 at 90% confidence level) when no data re-sampling applied and comparable to others when applying up-sampling on the largest open bug dataset, while training the model is significantly faster, thus finding optimal parameters is much easier. In terms of completeness, which measures the amount of bugs contained in the Java Classes predicted to be defective, PLS-DA outperforms every other algorithm: it found 69.3% and 79.4% of the total bugs with no re-sampling and up-sampling, respectively.

Compressive strength detection of tunnel lining using hyperspectral images and machine learning

Traditional tunnel lining strength detection techniques are mostly contact-based, with relatively low detection efficiency. This study innovatively proposes hyperspectral imaging method to rapidly detect tunnel concrete lining strength from a machine vision perspective. Hyperspectral cameras were employed in indoor experiments to capture hyperspectral images of concrete specimens with different compressive strength levels. The differences of concrete strength based on hyperspectral reflectance characteristics were analysed using hyperspectral images and machine learning algorithms. Firstly, the K-Nearest Neighbors (KNN) classification algorithm was used to predict the classification of the concrete hyperspectral dataset with accuracy mostly exceeding 90 %. The results indicate distinctive differences in hyperspectral reflectance characteristics among concrete specimens. Furthermore, compressive strength prediction of different concrete specimens was carried out using Principal component regression (PCR), Partial least squares regression (PLSR), and Least Squares Support Vector Machine (LSSVM) machine learning models on both original and Savitzky-Golay(S-G) processed spectral data. LSSVM and PLSR models performed excellently in the visible light spectrums(400–1000 nm), with LSSVM excelling in the near-infrared spectrums(900–1700 nm). Finally, the feasibility of using Hyperspectral imaging(HSI) technology to detect tunnel lining strength was demonstrated at the shield tunnel model site. The predicted results were validated by combining with strength values measured by the rebound hammer, and presented promoising research path for automated non-destructive detection of concrete tunnel lining strength.

Optimizing Starch Content Prediction in Kudzu: Integrating Hyperspectral Imaging and Deep Learning with WGAN-GP

Rapid and non-destructive prediction of starch content in kudzu is essential for the food industry. In this work, we present an approach combining hyperspectral imaging (HSI) and deep learning (DL) techniques for predicting kudzu root starch content. Practical constraints such as equipment and experimental conditions limit the quantity of spectral data and labels obtained, which leads to diminish model performance. To address this restriction, we employ Wasserstein generative adversarial networks with gradient penalty (WGAN-GP) to augment spectral and starch content data simultaneously. Through numerous iterations, synthetic data that closely resemble real data is generated, which is validated through comprehensive evaluations using various qualitative and quantitative analysis. Additionally, we establish and compare partial least squares regression (PLSR), support vector regression (SVR) and one-dimensional convolutional neural network (1DCNN) model before and after data augmentation. Experimental results demonstrate that the introduction of synthetic data could improve model performance significantly. Particularly, 1DCNN model exhibits the best performance, achieving correlation coefficients (R2) of 92.97% and 93.43% for starch content in the two types of kudzu roots. Overall, this study not only provides an effective method for rapidly, non-destructively, and accurately determining starch content in kudzu roots, but also addresses the challenge of requiring a large amount of data.

Hyperspectral Characteristics and SPAD Estimation of Wheat Leaves under CO2 Microleakage Stress

To non-destructively and rapidly monitor the chlorophyll content of winter wheat leaves under CO2 microleakage stress, and to establish the quantitative relationship between chlorophyll content and sensitive bands in the winter wheat growing season from 2023 to 2024, the leakage rate was set to 1 L/min, 3 L/min, 5 L/min, and 0 L/min through field experiments. The dimensional reduction was realized, fractional differential processing of a wheat canopy spectrum was carried out, a multiple linear regression (MLR) and partial least squares regression (PLSR) estimation model was constructed using a SPA selection band, and the model’s accuracy was evaluated. The optimal model for hyperspectral estimation of wheat SPAD under CO2 microleakage stress was screened. The results show that the spectral curves of winter wheat leaves under CO2 microleakage stress showed a “red shift” of the green peak and a “blue shift” of the red edge. Compared with 1 L/min and 3 L/min, wheat leaves were more affected by CO2 at 5 L/min. Evaluation of the accuracy of the MLR and PLSR models shows that the MLR model is better, where the MLR estimation model based on 1.1, 1.8, 0.4, and 1.7 differential SPAD is the best for leakage rates of 1 L/min, 3 L/min, 5 L/min, and 0 L/min, with validation set R² of 0.832, 0.760, 0.928, and 0.773, which are 11.528, 14.2, 17.048, and 37.3% higher than the raw spectra, respectively. This method can be used to estimate the chlorophyll content of winter wheat leaves under CO2 trace-leakage stress and to dynamically monitor CO2 trace-leakage stress in crops.

Elucidation of anti-pneumonia pharmacodynamic material basis and potential mechanisms of Xiebai San by combining spectrum–efficacy relationship and surface plasmon resonance

Ethnopharmacological relevanceXiebai San (XBS), a classic Chinese prescription, has been used for the clinical treatment of pneumonia-related diseases for thousands of years. However, the anti-pneumonia pharmacodynamic material basis of XBS and its underlying mechanisms remain unclear. Aim of the studyThis study aimed to comprehensively investigate and verify the anti-pneumonia pharmacodynamic material basis and mechanisms of XBS. Materials and methodsThis study explored the anti-pneumonia activity and key pneumonia targets of XBS in lipopolysaccharide (LPS)-induced zebrafish and RAW264.7 cells in vivo and in vitro through transcriptomics, western blotting, and reverse transcription–quantitative polymerase chain reaction (RT–qPCR). The chemical fingerprint of XBS was established using high-performance liquid chromatography, and the similarities and areas of characteristic peaks of 15 batches of XBS were analyzed. Based on the spectrum–efficacy relationship, the potential anti-inflammatory components were screened according to their peak areas and efficacy using principal component analysis (PCA), bivariate correlation, and partial least squares regression analysis. Active components that bind to core targets were further screened based on surface plasmon resonance (SPR). The binding mode of proteins and components was simulated via molecular docking, which enabled the identification of the primary active components of XBS, thereby elucidating its anti-pneumonia properties. Finally, the anti-inflammatory activities of these components were verified in vitro. ResultsXBS decreased neutrophil aggregation in zebrafish and nitric oxide (NO) secretion in RAW264.7 cells as well as suppressed the release of downstream inflammatory cytokines such as iNOS, TNF-α, IL-1β, IL-18, and CXCL10 related to TNF and JAK–STAT signaling pathways. The phosphorylation of IκBα, Akt, and Stat3 was alleviated after XBS in cells. The fingerprint similarities of 15 batches of XBS ranged from 0.381 to 0.994, with a large difference. A total of 15 characteristic peaks were identified, and the relative standard deviation of their peak areas ranged from 24.1% to 70.7%. The results of in vitro anti-inflammatory activities of 15 batches of XBS showed that all samples inhibited the expression levels of NO and nine inflammatory markers. The anti-inflammatory index of 15 batches of XBS was determined to be 0.69–0.96 based on transformation of the anti-inflammatory rate and composite index method via PCA. The spectrum–efficacy relationship model of 15 characteristic peak areas and the anti-inflammatory index showed that 7 main potential active components were related to the anti-inflammatory activity of XBS. Moreover, four components (mulberroside A, isoquercitrin, liquiritigenin, and glycyrrhizic acid) screened based on SPR had different affinities toward TNFR1, Akt1, and Stat3 proteins, and the binding modes were elucidated via molecular docking. Finally, in LPS-induced RAW264.7 cells, all four active components (at a concentration of 60 μM) significantly inhibited the expression levels of NO and inflammatory markers. ConclusionsBased on the comprehensive strategy of spectrum–efficacy relationship and SPR, mulberroside A, isoquercitrin, liquiritigenin, and glycyrrhizic acid were identified as the primary pharmacodynamic active components involved in the anti-pneumonia activity of XBS and were found to intervene in TNF and JAK–STAT signaling pathways.

Improving the Estimation Accuracy of Soil Organic Matter Content Based on the Spectral Reflectance from Soils with Different Grain Sizes

Accurate and rapid estimation of soil organic matter (SOM) content is of great significance for advancing precision agriculture. Compared with traditional chemical methods, the hyperspectral estimation is superior in rapidly estimating SOM content. Soil grain size affects soil spectral reflectance, thereby affecting the accuracy of hyperspectral estimation. However, the appropriate soil grain size for the hyperspectral analysis is nearly unknown. This study propose a best hyperspectral estimation method for determining SOM content of farmland soil in the Ibinur Lake Irrigation Area (ILIA) of the northwest arid zones of China. The original spectral reflectance of the 20-mesh (0.85 mm) and 60-mesh (0.25 mm) sieved soil were obtained, and the feature wavebands were selected using five types of spectral transformations. Then, hyperspectral estimation models were constructed based on the partial least squares regression (PLSR), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost) models. Results show that the SOM content had relatively higher correlation coefficient with spectral reflectance of the 0.85 mm sieved soil than that of the 0.25 mm sieved soil. The transformation of original spectral reflectance of soil effectively enhanced the spectral characteristics related to SOM content. Soil grain size obviously affected spectral reflectance and the accuracy of hyperspectral estimation models. The overall stability and estimation accuracy of RF model was significantly higher compared with the PLSR, SVM, and XGBoost. Finally, the RF model combined with the root mean first-order differentiation (RMSFD) of spectral reflectance of the 0.85 mm sieved soil (R2 = 0.82, RMSE = 2.37, RPD = 2.27) was identified as the best method for estimating SOM content of farmland soil in the ILIA.

Quasi-Non-Destructive Estimation of Concrete Compression Strength Using Laser-Induced Breakdown Spectroscopy and Multivariate Analysis.

Micro- and non-destructive methods of estimating compressive strength are useful for diagnosing the degradation of reinforced structures. The velocity of waves propagating through concrete can be measured using conventional non-destructive methods; however, the propagation path of waves varies depending on the distribution of coarse aggregate, resulting in variations in velocity at different measurement points. To address this issue, a method based on laser-induced breakdown spectroscopy and multivariate analysis was developed in this study for estimating the compressive strength of concrete non-destructively, ensuring the non-influence of the coarse aggregate spatial distribution. The method is based on the correlation between the emission intensity of the spectrum and the hardness of the object to be measured. Principal component analysis and partial least squares regression (PLSR) were used to extract the mortar spectrum, which determines the compressive strength of concrete, from a mixture of aggregate and mortar spectra. The compressive strength estimated based on the proposed method was consistent with the values obtained from the compressive strength test, which indicates the possibility of using multivariable analysis to estimate the compressive strength of concrete. Furthermore, the proposed method enabled on-site measurements through a simple experimental setup and insensitivity to spectral noise offered by PLSR.

Performance Evaluation and Comparison of Deep Neural Network Models for African Soil Properties Prediction

ABSTRACT The significance of soil in agriculture and human survival cannot be overstated. Given its limited supply, improving soil properties is imperative. This study addresses this challenge by predicting five major soil properties—organic carbon, pH values, Mehlich-3 extractable calcium, Mehlich-3 extractable phosphorus, and sand content—utilizing mid-infrared absorbance measurements from the African Soil Information Service (AfSIS) dataset, covering non-desert regions of Africa. With a pressing need for a reliable and efficient model to predict African soil properties using spectral measurements, this study fills a crucial gap, addressing the scarcity of functional soil property databases in Africa. The developed model eliminates costly soil sample preparation and lengthy chemical analysis, applicable in both onsite and laboratory settings for determining soil functional properties. By employing stacked autoencoders for feature dimensionality reduction and combining discrete wavelet transform with two feature selection methods (stepwise regression and random forest) to build robust multi-layer perceptron (MLP) models, the study offers a comprehensive approach. Evaluation metrics including root mean square error (RMSE), scatter index (SI), Variance Accounted For (VAF), Nash-Sutcliffe Model Efficiency (NSE), and Correlation Coefficient (R) demonstrate the superior performance of the MLP model informed by stacked autoencoder-selected features, outperforming models informed by wavelet-transformed features and partial least square regression. This best-performing autoencoder-based model presents a valuable tool for soil scientists tasked with modeling African soil properties.