Tropospheric zenith wet delay(ZWD)plays a vital role in the analysis of space geodetic observations.In recent years,machine learning methods have been increasingly applied to improve the accuracy of ZWD calculations.H...Tropospheric zenith wet delay(ZWD)plays a vital role in the analysis of space geodetic observations.In recent years,machine learning methods have been increasingly applied to improve the accuracy of ZWD calculations.However,a single machine learning model has limited generalization capabilities.To address these limitations,this study introduces a novel machine learning fusion(MLF)algorithm with stronger generalization capabilities to enhance ZWD modeling and prediction accuracy.The MLF algorithm utilizes a two-layer structure integrating extra trees(ET),backpropagation neural network(BPNN),and linear regression models.By comparing the root mean square error(RMSE)of these models,we found that both ET-based and MLF-based models outperform RF-based and BPNN-based models in terms of internal and external accuracy,across both surface meteorological data-based and blind models.The improvement in exte rnal accuracy is particularly significant in the blind models.Our re sults show that the MLF(with an RMSE of 3.93 cm)and ET(3.99 cm)models outperform the traditional GPT3model(4.07 cm),while the RF(4.21 cm)and BPNN(4.14 cm)have worse external accuracies than the GPT3 model.It is worth noting that the BPNN suffered from overfitting during external accuracy tests,which was avoided by the MLF.In summary,regardless of the availability of surface meteorological data,the MLF-based empirical models demonstrate superior internal and external accuracy compared to the other tested models in this study.展开更多
The uplift resistance of the soil overlying shield tunnels significantly impacts their anti-floating stability.However,research on uplift resistance concerning special-shaped shield tunnels is limited.This study combi...The uplift resistance of the soil overlying shield tunnels significantly impacts their anti-floating stability.However,research on uplift resistance concerning special-shaped shield tunnels is limited.This study combines numerical simulation with machine learning techniques to explore this issue.It presents a summary of special-shaped tunnel geometries and introduces a shape coefficient.Through the finite element software,Plaxis3D,the study simulates six key parameters—shape coefficient,burial depth ratio,tunnel’s longest horizontal length,internal friction angle,cohesion,and soil submerged bulk density—that impact uplift resistance across different conditions.Employing XGBoost and ANN methods,the feature importance of each parameter was analyzed based on the numerical simulation results.The findings demonstrate that a tunnel shape more closely resembling a circle leads to reduced uplift resistance in the overlying soil,whereas other parameters exhibit the contrary effects.Furthermore,the study reveals a diminishing trend in the feature importance of buried depth ratio,internal friction angle,tunnel longest horizontal length,cohesion,soil submerged bulk density,and shape coefficient in influencing uplift resistance.展开更多
Countries around the world have been making efforts to reduce pollutant emissions. However, the response of global black carbon(BC) aging to emission changes remains unclear. Using the Community Atmosphere Model versi...Countries around the world have been making efforts to reduce pollutant emissions. However, the response of global black carbon(BC) aging to emission changes remains unclear. Using the Community Atmosphere Model version 6 with a machine-learning-integrated four-mode version of the Modal Aerosol Module, we quantify global BC aging responses to emission reductions for 2011–2018 and for 2050 and 2100 under carbon neutrality. During 2011–18, global trends in BC aging degree(mass ratio of coatings to BC, R_(BC)) exhibited marked regional disparities, with a significant increase in China(5.4% yr^(-1)), which contrasts with minimal changes in the USA, Europe, and India. The divergence is attributed to opposing trends in secondary organic aerosol(SOA) and sulfate coatings, driven by regional changes in the emission ratios of corresponding coating precursors to BC(volatile organic compounds-VOCs/BC and SO_(2)/BC). Projections under carbon neutrality reveal that R_(BC) will increase globally by 47%(118%) in 2050(2100), with strong convergent increases expected across major source regions. The R_(BC) increase, primarily driven by enhanced SOA coatings due to sharper BC reductions relative to VOCs, will enhance the global BC mass absorption cross-section(MAC) by 11%(17%) in 2050(2100).Consequently, although the global BC burden will decline sharply by 60%(76%), the enhanced MAC partially offsets the magnitude of the decline in the BC direct radiative effect, resulting in the moderation of global BC DRE decreases to 88%(92%) of the BC burden reductions in 2050(2100). This study highlights the globally enhanced BC aging and light absorption capacity under carbon neutrality, thereby partly offsetting the impact of BC direct emission reductions on future changes in BC radiative effects globally.展开更多
The application and promotion of waste glass powder concrete(WGPC)cansignificantly alleviate the pressure of concrete material scarcity and environmental pollution.Compressive strength(CS)is a critical parameter for e...The application and promotion of waste glass powder concrete(WGPC)cansignificantly alleviate the pressure of concrete material scarcity and environmental pollution.Compressive strength(CS)is a critical parameter for evaluating the efficacy of WGPC.Unlike conventional testing methods,machine learning techniques offer precise and reliable predictions of concrete’s compressive strength,especially in its long-term mechanical properties.In this work,four models,namely Multiple Linear Regression(MLR),Back Propagation Neural Network(BPNN),Support Vector Regression(SVR),and Random Forest Regression(RFR)were employed.Furthermore,particle swarm optimization(PSO)algorithm and cross-validation techniques were applied to fine-tune the model parameters,striving for peak prediction performance.The results indicated that optimized models generally exhibit enhanced predictive accuracy compared to their basic counterparts.Notably,the PSO-RFR model excels among all evaluated models,showcasing superior performance on the testing dataset.It achieves a coefficient of determination(R^(2))of 0.9231,a mean absolute error(MAE)of 2.1073,and a root mean square error(RMSE)of 3.6903.When compared to experimental results,the PSO-RFR and PSO-BPNN models demonstrate exceptional predictive accuracy.Notably,the PSO-BPNN model exhibits the closest R^(2)values between its training and test sets.This close alignment of R^(2)values between the training and testing sets reflects the PSO-BPNN model’s superior generalization ability for unseen data.The findings present an efficient method for predicting concrete’s compressive strength,contributing to the sustainable development of concrete materials,and providing theoretical support for their research and application.展开更多
Cyclohexene is an important raw material in the production of nylon.Selective hydrogenation of benzene is a key method for preparing cyclohexene.However,the Ru catalysts used in current industrial processes still face...Cyclohexene is an important raw material in the production of nylon.Selective hydrogenation of benzene is a key method for preparing cyclohexene.However,the Ru catalysts used in current industrial processes still face challenges,including high metal usage,high process costs,and low cyclohexene yield.This study utilizes existing literature data combined with machine learning methods to analyze the factors influencing benzene conversion,cyclohexene selectivity,and yield in the benzene hydrogenation to cyclohexene reaction.It constructs predictive models based on XGBoost and Random Forest algorithms.After analysis,it was found that reaction time,Ru content,and space velocity are key factors influencing cyclohexene yield,selectivity,and benzene conversion.Shapley Additive Explanations(SHAP)analysis and feature importance analysis further revealed the contribution of each variable to the reaction outcomes.Additionally,we randomly generated one million variable combinations using the Dirichlet distribution to attempt to predict high-yield catalyst formulations.This paper provides new insights into the application of machine learning in heterogeneous catalysis and offers some reference for further research.展开更多
In the pharmaceutical field,machine learning can play an important role in drug development,production and treatment.Co-crystallization techniques have shown promising potential to enhance the properties of active pha...In the pharmaceutical field,machine learning can play an important role in drug development,production and treatment.Co-crystallization techniques have shown promising potential to enhance the properties of active pharmaceutical ingredients(APIs)such as solubility,permeability,and bioavailability,all without altering their chemical structure.This approach opens new avenues for developing natural products into effective drugs,especially those previously challenging in formulation.Emodin,an anthraquinone-based natural product,is a notable example due to its diverse biological activities;however,its physicochemical limitations,such as poor solubility and easy sublimation,restricted its clinical application.While various methods have improved emodin's physicochemical properties,research on its bioavailability remains limited.In our study,we summarize cocrystals and salts produced through co-crystallization technology and identify piperazine as a favorable coformer.Conflicting conclusions from computational chemistry and molecular modeling method and machine learning method regarding the formation of an emodin-piperazine cocrystal or salt led us to experimentally validate these possibilities.Ultimately,we successfully obtained the emodin-piperazine cocrystal,which were characterized and evaluated by several in vitro methods and pharmacokinetic studies.In addition,experiments have shown that emodin has a certain therapeutic effect on sepsis,so we also evaluated emodin-piperazine biological activity in a sepsis model.The results demonstrate that co-crystallization significantly enhances emodin's solubility,permeability,and bioavailability.Pharmacodynamic studies indicate that the emodin-piperazine cocrystal improves sepsis symptoms and provides protective effects against liver and kidney damage associated with sepsis.This study offers renewed hope for natural products with broad biological activities yet hindered by physicochemical limitations by advancing co-crystallization as a viable development approach.展开更多
Machine learning(ML)is recognized as a potent tool for the inverse design of environmental functional material,particularly for complex entities like biochar-based catalysts(BCs).Thus,the tailored BCs can have a disti...Machine learning(ML)is recognized as a potent tool for the inverse design of environmental functional material,particularly for complex entities like biochar-based catalysts(BCs).Thus,the tailored BCs can have a distinct ability to trigger the nonradical pathway in advance oxidation processes(AOPs),promising a stable,rapid and selective degradation of persistent contaminants.However,due to the inherent“black box”nature and limitations of input features,results and conclusions derived from ML may not always be intuitively understood or comprehensively validated.To tackle this challenge,we linked the front-point interpretable analysis approaches with back-point density functional theory(DFT)calculations to form a chained learning strategy for deeper sight into the intrinsic activation mechanism of BCs in AOPs.At the front point,we conducted an easy-to-interpret meta-analysis to validate two strategies for enhancing nonradical pathways by increasing oxygen content and specific surface area(SSA),and prepared oxidized biochar(OBC500)and SSA-increased biochar(SBC900)by controlling pyrolysis conditions and modification methods.Subsequently,experimental results showed that OBC500 and SBC900 had distinct dominant degradation pathways for 1O2 generation and electron transfer,respectively.Finally,at the end point,DFT calculations revealed their active sites and degradation mechanisms.This chained learning strategy elucidates fundamental principles for BC inverse design and showcases the exceptional capacity to integrate computational techniques to accelerate catalyst inverse design.展开更多
Artificial intelligence(AI)based models have been used to predict the structural,optical,mechanical,and electrochemical properties of zinc oxide/graphene oxide nanocomposites.Machine learning(ML)models such as Artific...Artificial intelligence(AI)based models have been used to predict the structural,optical,mechanical,and electrochemical properties of zinc oxide/graphene oxide nanocomposites.Machine learning(ML)models such as Artificial Neural Networks(ANN),Support Vector Regression(SVR),Multilayer Perceptron(MLP),and hybrid,along with fuzzy logic tools,were applied to predict the different properties like wavelength at maximum intensity(444 nm),crystallite size(17.50 nm),and optical bandgap(2.85 eV).While some other properties,such as energy density,power density,and charge transfer resistance,were also predicted with the help of datasets of 1000(80:20).In general,the energy parameters were predicted more accurately by hybrid models.The hydrothermal method was used to synthesize graphene oxide(GO)and zinc oxide(ZnO)nanocomposites.The increased surface area,conductivity,and stability of graphene oxide in zinc oxide nanoparticles make the composite an ideal option for energy storage.X-ray diffraction(XRD)confirmed the crystallite size of 17.41 nm for the nanocomposite and the presence of GO(12.8○)peaks.The scanning electron microscope(SEM)showed anchored wrinkled GO sheets on zinc oxide with an average particle size of 2.93μm.Energy-dispersive X-ray spectroscopy(EDX)confirmed the elemental composition,and Fouriertransform infrared spectroscopy(FTIR)revealed the impact of GO on functional groups and electrochemical behavior.Photoluminescence(PL)wavelength of(439 nm)and band gap of(2.81 eV)show that the material is suitable for energy applications in nanocomposites.Smart nanocomposite materials with improved performance in energy storage and related applications were fabricated by combining synthesis,characterization,fuzzy logic,and machine learning in this work.展开更多
Modern intrusion detection systems(MIDS)face persistent challenges in coping with the rapid evolution of cyber threats,high-volume network traffic,and imbalanced datasets.Traditional models often lack the robustness a...Modern intrusion detection systems(MIDS)face persistent challenges in coping with the rapid evolution of cyber threats,high-volume network traffic,and imbalanced datasets.Traditional models often lack the robustness and explainability required to detect novel and sophisticated attacks effectively.This study introduces an advanced,explainable machine learning framework for multi-class IDS using the KDD99 and IDS datasets,which reflects real-world network behavior through a blend of normal and diverse attack classes.The methodology begins with sophisticated data preprocessing,incorporating both RobustScaler and QuantileTransformer to address outliers and skewed feature distributions,ensuring standardized and model-ready inputs.Critical dimensionality reduction is achieved via the Harris Hawks Optimization(HHO)algorithm—a nature-inspired metaheuristic modeled on hawks’hunting strategies.HHO efficiently identifies the most informative features by optimizing a fitness function based on classification performance.Following feature selection,the SMOTE is applied to the training data to resolve class imbalance by synthetically augmenting underrepresented attack types.The stacked architecture is then employed,combining the strengths of XGBoost,SVM,and RF as base learners.This layered approach improves prediction robustness and generalization by balancing bias and variance across diverse classifiers.The model was evaluated using standard classification metrics:precision,recall,F1-score,and overall accuracy.The best overall performance was recorded with an accuracy of 99.44%for UNSW-NB15,demonstrating the model’s effectiveness.After balancing,the model demonstrated a clear improvement in detecting the attacks.We tested the model on four datasets to show the effectiveness of the proposed approach and performed the ablation study to check the effect of each parameter.Also,the proposed model is computationaly efficient.To support transparency and trust in decision-making,explainable AI(XAI)techniques are incorporated that provides both global and local insight into feature contributions,and offers intuitive visualizations for individual predictions.This makes it suitable for practical deployment in cybersecurity environments that demand both precision and accountability.展开更多
This study investigates the uncertain dynamic characterization of hybrid composite plates by employing advanced machine-assisted finite element methodologies.Hybrid composites,widely used in aerospace,automotive,and s...This study investigates the uncertain dynamic characterization of hybrid composite plates by employing advanced machine-assisted finite element methodologies.Hybrid composites,widely used in aerospace,automotive,and structural applications,often face variability in material properties,geometric configurations,and manufacturing processes,leading to uncertainty in their dynamic response.To address this,three surrogate-based machine learning approaches like radial basis function(RBF),multivariate adaptive regression splines(MARS),and polynomial neural networks(PNN)are integrated with a finite element framework to efficiently capture the stochastic behavior of these plates.The research focuses on predicting the first three natural frequencies under material uncertainties,which are critical to ensuring structural reliability.Monte Carlo simulation(MCS)is used as a benchmark for generating probabilistic datasets,including mean values,standard deviations,and probability density functions.The surrogate models are then trained and validated against these datasets,enabling accurate representation of uncertainty with substantially fewer samples compared to conventionalMCS.Among the methods studied,the RBFmodel demonstrates superior performance,closely approximating MCS results with a reduced sample size,thereby achieving significant computational savings.The proposed framework not only reduces computational time and costs but also maintains high predictive accuracy,making it well-suited for complex engineering systems.Beyond free vibration analysis,the methodology can be extended to more sophisticated scenarios,such as forced vibration,damping effects,and nonlinear structural responses.Overall,this work presents a computationally efficient and robust approach for surrogate-based uncertainty quantification,advancing the analysis and design of hybrid composite structures under uncertainty.展开更多
Post-kidney transplant rejection is a critical factor influencing transplant success rates and the survival of transplanted organs.With the rapid advancement of artificial intelligence technologies,machine learning(ML...Post-kidney transplant rejection is a critical factor influencing transplant success rates and the survival of transplanted organs.With the rapid advancement of artificial intelligence technologies,machine learning(ML)has emerged as a powerful data analysis tool,widely applied in the prediction,diagnosis,and mechanistic study of kidney transplant rejection.This mini-review systematically summarizes the recent applications of ML techniques in post-kidney transplant rejection,covering areas such as the construction of predictive models,identification of biomarkers,analysis of pathological images,assessment of immune cell infiltration,and formulation of personalized treatment strategies.By integrating multi-omics data and clinical information,ML has significantly enhanced the accuracy of early rejection diagnosis and the capability for prognostic evaluation,driving the development of precision medicine in the field of kidney transplantation.Furthermore,this article discusses the challenges faced in existing research and potential future directions,providing a theoretical basis and technical references for related studies.展开更多
Urban rainwater runoff is an important source of nonpoint source pollution due to its transport of diverse contaminants,including polycyclic aromatic hydrocarbons(PAHs)and chlorinated derivatives.Importantly,these chl...Urban rainwater runoff is an important source of nonpoint source pollution due to its transport of diverse contaminants,including polycyclic aromatic hydrocarbons(PAHs)and chlorinated derivatives.Importantly,these chlorinated polycyclic aromatic hydrocarbons(Cl-PAHs)exhibit elevated toxicological potential compared to their non-halogenated parent compounds.In this study,we proposed an approach that combined multivariate receptor model with integration of SHapley Additive exPlanations and Random Forest model.This method identifies the possible sources and reveals the impact of source apportionment results and environmental driving factors(such as geographical and meteorological data)on pollutant concentrations.Sixteen PAHs and nine ClPAHs were detected in 79 runoff samples from all three sites.TheΣ_(16)PAHs average concentration(2923.93 to 6071.83 ng/L)was significantly higher than theΣ_(9)Cl-PAHs(384.34 to 1314.73 ng/L).The source apportionment was conducted by positive matrix factorization(PMF),and six potential pollution sources for PAHs and three for Cl-PAHs were quantified.PAHs primarily originate from the combustion of fossil fuels such as traffic,industrial emissions and coal tar,while Cl-PAHs are mainly derived from atmospheric deposition and industrial emissions.Meanwhile,the self‑organizing map classified PAHs and Cl-PAHs into 2 and 3 groups,respectively.The k-means algorithm yielded 4 clusters for runoff samples.Among machine learning models,Random Forest(RF)demonstrated optimal predictive performance and integrated with SHapley Additive exPlanations(RF-SHAP)revealed the effects of driving factors on the predicted concentration of PAHs and Cl-PAHs in urban runoff samples.展开更多
Accurate retrieval of atmospheric vertical profiles is critical for improving weather prediction and climate monitoring.However,the complexity of atmospheric processes in cloudy regions poses challenges compared to th...Accurate retrieval of atmospheric vertical profiles is critical for improving weather prediction and climate monitoring.However,the complexity of atmospheric processes in cloudy regions poses challenges compared to those of clear sky scenarios.This study presents a novel framework that integrates Bayesian optimization and machine learning approaches to retrieve atmospheric vertical profiles—including temperature,humidity,ozone concentration,cloud fraction,ice water content(IWC),and liquid water content(LWC)—from hyperspectral infrared observations.Specifically,a Bayesian method was used to refine ERA5 reanalysis data by minimizing brightness temperature(BT)discrepancies against FY-4B Geostationary Interferometric Infrared Sounder(GIIRS)observations,generating a high-quality profile database(~2.8 million profiles)across diverse weather systems.The optimized profiles improve radiative consistency,reducing BT biases from>40 K to<10 K in cloudy regions.To further overcome the limitations of the Bayesian method,we developed a Transformer-Resnet hybrid model(TERNet),which achieved superior performance with RMSE values of 1.61 K(temperature),5.77%(humidity),and 2.25×10^(–6)/6.09×10^(–6)kg kg^(–1)(IWC/LWC)across the entire vertical levels in all-sky conditions.The TERNet outperforms both ERA5 in cloud parameter retrieval and the GIIRS L2 product in thermodynamic profiling.Independent verification with radiosonde and Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observations(CALIPSO)datasets confirms the framework's reliability across various meteorological regimes.This work demonstrates the capability of combining physics-informed Bayesian methods with data-driven machine learning to fully exploit hyperspectral IR data.展开更多
BACKGROUND:This study aims to develop and validate a machine learning-based in-hospital mortality predictive model for acute aortic syndrome(AAS)in the emergency department(ED)and to derive a simplifi ed version suita...BACKGROUND:This study aims to develop and validate a machine learning-based in-hospital mortality predictive model for acute aortic syndrome(AAS)in the emergency department(ED)and to derive a simplifi ed version suitable for rapid clinical application.METHODS:In this multi-center retrospective cohort study,AAS patient data from three hospitals were analyzed.The modeling cohort included data from the First Affiliated Hospital of Zhengzhou University and the People’s Hospital of Xinjiang Uygur Autonomous Region,with Peking University Third Hospital data serving as the external test set.Four machine learning algorithms—logistic regression(LR),multilayer perceptron(MLP),Gaussian naive Bayes(GNB),and random forest(RF)—were used to develop predictive models based on 34 early-accessible clinical variables.A simplifi ed model was then derived based on fi ve key variables(Stanford type,pericardial eff usion,asymmetric peripheral arterial pulsation,decreased bowel sounds,and dyspnea)via Least Absolute Shrinkage and Selection Operator(LASSO)regression to improve ED applicability.RESULTS:A total of 929 patients were included in the modeling cohort,and 210 were included in the external test set.Four machine learning models based on 34 clinical variables were developed,achieving internal and external validation AUCs of 0.85-0.90 and 0.73-0.85,respectively.The simplifi ed model incorporating fi ve key variables demonstrated internal and external validation AUCs of 0.71-0.86 and 0.75-0.78,respectively.Both models showed robust calibration and predictive stability across datasets.CONCLUSION:Both kinds of models were built based on machine learning tools,and proved to have certain prediction performance and extrapolation.展开更多
Nasopharyngeal carcinoma(NPC)is a malignant tumor prevalent in southern China and Southeast Asia,where its early detection is crucial for improving patient prognosis and reducing mortality rates.However,existing scree...Nasopharyngeal carcinoma(NPC)is a malignant tumor prevalent in southern China and Southeast Asia,where its early detection is crucial for improving patient prognosis and reducing mortality rates.However,existing screening methods suffer from limitations in accuracy and accessibility,hindering their application in large-scale population screening.In this work,a surface-enhanced Raman spectroscopy(SERS)-based method was established to explore the profiles of different stratified components in saliva from NPC and healthy subjects after fractionation processing.The study findings indicate that all fractionated samples exhibit diseaseassociated molecular signaling differences,where small-molecule(molecular weight cut-offvalue is 10 kDa)demonstrating superior classification capabilities with sensitivity of 90.5%and speci-ficity of 75.6%,area under receiver operating characteristic(ROC)curve of 0:925±0:031.The primary objective of this study was to qualitatively explore patterns in saliva composition across groups.The proposed SERS detection strategy for fractionated saliva offers novel insights for enhancing the sensitivity and reliability of noninvasive NPC screening,laying the foundation for translational application in large-scale clinical settings.展开更多
Accurate prediction of rockburst intensity levels is crucial for ensuring the safety of deep hard rock engineering construction.This paper introduced an expert system for rockburst intensity level prediction that empl...Accurate prediction of rockburst intensity levels is crucial for ensuring the safety of deep hard rock engineering construction.This paper introduced an expert system for rockburst intensity level prediction that employs machine learning algorithms as the basis for its inference rules.The system comprises four modules:a database,a repository,an inference engine,and an interpreter.A database containing 1114 rockburst cases was used to construct 357 datasets that serve as the repository for the expert system.Additionally,19 types of machine learning algorithms were used to establish 6783 micro-models to construct cognitive rules within the inference engine.By integrating probability theory and marginal analysis,a fuzzy scoring method based on the SoftMax function was developed and applied to the interpreter for rockburst intensity level prediction,effectively restoring the continuity of rockburst characteristics.The research results indicate that ensemble algorithms based on decision trees are more effective in capturing the characteristics of rockburst.Key factors for accurate prediction of rockburst intensity include uniaxial compressive strength,elastic energy index,the maximum principal stress,tangential stress,and their composite indicators.The accuracy of the proposed rockburst intensity level prediction expert system was verified using 20 engineering rockburst cases,with predictions aligning closely with the actual rockburst intensity levels.展开更多
Motor imbalance is a critical failure mode in rotating machinery,potentially causing severe equipment damage if undetected.Traditional vibration-based diagnostic methods rely on direct sensor contact,leading to instal...Motor imbalance is a critical failure mode in rotating machinery,potentially causing severe equipment damage if undetected.Traditional vibration-based diagnostic methods rely on direct sensor contact,leading to installation challenges and measurement artifacts that can compromise accuracy.This study presents a novel radar-based framework for non-contact motor imbalance detection using 24 GHz continuous-wave radar.A dataset of 1802 experimental trials was sourced,covering four imbalance levels(0,10,20,30 g)across varying motor speeds(500–1500 rpm)and load torques(0–3 Nm).Dual-channel in-phase and quadrature radar signals were captured at 10,000 samples per second for 30-s intervals,preserving both amplitude and phase information for analysis.A multi-domain feature extraction methodology captured imbalance signatures in time,frequency,and complex signal domains.From 65 initial features,statistical analysis using Kruskal–Wallis tests identified significant descriptors,and recursive feature elimination with Random Forest reduced the feature set to 20 dimensions,achieving 69%dimensionality reduction without loss of performance.Six machine learning algorithms,Random Forest,Extra Trees Classifier,Extreme Gradient Boosting,Categorical Boosting,Support Vector Machine with radial basis function kernel,and k-Nearest Neighbors were evaluated with grid-search hyperparameter optimization and five-fold cross-validation.The Extra Trees Classifier achieved the best performance with 98.52%test accuracy,98%cross-validation accuracy,and minimal variance,maintaining per-class precision and recall above 97%.Its superior performance is attributed to its randomized split selection and full bootstrapping strategy,which reduce variance and overfitting while effectively capturing the nonlinear feature interactions and non-normal distributions present in the dataset.The model’s average inference time of 70 ms enables near real-time deployment.Comparative analysis demonstrates that the radar-based framework matches or exceeds traditional contact-based methods while eliminating their inherent limitations,providing a robust,scalable,and noninvasive solution for industrial motor condition monitoring,particularly in hazardous or space-constrained environments.展开更多
Accurate prediction of concrete compressive strength is fundamental for optimizing mix designs,improving material utilization,and ensuring structural safety in modern construction.Traditional empirical methods often f...Accurate prediction of concrete compressive strength is fundamental for optimizing mix designs,improving material utilization,and ensuring structural safety in modern construction.Traditional empirical methods often fail to capture the non-linear relationships among concrete constituents,especially with the growing use of supple-mentary cementitious materials and recycled aggregates.This study presents an integrated machine learning framework for concrete strength prediction,combining advanced regression models—namely CatBoost—with metaheuristic optimization algorithms,with a particular focus on the Somersaulting Spider Optimizer(SSO).A comprehensive dataset encompassing diverse mix proportions and material types was used to evaluate baseline machine learning models,including CatBoost,XGBoost,ExtraTrees,and RandomForest.Among these,CatBoost demonstrated superior accuracy across multiple performance metrics.To further enhance predictive capability,several bio-inspired optimizers were employed for hyperparameter tuning.The SSO-CatBoost hybrid achieved the lowest mean squared error and highest correlation coefficients,outperforming other metaheuristic approaches such as Genetic Algorithm,Particle Swarm Optimization,and Grey Wolf Optimizer.Statistical significance was established through Analysis of Variance and Wilcoxon signed-rank testing,confirming the robustness of the optimized models.The proposed methodology not only delivers improved predictive performance but also offers a transparent framework for mix design optimization,supporting data-driven decision making in sustainable and resilient infrastructure development.展开更多
Colorectal cancer is the third most diagnosed cancer worldwide,and immune checkpoint inhibitors have shown promising therapeutic outcomes in selected patient groups.This study performed a comprehensive analysis of mul...Colorectal cancer is the third most diagnosed cancer worldwide,and immune checkpoint inhibitors have shown promising therapeutic outcomes in selected patient groups.This study performed a comprehensive analysis of multi-omics data from The Cancer Genome Atlas colorectal adenocarcinoma cohort(TCGA-COADREAD),accessed through cBioPortal,to develop machine learning models for predicting progression-free survival(PFS)following immunotherapy.The dataset included clinical variables,genomic alterations in Kirsten Rat Sarcoma Viral Oncogene Homolog(KRAS),B-Raf Proto-Oncogene(BRAF),and Neuroblastoma RAS Viral Oncogene Homolog(NRAS),microsatellite instability(MSI)status,tumor mutation burden(TMB),and expression of immune checkpoint genes.Kaplan–Meier analysis showed that KRAS mutations were significantly associated with reduced PFS,while BRAF and NRAS mutations had no significant impact.MSI-high tumors exhibited elevated TMB and increased immune checkpoint expression,reflecting their immunologically active phenotype.We developed both survival and classification models,with the Extra Trees classifier achieving the best performance(accuracy=0.86,precision=0.67,recall=0.70,F1-score=0.68,AUC=0.84).These findings highlight the potential of combining genomic and immune biomarkers with machine learning to improve patient stratification and guide personalized immunotherapy decisions.An interactive web application was also developed to enable clinicians to input patient-specific molecular and clinical data and visualize individualized PFS predictions,supporting timely,data-driven treatment planning.展开更多
Objectives:Decisions regarding CT after nCCRT for locally advanced rectal cancer(LARC)are challenging due to limited evidence guiding treatment.This study aimed to(i)evaluate the predictive performance of machine lear...Objectives:Decisions regarding CT after nCCRT for locally advanced rectal cancer(LARC)are challenging due to limited evidence guiding treatment.This study aimed to(i)evaluate the predictive performance of machine learning(ML)models in patients treated with neoadjuvant concurrent chemoradiotherapy(nCCRT)alone vs.those receiving nCCRT plus chemotherapy(CT),(ii)identify features associated with treatment improvement,and(iii)derive ML-based thresholds for treatment response.Methods:This retrospective study included 409 patients with LARC treated at three affiliated hospitals of Taipei Medical University.Patients were categorised into two groups:nCCRT alone followed by surgery(n=182)and nCCRT plus additional CT(n=227).Thirty-four baseline demographic,tumor,and laboratory variables were analysed.Four ML algorithms(K-Star,Random Forest,Multilayer Perceptron,and Random Committee)were evaluated,while five feature-ranking algorithms identified influential attributes among improved patients across both treatments.Decision Stump and AdaBoostM1 were applied to derive threshold-based patterns.Results:K-Star achieved the highest accuracy for nCCRT alone(80.8%;AUC=0.89),while Random Committee performed best for nCCRT plus CT(77.3%;AUC=0.84).Clinical N stage(cN)ranked highest,followed by Sodium(Na),Glutamic pyruvic transaminase,estimated glomerular filtration rate,body weight,red blood cell count,mean corpuscular hemoglobin concentration,and blood urea nitrogen.Threshold patterns suggested that CT-related improvement aligned with higher lymphocyte percentage and lower platelet distribution width,whereas nCCRT-only improvement aligned with elevated eGFR,GPT,and cN=2.Conclusions:ML-based analysis identified key predictors and demonstrated good model performance,supporting individualised post-nCCRT chemotherapy decisions.展开更多
基金funded by National Natural Science Foundation of China Key Program(12431014)Key Project of Hunan Education Department(22A0126)+1 种基金Natural Science Foundation of Hunan Province(2022JJ30555)Postgraduate Scientific Research Innovation Project of Xiangtan University(XDCX2024Y172)。
文摘Tropospheric zenith wet delay(ZWD)plays a vital role in the analysis of space geodetic observations.In recent years,machine learning methods have been increasingly applied to improve the accuracy of ZWD calculations.However,a single machine learning model has limited generalization capabilities.To address these limitations,this study introduces a novel machine learning fusion(MLF)algorithm with stronger generalization capabilities to enhance ZWD modeling and prediction accuracy.The MLF algorithm utilizes a two-layer structure integrating extra trees(ET),backpropagation neural network(BPNN),and linear regression models.By comparing the root mean square error(RMSE)of these models,we found that both ET-based and MLF-based models outperform RF-based and BPNN-based models in terms of internal and external accuracy,across both surface meteorological data-based and blind models.The improvement in exte rnal accuracy is particularly significant in the blind models.Our re sults show that the MLF(with an RMSE of 3.93 cm)and ET(3.99 cm)models outperform the traditional GPT3model(4.07 cm),while the RF(4.21 cm)and BPNN(4.14 cm)have worse external accuracies than the GPT3 model.It is worth noting that the BPNN suffered from overfitting during external accuracy tests,which was avoided by the MLF.In summary,regardless of the availability of surface meteorological data,the MLF-based empirical models demonstrate superior internal and external accuracy compared to the other tested models in this study.
基金Guangzhou Metro Scientific Research Project(No.JT204-100111-23001)Chongqing Municipal Special Project for Technological Innovation and Application Development(No.CSTB2022TIAD-KPX0101)Science and Technology Research and Development Program of China State Railway Group Co.,Ltd.(No.N2023G045)。
文摘The uplift resistance of the soil overlying shield tunnels significantly impacts their anti-floating stability.However,research on uplift resistance concerning special-shaped shield tunnels is limited.This study combines numerical simulation with machine learning techniques to explore this issue.It presents a summary of special-shaped tunnel geometries and introduces a shape coefficient.Through the finite element software,Plaxis3D,the study simulates six key parameters—shape coefficient,burial depth ratio,tunnel’s longest horizontal length,internal friction angle,cohesion,and soil submerged bulk density—that impact uplift resistance across different conditions.Employing XGBoost and ANN methods,the feature importance of each parameter was analyzed based on the numerical simulation results.The findings demonstrate that a tunnel shape more closely resembling a circle leads to reduced uplift resistance in the overlying soil,whereas other parameters exhibit the contrary effects.Furthermore,the study reveals a diminishing trend in the feature importance of buried depth ratio,internal friction angle,tunnel longest horizontal length,cohesion,soil submerged bulk density,and shape coefficient in influencing uplift resistance.
基金supported by the National Natural Science Foundation of China (42505149,41925023,U2342223,42105069,and 91744208)the China Postdoctoral Science Foundation (2025M770303)+1 种基金the Fundamental Research Funds for the Central Universities (14380230)the Jiangsu Funding Program for Excellent Postdoctoral Talent,and Jiangsu Collaborative Innovation Center of Climate Change。
文摘Countries around the world have been making efforts to reduce pollutant emissions. However, the response of global black carbon(BC) aging to emission changes remains unclear. Using the Community Atmosphere Model version 6 with a machine-learning-integrated four-mode version of the Modal Aerosol Module, we quantify global BC aging responses to emission reductions for 2011–2018 and for 2050 and 2100 under carbon neutrality. During 2011–18, global trends in BC aging degree(mass ratio of coatings to BC, R_(BC)) exhibited marked regional disparities, with a significant increase in China(5.4% yr^(-1)), which contrasts with minimal changes in the USA, Europe, and India. The divergence is attributed to opposing trends in secondary organic aerosol(SOA) and sulfate coatings, driven by regional changes in the emission ratios of corresponding coating precursors to BC(volatile organic compounds-VOCs/BC and SO_(2)/BC). Projections under carbon neutrality reveal that R_(BC) will increase globally by 47%(118%) in 2050(2100), with strong convergent increases expected across major source regions. The R_(BC) increase, primarily driven by enhanced SOA coatings due to sharper BC reductions relative to VOCs, will enhance the global BC mass absorption cross-section(MAC) by 11%(17%) in 2050(2100).Consequently, although the global BC burden will decline sharply by 60%(76%), the enhanced MAC partially offsets the magnitude of the decline in the BC direct radiative effect, resulting in the moderation of global BC DRE decreases to 88%(92%) of the BC burden reductions in 2050(2100). This study highlights the globally enhanced BC aging and light absorption capacity under carbon neutrality, thereby partly offsetting the impact of BC direct emission reductions on future changes in BC radiative effects globally.
文摘The application and promotion of waste glass powder concrete(WGPC)cansignificantly alleviate the pressure of concrete material scarcity and environmental pollution.Compressive strength(CS)is a critical parameter for evaluating the efficacy of WGPC.Unlike conventional testing methods,machine learning techniques offer precise and reliable predictions of concrete’s compressive strength,especially in its long-term mechanical properties.In this work,four models,namely Multiple Linear Regression(MLR),Back Propagation Neural Network(BPNN),Support Vector Regression(SVR),and Random Forest Regression(RFR)were employed.Furthermore,particle swarm optimization(PSO)algorithm and cross-validation techniques were applied to fine-tune the model parameters,striving for peak prediction performance.The results indicated that optimized models generally exhibit enhanced predictive accuracy compared to their basic counterparts.Notably,the PSO-RFR model excels among all evaluated models,showcasing superior performance on the testing dataset.It achieves a coefficient of determination(R^(2))of 0.9231,a mean absolute error(MAE)of 2.1073,and a root mean square error(RMSE)of 3.6903.When compared to experimental results,the PSO-RFR and PSO-BPNN models demonstrate exceptional predictive accuracy.Notably,the PSO-BPNN model exhibits the closest R^(2)values between its training and test sets.This close alignment of R^(2)values between the training and testing sets reflects the PSO-BPNN model’s superior generalization ability for unseen data.The findings present an efficient method for predicting concrete’s compressive strength,contributing to the sustainable development of concrete materials,and providing theoretical support for their research and application.
基金Supported by CAS Basic and Interdisciplinary Frontier Scientific Research Pilot Project(XDB1190300,XDB1190302)Youth Innovation Promotion Association CAS(Y2021056)+1 种基金Joint Fund of the Yulin University and the Dalian National Laboratory for Clean Energy(YLU-DNL Fund 2022007)The special fund for Science and Technology Innovation Teams of Shanxi Province(202304051001007)。
文摘Cyclohexene is an important raw material in the production of nylon.Selective hydrogenation of benzene is a key method for preparing cyclohexene.However,the Ru catalysts used in current industrial processes still face challenges,including high metal usage,high process costs,and low cyclohexene yield.This study utilizes existing literature data combined with machine learning methods to analyze the factors influencing benzene conversion,cyclohexene selectivity,and yield in the benzene hydrogenation to cyclohexene reaction.It constructs predictive models based on XGBoost and Random Forest algorithms.After analysis,it was found that reaction time,Ru content,and space velocity are key factors influencing cyclohexene yield,selectivity,and benzene conversion.Shapley Additive Explanations(SHAP)analysis and feature importance analysis further revealed the contribution of each variable to the reaction outcomes.Additionally,we randomly generated one million variable combinations using the Dirichlet distribution to attempt to predict high-yield catalyst formulations.This paper provides new insights into the application of machine learning in heterogeneous catalysis and offers some reference for further research.
基金funded by the National Natural Science Foundation of China(No.22278443)CAMS Innovation Fund for Medical Sciences(No.2022-I2M-1-015)+3 种基金the Key R&D Program of Shandong Province(No.2021ZDSYS26)Xinjiang Uygur Autonomous Region Innovation Environment Construction Special Fund and Technology Innovation Base Construction Key Laboratory Open Project(No.2023D04065)2023 Xinjiang Uygur Autonomous Region Innovation Tianchi Talent Introduction Program for financial supportthe Key Project of Natural Science of Bengbu Medical University(No.2024byzd138).
文摘In the pharmaceutical field,machine learning can play an important role in drug development,production and treatment.Co-crystallization techniques have shown promising potential to enhance the properties of active pharmaceutical ingredients(APIs)such as solubility,permeability,and bioavailability,all without altering their chemical structure.This approach opens new avenues for developing natural products into effective drugs,especially those previously challenging in formulation.Emodin,an anthraquinone-based natural product,is a notable example due to its diverse biological activities;however,its physicochemical limitations,such as poor solubility and easy sublimation,restricted its clinical application.While various methods have improved emodin's physicochemical properties,research on its bioavailability remains limited.In our study,we summarize cocrystals and salts produced through co-crystallization technology and identify piperazine as a favorable coformer.Conflicting conclusions from computational chemistry and molecular modeling method and machine learning method regarding the formation of an emodin-piperazine cocrystal or salt led us to experimentally validate these possibilities.Ultimately,we successfully obtained the emodin-piperazine cocrystal,which were characterized and evaluated by several in vitro methods and pharmacokinetic studies.In addition,experiments have shown that emodin has a certain therapeutic effect on sepsis,so we also evaluated emodin-piperazine biological activity in a sepsis model.The results demonstrate that co-crystallization significantly enhances emodin's solubility,permeability,and bioavailability.Pharmacodynamic studies indicate that the emodin-piperazine cocrystal improves sepsis symptoms and provides protective effects against liver and kidney damage associated with sepsis.This study offers renewed hope for natural products with broad biological activities yet hindered by physicochemical limitations by advancing co-crystallization as a viable development approach.
基金supported by Project of National and Local Joint Engineering Research Center for Biomass Energy Development and Utilization(Harbin Institute of Technology,No.2021A004).
文摘Machine learning(ML)is recognized as a potent tool for the inverse design of environmental functional material,particularly for complex entities like biochar-based catalysts(BCs).Thus,the tailored BCs can have a distinct ability to trigger the nonradical pathway in advance oxidation processes(AOPs),promising a stable,rapid and selective degradation of persistent contaminants.However,due to the inherent“black box”nature and limitations of input features,results and conclusions derived from ML may not always be intuitively understood or comprehensively validated.To tackle this challenge,we linked the front-point interpretable analysis approaches with back-point density functional theory(DFT)calculations to form a chained learning strategy for deeper sight into the intrinsic activation mechanism of BCs in AOPs.At the front point,we conducted an easy-to-interpret meta-analysis to validate two strategies for enhancing nonradical pathways by increasing oxygen content and specific surface area(SSA),and prepared oxidized biochar(OBC500)and SSA-increased biochar(SBC900)by controlling pyrolysis conditions and modification methods.Subsequently,experimental results showed that OBC500 and SBC900 had distinct dominant degradation pathways for 1O2 generation and electron transfer,respectively.Finally,at the end point,DFT calculations revealed their active sites and degradation mechanisms.This chained learning strategy elucidates fundamental principles for BC inverse design and showcases the exceptional capacity to integrate computational techniques to accelerate catalyst inverse design.
基金extend their gratitude to the Deanship of Scientific Research,Vice Presidency for Graduate Studies and Scientific Research,King Faisal University,Saudi Arabia,for funding the publication of this work under the Ambitious Researcher program(Project No.KFU253806).
文摘Artificial intelligence(AI)based models have been used to predict the structural,optical,mechanical,and electrochemical properties of zinc oxide/graphene oxide nanocomposites.Machine learning(ML)models such as Artificial Neural Networks(ANN),Support Vector Regression(SVR),Multilayer Perceptron(MLP),and hybrid,along with fuzzy logic tools,were applied to predict the different properties like wavelength at maximum intensity(444 nm),crystallite size(17.50 nm),and optical bandgap(2.85 eV).While some other properties,such as energy density,power density,and charge transfer resistance,were also predicted with the help of datasets of 1000(80:20).In general,the energy parameters were predicted more accurately by hybrid models.The hydrothermal method was used to synthesize graphene oxide(GO)and zinc oxide(ZnO)nanocomposites.The increased surface area,conductivity,and stability of graphene oxide in zinc oxide nanoparticles make the composite an ideal option for energy storage.X-ray diffraction(XRD)confirmed the crystallite size of 17.41 nm for the nanocomposite and the presence of GO(12.8○)peaks.The scanning electron microscope(SEM)showed anchored wrinkled GO sheets on zinc oxide with an average particle size of 2.93μm.Energy-dispersive X-ray spectroscopy(EDX)confirmed the elemental composition,and Fouriertransform infrared spectroscopy(FTIR)revealed the impact of GO on functional groups and electrochemical behavior.Photoluminescence(PL)wavelength of(439 nm)and band gap of(2.81 eV)show that the material is suitable for energy applications in nanocomposites.Smart nanocomposite materials with improved performance in energy storage and related applications were fabricated by combining synthesis,characterization,fuzzy logic,and machine learning in this work.
基金funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R104)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Modern intrusion detection systems(MIDS)face persistent challenges in coping with the rapid evolution of cyber threats,high-volume network traffic,and imbalanced datasets.Traditional models often lack the robustness and explainability required to detect novel and sophisticated attacks effectively.This study introduces an advanced,explainable machine learning framework for multi-class IDS using the KDD99 and IDS datasets,which reflects real-world network behavior through a blend of normal and diverse attack classes.The methodology begins with sophisticated data preprocessing,incorporating both RobustScaler and QuantileTransformer to address outliers and skewed feature distributions,ensuring standardized and model-ready inputs.Critical dimensionality reduction is achieved via the Harris Hawks Optimization(HHO)algorithm—a nature-inspired metaheuristic modeled on hawks’hunting strategies.HHO efficiently identifies the most informative features by optimizing a fitness function based on classification performance.Following feature selection,the SMOTE is applied to the training data to resolve class imbalance by synthetically augmenting underrepresented attack types.The stacked architecture is then employed,combining the strengths of XGBoost,SVM,and RF as base learners.This layered approach improves prediction robustness and generalization by balancing bias and variance across diverse classifiers.The model was evaluated using standard classification metrics:precision,recall,F1-score,and overall accuracy.The best overall performance was recorded with an accuracy of 99.44%for UNSW-NB15,demonstrating the model’s effectiveness.After balancing,the model demonstrated a clear improvement in detecting the attacks.We tested the model on four datasets to show the effectiveness of the proposed approach and performed the ablation study to check the effect of each parameter.Also,the proposed model is computationaly efficient.To support transparency and trust in decision-making,explainable AI(XAI)techniques are incorporated that provides both global and local insight into feature contributions,and offers intuitive visualizations for individual predictions.This makes it suitable for practical deployment in cybersecurity environments that demand both precision and accountability.
文摘This study investigates the uncertain dynamic characterization of hybrid composite plates by employing advanced machine-assisted finite element methodologies.Hybrid composites,widely used in aerospace,automotive,and structural applications,often face variability in material properties,geometric configurations,and manufacturing processes,leading to uncertainty in their dynamic response.To address this,three surrogate-based machine learning approaches like radial basis function(RBF),multivariate adaptive regression splines(MARS),and polynomial neural networks(PNN)are integrated with a finite element framework to efficiently capture the stochastic behavior of these plates.The research focuses on predicting the first three natural frequencies under material uncertainties,which are critical to ensuring structural reliability.Monte Carlo simulation(MCS)is used as a benchmark for generating probabilistic datasets,including mean values,standard deviations,and probability density functions.The surrogate models are then trained and validated against these datasets,enabling accurate representation of uncertainty with substantially fewer samples compared to conventionalMCS.Among the methods studied,the RBFmodel demonstrates superior performance,closely approximating MCS results with a reduced sample size,thereby achieving significant computational savings.The proposed framework not only reduces computational time and costs but also maintains high predictive accuracy,making it well-suited for complex engineering systems.Beyond free vibration analysis,the methodology can be extended to more sophisticated scenarios,such as forced vibration,damping effects,and nonlinear structural responses.Overall,this work presents a computationally efficient and robust approach for surrogate-based uncertainty quantification,advancing the analysis and design of hybrid composite structures under uncertainty.
文摘Post-kidney transplant rejection is a critical factor influencing transplant success rates and the survival of transplanted organs.With the rapid advancement of artificial intelligence technologies,machine learning(ML)has emerged as a powerful data analysis tool,widely applied in the prediction,diagnosis,and mechanistic study of kidney transplant rejection.This mini-review systematically summarizes the recent applications of ML techniques in post-kidney transplant rejection,covering areas such as the construction of predictive models,identification of biomarkers,analysis of pathological images,assessment of immune cell infiltration,and formulation of personalized treatment strategies.By integrating multi-omics data and clinical information,ML has significantly enhanced the accuracy of early rejection diagnosis and the capability for prognostic evaluation,driving the development of precision medicine in the field of kidney transplantation.Furthermore,this article discusses the challenges faced in existing research and potential future directions,providing a theoretical basis and technical references for related studies.
基金supported by Guangdong Basic and Applied Basic Research Foundation(Nos.2021B1515120055 and 2022A1515010499).
文摘Urban rainwater runoff is an important source of nonpoint source pollution due to its transport of diverse contaminants,including polycyclic aromatic hydrocarbons(PAHs)and chlorinated derivatives.Importantly,these chlorinated polycyclic aromatic hydrocarbons(Cl-PAHs)exhibit elevated toxicological potential compared to their non-halogenated parent compounds.In this study,we proposed an approach that combined multivariate receptor model with integration of SHapley Additive exPlanations and Random Forest model.This method identifies the possible sources and reveals the impact of source apportionment results and environmental driving factors(such as geographical and meteorological data)on pollutant concentrations.Sixteen PAHs and nine ClPAHs were detected in 79 runoff samples from all three sites.TheΣ_(16)PAHs average concentration(2923.93 to 6071.83 ng/L)was significantly higher than theΣ_(9)Cl-PAHs(384.34 to 1314.73 ng/L).The source apportionment was conducted by positive matrix factorization(PMF),and six potential pollution sources for PAHs and three for Cl-PAHs were quantified.PAHs primarily originate from the combustion of fossil fuels such as traffic,industrial emissions and coal tar,while Cl-PAHs are mainly derived from atmospheric deposition and industrial emissions.Meanwhile,the self‑organizing map classified PAHs and Cl-PAHs into 2 and 3 groups,respectively.The k-means algorithm yielded 4 clusters for runoff samples.Among machine learning models,Random Forest(RF)demonstrated optimal predictive performance and integrated with SHapley Additive exPlanations(RF-SHAP)revealed the effects of driving factors on the predicted concentration of PAHs and Cl-PAHs in urban runoff samples.
基金supported by the National Natural Science Foundation of China under Grant U2442219Fengyun Satellite Application Pioneer Program(2023)Special Initiative on Numerical Weather Prediction(NWP)Applications,the Civil Aerospace Technology Pre-Research Project(D040405)the Joint Funds of the Zhejiang Provincial Natural Science Foundation of China under Grant No.LZJMZ23D050003。
文摘Accurate retrieval of atmospheric vertical profiles is critical for improving weather prediction and climate monitoring.However,the complexity of atmospheric processes in cloudy regions poses challenges compared to those of clear sky scenarios.This study presents a novel framework that integrates Bayesian optimization and machine learning approaches to retrieve atmospheric vertical profiles—including temperature,humidity,ozone concentration,cloud fraction,ice water content(IWC),and liquid water content(LWC)—from hyperspectral infrared observations.Specifically,a Bayesian method was used to refine ERA5 reanalysis data by minimizing brightness temperature(BT)discrepancies against FY-4B Geostationary Interferometric Infrared Sounder(GIIRS)observations,generating a high-quality profile database(~2.8 million profiles)across diverse weather systems.The optimized profiles improve radiative consistency,reducing BT biases from>40 K to<10 K in cloudy regions.To further overcome the limitations of the Bayesian method,we developed a Transformer-Resnet hybrid model(TERNet),which achieved superior performance with RMSE values of 1.61 K(temperature),5.77%(humidity),and 2.25×10^(–6)/6.09×10^(–6)kg kg^(–1)(IWC/LWC)across the entire vertical levels in all-sky conditions.The TERNet outperforms both ERA5 in cloud parameter retrieval and the GIIRS L2 product in thermodynamic profiling.Independent verification with radiosonde and Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observations(CALIPSO)datasets confirms the framework's reliability across various meteorological regimes.This work demonstrates the capability of combining physics-informed Bayesian methods with data-driven machine learning to fully exploit hyperspectral IR data.
基金supported by the special fund of the National Clinical Key Specialty Construction Program[(2022)301-2305].
文摘BACKGROUND:This study aims to develop and validate a machine learning-based in-hospital mortality predictive model for acute aortic syndrome(AAS)in the emergency department(ED)and to derive a simplifi ed version suitable for rapid clinical application.METHODS:In this multi-center retrospective cohort study,AAS patient data from three hospitals were analyzed.The modeling cohort included data from the First Affiliated Hospital of Zhengzhou University and the People’s Hospital of Xinjiang Uygur Autonomous Region,with Peking University Third Hospital data serving as the external test set.Four machine learning algorithms—logistic regression(LR),multilayer perceptron(MLP),Gaussian naive Bayes(GNB),and random forest(RF)—were used to develop predictive models based on 34 early-accessible clinical variables.A simplifi ed model was then derived based on fi ve key variables(Stanford type,pericardial eff usion,asymmetric peripheral arterial pulsation,decreased bowel sounds,and dyspnea)via Least Absolute Shrinkage and Selection Operator(LASSO)regression to improve ED applicability.RESULTS:A total of 929 patients were included in the modeling cohort,and 210 were included in the external test set.Four machine learning models based on 34 clinical variables were developed,achieving internal and external validation AUCs of 0.85-0.90 and 0.73-0.85,respectively.The simplifi ed model incorporating fi ve key variables demonstrated internal and external validation AUCs of 0.71-0.86 and 0.75-0.78,respectively.Both models showed robust calibration and predictive stability across datasets.CONCLUSION:Both kinds of models were built based on machine learning tools,and proved to have certain prediction performance and extrapolation.
基金financially supported by National Natural Science Foundation ofChina(No.12374405)Provincial Science Foundation for Distinguished Young Scholars of Fujian(No.2024J010024)+1 种基金Natural Science Foundation of Fujian Province of China(No.2023J011267)Major Research Projects for Young and Middle-aged Researchers of Fujian Provincial Health Commission(No.2021ZQNZD010).
文摘Nasopharyngeal carcinoma(NPC)is a malignant tumor prevalent in southern China and Southeast Asia,where its early detection is crucial for improving patient prognosis and reducing mortality rates.However,existing screening methods suffer from limitations in accuracy and accessibility,hindering their application in large-scale population screening.In this work,a surface-enhanced Raman spectroscopy(SERS)-based method was established to explore the profiles of different stratified components in saliva from NPC and healthy subjects after fractionation processing.The study findings indicate that all fractionated samples exhibit diseaseassociated molecular signaling differences,where small-molecule(molecular weight cut-offvalue is 10 kDa)demonstrating superior classification capabilities with sensitivity of 90.5%and speci-ficity of 75.6%,area under receiver operating characteristic(ROC)curve of 0:925±0:031.The primary objective of this study was to qualitatively explore patterns in saliva composition across groups.The proposed SERS detection strategy for fractionated saliva offers novel insights for enhancing the sensitivity and reliability of noninvasive NPC screening,laying the foundation for translational application in large-scale clinical settings.
基金Project(42077244)supported by the National Natural Science Foundation of ChinaProject(2020-05)supported by the Open Research Fund of Guangdong Provincial Key Laboratory of Deep Earth Sciences and Geothermal Energy Exploitation and Utilization,China。
文摘Accurate prediction of rockburst intensity levels is crucial for ensuring the safety of deep hard rock engineering construction.This paper introduced an expert system for rockburst intensity level prediction that employs machine learning algorithms as the basis for its inference rules.The system comprises four modules:a database,a repository,an inference engine,and an interpreter.A database containing 1114 rockburst cases was used to construct 357 datasets that serve as the repository for the expert system.Additionally,19 types of machine learning algorithms were used to establish 6783 micro-models to construct cognitive rules within the inference engine.By integrating probability theory and marginal analysis,a fuzzy scoring method based on the SoftMax function was developed and applied to the interpreter for rockburst intensity level prediction,effectively restoring the continuity of rockburst characteristics.The research results indicate that ensemble algorithms based on decision trees are more effective in capturing the characteristics of rockburst.Key factors for accurate prediction of rockburst intensity include uniaxial compressive strength,elastic energy index,the maximum principal stress,tangential stress,and their composite indicators.The accuracy of the proposed rockburst intensity level prediction expert system was verified using 20 engineering rockburst cases,with predictions aligning closely with the actual rockburst intensity levels.
基金funded by Princess Nourah bint Abdulrahman University Researchers Support-ing Project number(PNURSP2026R346)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Motor imbalance is a critical failure mode in rotating machinery,potentially causing severe equipment damage if undetected.Traditional vibration-based diagnostic methods rely on direct sensor contact,leading to installation challenges and measurement artifacts that can compromise accuracy.This study presents a novel radar-based framework for non-contact motor imbalance detection using 24 GHz continuous-wave radar.A dataset of 1802 experimental trials was sourced,covering four imbalance levels(0,10,20,30 g)across varying motor speeds(500–1500 rpm)and load torques(0–3 Nm).Dual-channel in-phase and quadrature radar signals were captured at 10,000 samples per second for 30-s intervals,preserving both amplitude and phase information for analysis.A multi-domain feature extraction methodology captured imbalance signatures in time,frequency,and complex signal domains.From 65 initial features,statistical analysis using Kruskal–Wallis tests identified significant descriptors,and recursive feature elimination with Random Forest reduced the feature set to 20 dimensions,achieving 69%dimensionality reduction without loss of performance.Six machine learning algorithms,Random Forest,Extra Trees Classifier,Extreme Gradient Boosting,Categorical Boosting,Support Vector Machine with radial basis function kernel,and k-Nearest Neighbors were evaluated with grid-search hyperparameter optimization and five-fold cross-validation.The Extra Trees Classifier achieved the best performance with 98.52%test accuracy,98%cross-validation accuracy,and minimal variance,maintaining per-class precision and recall above 97%.Its superior performance is attributed to its randomized split selection and full bootstrapping strategy,which reduce variance and overfitting while effectively capturing the nonlinear feature interactions and non-normal distributions present in the dataset.The model’s average inference time of 70 ms enables near real-time deployment.Comparative analysis demonstrates that the radar-based framework matches or exceeds traditional contact-based methods while eliminating their inherent limitations,providing a robust,scalable,and noninvasive solution for industrial motor condition monitoring,particularly in hazardous or space-constrained environments.
文摘Accurate prediction of concrete compressive strength is fundamental for optimizing mix designs,improving material utilization,and ensuring structural safety in modern construction.Traditional empirical methods often fail to capture the non-linear relationships among concrete constituents,especially with the growing use of supple-mentary cementitious materials and recycled aggregates.This study presents an integrated machine learning framework for concrete strength prediction,combining advanced regression models—namely CatBoost—with metaheuristic optimization algorithms,with a particular focus on the Somersaulting Spider Optimizer(SSO).A comprehensive dataset encompassing diverse mix proportions and material types was used to evaluate baseline machine learning models,including CatBoost,XGBoost,ExtraTrees,and RandomForest.Among these,CatBoost demonstrated superior accuracy across multiple performance metrics.To further enhance predictive capability,several bio-inspired optimizers were employed for hyperparameter tuning.The SSO-CatBoost hybrid achieved the lowest mean squared error and highest correlation coefficients,outperforming other metaheuristic approaches such as Genetic Algorithm,Particle Swarm Optimization,and Grey Wolf Optimizer.Statistical significance was established through Analysis of Variance and Wilcoxon signed-rank testing,confirming the robustness of the optimized models.The proposed methodology not only delivers improved predictive performance but also offers a transparent framework for mix design optimization,supporting data-driven decision making in sustainable and resilient infrastructure development.
基金funded by the Research,Development,and Innovation Authority(RDIA)—Kingdom of Saudi Arabia(Grant No.13292-psu-2023-PSNU-R-3-1-EF-).
文摘Colorectal cancer is the third most diagnosed cancer worldwide,and immune checkpoint inhibitors have shown promising therapeutic outcomes in selected patient groups.This study performed a comprehensive analysis of multi-omics data from The Cancer Genome Atlas colorectal adenocarcinoma cohort(TCGA-COADREAD),accessed through cBioPortal,to develop machine learning models for predicting progression-free survival(PFS)following immunotherapy.The dataset included clinical variables,genomic alterations in Kirsten Rat Sarcoma Viral Oncogene Homolog(KRAS),B-Raf Proto-Oncogene(BRAF),and Neuroblastoma RAS Viral Oncogene Homolog(NRAS),microsatellite instability(MSI)status,tumor mutation burden(TMB),and expression of immune checkpoint genes.Kaplan–Meier analysis showed that KRAS mutations were significantly associated with reduced PFS,while BRAF and NRAS mutations had no significant impact.MSI-high tumors exhibited elevated TMB and increased immune checkpoint expression,reflecting their immunologically active phenotype.We developed both survival and classification models,with the Extra Trees classifier achieving the best performance(accuracy=0.86,precision=0.67,recall=0.70,F1-score=0.68,AUC=0.84).These findings highlight the potential of combining genomic and immune biomarkers with machine learning to improve patient stratification and guide personalized immunotherapy decisions.An interactive web application was also developed to enable clinicians to input patient-specific molecular and clinical data and visualize individualized PFS predictions,supporting timely,data-driven treatment planning.
基金funded by the Australian National Health and Medical Research Council(Grant No.GNT1192469)supported by the Research Technology Services at the University of New South Wales Sydney,Google Cloud Research(Award No.GCP19980904)。
文摘Objectives:Decisions regarding CT after nCCRT for locally advanced rectal cancer(LARC)are challenging due to limited evidence guiding treatment.This study aimed to(i)evaluate the predictive performance of machine learning(ML)models in patients treated with neoadjuvant concurrent chemoradiotherapy(nCCRT)alone vs.those receiving nCCRT plus chemotherapy(CT),(ii)identify features associated with treatment improvement,and(iii)derive ML-based thresholds for treatment response.Methods:This retrospective study included 409 patients with LARC treated at three affiliated hospitals of Taipei Medical University.Patients were categorised into two groups:nCCRT alone followed by surgery(n=182)and nCCRT plus additional CT(n=227).Thirty-four baseline demographic,tumor,and laboratory variables were analysed.Four ML algorithms(K-Star,Random Forest,Multilayer Perceptron,and Random Committee)were evaluated,while five feature-ranking algorithms identified influential attributes among improved patients across both treatments.Decision Stump and AdaBoostM1 were applied to derive threshold-based patterns.Results:K-Star achieved the highest accuracy for nCCRT alone(80.8%;AUC=0.89),while Random Committee performed best for nCCRT plus CT(77.3%;AUC=0.84).Clinical N stage(cN)ranked highest,followed by Sodium(Na),Glutamic pyruvic transaminase,estimated glomerular filtration rate,body weight,red blood cell count,mean corpuscular hemoglobin concentration,and blood urea nitrogen.Threshold patterns suggested that CT-related improvement aligned with higher lymphocyte percentage and lower platelet distribution width,whereas nCCRT-only improvement aligned with elevated eGFR,GPT,and cN=2.Conclusions:ML-based analysis identified key predictors and demonstrated good model performance,supporting individualised post-nCCRT chemotherapy decisions.
