Customer churn is the rate at which customers discontinue doing business with a company over a given time period.It is an essential measure for businesses to monitor high churn rates,as they often indicate underlying ...Customer churn is the rate at which customers discontinue doing business with a company over a given time period.It is an essential measure for businesses to monitor high churn rates,as they often indicate underlying issues with services,products,or customer experience,resulting in considerable income loss.Prediction of customer churn is a crucial task aimed at retaining customers and maintaining revenue growth.Traditional machine learning(ML)models often struggle to capture complex temporal dependencies in client behavior data.To address this,an optimized deep learning(DL)approach using a Regularized Bidirectional Long Short-Term Memory(RBiLSTM)model is proposed to mitigate overfitting and improve generalization error.The model integrates dropout,L2-regularization,and early stopping to enhance predictive accuracy while preventing over-reliance on specific patterns.Moreover,this study investigates the effect of optimization techniques on boosting the training efficiency of the developed model.Experimental results on a recent public customer churn dataset demonstrate that the trained model outperforms the traditional ML models and some other DL models,such as Long Short-Term Memory(LSTM)and Deep Neural Network(DNN),in churn prediction performance and stability.The proposed approach achieves 96.1%accuracy,compared with LSTM and DNN,which attain 94.5%and 94.1%accuracy,respectively.These results confirm that the proposed approach can be used as a valuable tool for businesses to identify at-risk consumers proactively and implement targeted retention strategies.展开更多
Machine learning-assisted methods for rapid and accurate prediction of temperature field,mushy zone,and grain size were proposed for the heating−cooling combined mold(HCCM)horizontal continuous casting of C70250 alloy...Machine learning-assisted methods for rapid and accurate prediction of temperature field,mushy zone,and grain size were proposed for the heating−cooling combined mold(HCCM)horizontal continuous casting of C70250 alloy plates.First,finite element simulations of casting processes were carried out with various parameters to build a dataset.Subsequently,different machine learning algorithms were employed to achieve high precision in predicting temperature fields,mushy zone locations,mushy zone inclination angle,and billet grain size.Finally,the process parameters were quickly optimized using a strategy consisting of random generation,prediction,and screening,allowing the mushy zone to be controlled to the desired target.The optimized parameters are 1234℃for heating mold temperature,47 mm/min for casting speed,and 10 L/min for cooling water flow rate.The optimized mushy zone is located in the middle of the second heat insulation section and has an inclination angle of roughly 7°.展开更多
Current shipping,tourism,and resource development requirements call for more accurate predictions of the Arctic sea-ice concentration(SIC).However,due to the complex physical processes involved,predicting the spatiote...Current shipping,tourism,and resource development requirements call for more accurate predictions of the Arctic sea-ice concentration(SIC).However,due to the complex physical processes involved,predicting the spatiotemporal distribution of Arctic SIC is more challenging than predicting its total extent.In this study,spatiotemporal prediction models for monthly Arctic SIC at 1-to 3-month leads are developed based on U-Net-an effective convolutional deep-learning approach.Based on explicit Arctic sea-ice-atmosphere interactions,11 variables associated with Arctic sea-ice variations are selected as predictors,including observed Arctic SIC,atmospheric,oceanic,and heat flux variables at 1-to 3-month leads.The prediction skills for the monthly Arctic SIC of the test set(from January 2018 to December 2022)are evaluated by examining the mean absolute error(MAE)and binary accuracy(BA).Results showed that the U-Net model had lower MAE and higher BA for Arctic SIC compared to two dynamic climate prediction systems(CFSv2 and NorCPM).By analyzing the relative importance of each predictor,the prediction accuracy relies more on the SIC at the 1-month lead,but on the surface net solar radiation flux at 2-to 3-month leads.However,dynamic models show limited prediction skills for surface net solar radiation flux and other physical processes,especially in autumn.Therefore,the U-Net model can be used to capture the connections among these key physical processes associated with Arctic sea ice and thus offers a significant advantage in predicting Arctic SIC.展开更多
Predicting monsoon climate is one of the major endeavors in climate science and is becoming increasingly challenging due to global warming. The accuracy of monsoon seasonal predictions significantly impacts the lives ...Predicting monsoon climate is one of the major endeavors in climate science and is becoming increasingly challenging due to global warming. The accuracy of monsoon seasonal predictions significantly impacts the lives of billions who depend on or are affected by monsoons, as it is essential for the water cycle, food security, ecology, disaster prevention, and the economy of monsoon regions. Given the extensive literature on Asian monsoon climate prediction, we limit our focus to reviewing the seasonal prediction and predictability of the Asian Summer Monsoon (ASM). However, much of this review is also relevant to monsoon predictions in other seasons and regions. Over the past two decades, considerable progress has been made in the seasonal forecasting of the ASM, driven by an enhanced understanding of the sources of predictability and the dynamics of seasonal variability, along with advanced development in sophisticated models and technologies. This review centers on advances in understanding the physical foundation for monsoon climate prediction (section 2), significant findings and insights into the primary and regional sources of predictability arising from feedback processes among various climate components (sections 3 and 4), the effects of global warming and external forcings on predictability (section 5), developments in seasonal prediction models and techniques (section 6), the challenges and limitations of monsoon climate prediction (section 7), and emerging research trends with suggestions for future directions (section 8). We hope this review will stimulate creative activities to enhance monsoon climate prediction.展开更多
To investigate the influence of coarse aggregate parent rock properties on the elastic modulus of concrete,the mineralogical properties and stress-strain curves of granite and dolomite parent rocks,as well as the stre...To investigate the influence of coarse aggregate parent rock properties on the elastic modulus of concrete,the mineralogical properties and stress-strain curves of granite and dolomite parent rocks,as well as the strength and elastic modulus of mortar and concrete prepared with mechanism aggregates of the corresponding lithology,and the stress-strain curves of concrete were investigated.In this paper,a coarse aggregate and mortar matrix bonding assumption is proposed,and a prediction model for the elastic modulus of mortar is established by considering the lithology of the mechanism sand and the slurry components.An equivalent coarse aggregate elastic modulus model was established by considering factors such as coarse aggregate particle size,volume fraction,and mortar thickness between coarse aggregates.Based on the elastic modulus of the equivalent coarse aggregate and the remaining mortar,a prediction model for the elastic modulus of the two and three components of concrete in series and then in parallel was established,and the predicted values differed from the measured values within 10%.It is proposed that the coarse aggregate elastic modulus in highstrength concrete is the most critical factor affecting the elastic modulus of concrete,and as the coarse aggregate elastic modulus increases by 27.7%,the concrete elastic modulus increases by 19.5%.展开更多
Accurate prediction of flood events is important for flood control and risk management.Machine learning techniques contributed greatly to advances in flood predictions,and existing studies mainly focused on predicting...Accurate prediction of flood events is important for flood control and risk management.Machine learning techniques contributed greatly to advances in flood predictions,and existing studies mainly focused on predicting flood resource variables using single or hybrid machine learning techniques.However,class-based flood predictions have rarely been investigated,which can aid in quickly diagnosing comprehensive flood characteristics and proposing targeted management strategies.This study proposed a prediction approach of flood regime metrics and event classes coupling machine learning algorithms with clustering-deduced membership degrees.Five algorithms were adopted for this exploration.Results showed that the class membership degrees accurately determined event classes with class hit rates up to 100%,compared with the four classes clustered from nine regime metrics.The nonlinear algorithms(Multiple Linear Regression,Random Forest,and least squares-Support Vector Machine)outperformed the linear techniques(Multiple Linear Regression and Stepwise Regression)in predicting flood regime metrics.The proposed approach well predicted flood event classes with average class hit rates of 66.0%-85.4%and 47.2%-76.0%in calibration and validation periods,respectively,particularly for the slow and late flood events.The predictive capability of the proposed prediction approach for flood regime metrics and classes was considerably stronger than that of hydrological modeling approach.展开更多
Influenced by complex external factors,the displacement-time curve of reservoir landslides demonstrates both short-term and long-term diversity and dynamic complexity.It is difficult for existing methods,including Reg...Influenced by complex external factors,the displacement-time curve of reservoir landslides demonstrates both short-term and long-term diversity and dynamic complexity.It is difficult for existing methods,including Regression models and Neural network models,to perform multi-characteristic coupled displacement prediction because they fail to consider landslide creep characteristics.This paper integrates the creep characteristics of landslides with non-linear intelligent algorithms and proposes a dynamic intelligent landslide displacement prediction method based on a combination of the Biological Growth model(BG),Convolutional Neural Network(CNN),and Long ShortTerm Memory Network(LSTM).This prediction approach improves three different biological growth models,thereby effectively extracting landslide creep characteristic parameters.Simultaneously,it integrates external factors(rainfall and reservoir water level)to construct an internal and external comprehensive dataset for data augmentation,which is input into the improved CNN-LSTM model.Thereafter,harnessing the robust feature extraction capabilities and spatial translation invariance of CNN,the model autonomously captures short-term local fluctuation characteristics of landslide displacement,and combines LSTM's efficient handling of long-term nonlinear temporal data to improve prediction performance.An evaluation of the Liangshuijing landslide in the Three Gorges Reservoir Area indicates that BG-CNN-LSTM exhibits high prediction accuracy,excellent generalization capabilities when dealing with various types of landslides.The research provides an innovative approach to achieving the whole-process,realtime,high-precision displacement predictions for multicharacteristic coupled landslides.展开更多
A new unified constitutive model was developed to predict the two-stage creep-aging(TSCA)behavior of Al-Zn-Mg-Cu alloys.The particular bimodal precipitation feature was analyzed and modeled by considering the primary ...A new unified constitutive model was developed to predict the two-stage creep-aging(TSCA)behavior of Al-Zn-Mg-Cu alloys.The particular bimodal precipitation feature was analyzed and modeled by considering the primary micro-variables evolution at different temperatures and their interaction.The dislocation density was incorporated into the model to capture the effect of creep deformation on precipitation.Quantitative transmission electron microscopy and experimental data obtained from a previous study were used to calibrate the model.Subsequently,the developed constitutive model was implemented in the finite element(FE)software ABAQUS via the user subroutines for TSCA process simulation and the springback prediction of an integral panel.A TSCA test was performed.The result shows that the maximum radius deviation between the formed plate and the simulation results is less than 0.4 mm,thus validating the effectiveness of the developed constitutive model and FE model.展开更多
Background: Pancreatic cancer is one of the most lethal malignancies, with postoperative recurrence severely affecting patient survival and prognosis. This study aims to develop and validate a clinical prediction mode...Background: Pancreatic cancer is one of the most lethal malignancies, with postoperative recurrence severely affecting patient survival and prognosis. This study aims to develop and validate a clinical prediction model for postoperative recurrence in pancreatic cancer patients, incorporating multiple preoperative, intraoperative, and postoperative factors to assist clinical decision-making. Methods: A retrospective study was conducted on 216 patients who underwent surgical treatment for pancreatic malignancy at the First Affiliated Hospital of Chongqing Medical University between January 2015 and January 2023. An independent external validation cohort of 76 patients from the Second Affiliated Hospital of Chongqing Medical University was used to validate the model. Seven independent risk factors for postoperative recurrence were identified through univariate and multivariate Cox regression analyses. The model’s performance was evaluated using the concordance index (C-index) and ROC curves, and its accuracy and clinical value were assessed using calibration curves and decision curve analysis (DCA). Results: The predictive model demonstrated good discriminatory power, with a C-index of 0.72 in the training cohort and 0.66 in the validation cohort. The ROC curves for predicting recurrence at 3, 6, and 12 months postoperatively showed AUC values ranging from 0.72 to 0.83, indicating strong predictive value. Calibration curves and DCA confirmed the model’s accuracy and clinical utility. Conclusion: This study successfully developed and validated a clinical prediction model that incorporates seven independent risk factors for postoperative recurrence in pancreatic cancer. The model provides a useful tool for predicting recurrence risk, aiding in the identification of high-risk patients, and informing clinical decision-making.展开更多
With the rapid development of economy,air pollution caused by industrial expansion has caused serious harm to human health and social development.Therefore,establishing an effective air pollution concentration predict...With the rapid development of economy,air pollution caused by industrial expansion has caused serious harm to human health and social development.Therefore,establishing an effective air pollution concentration prediction system is of great scientific and practical significance for accurate and reliable predictions.This paper proposes a combination of pointinterval prediction system for pollutant concentration prediction by leveraging neural network,meta-heuristic optimization algorithm,and fuzzy theory.Fuzzy information granulation technology is used in data preprocessing to transform numerical sequences into fuzzy particles for comprehensive feature extraction.The golden Jackal optimization algorithm is employed in the optimization stage to fine-tune model hyperparameters.In the prediction stage,an ensemble learning method combines training results frommultiplemodels to obtain final point predictions while also utilizing quantile regression and kernel density estimation methods for interval predictions on the test set.Experimental results demonstrate that the combined model achieves a high goodness of fit coefficient of determination(R^(2))at 99.3% and a maximum difference between prediction accuracy mean absolute percentage error(MAPE)and benchmark model at 12.6%.This suggests that the integrated learning system proposed in this paper can provide more accurate deterministic predictions as well as reliable uncertainty analysis compared to traditionalmodels,offering practical reference for air quality early warning.展开更多
AIM:To explore the relationship between matrix metalloproteinases(MMPs)expression levels in the tumor and the prognosis of uveal melanoma(UM)and to construct prognostic prediction models.METHODS:Transcriptome sequenci...AIM:To explore the relationship between matrix metalloproteinases(MMPs)expression levels in the tumor and the prognosis of uveal melanoma(UM)and to construct prognostic prediction models.METHODS:Transcriptome sequencing data from 17 normal choroid tissues and 53 UM tumor tissues were collected.Based on the differential gene expression levels and their function,MMPs family was selected for establishing risk-score system and prognostic prediction model with machine learning.Tumor microenvironment(TME)analysis was also applied for the impact of immune cell infiltration on prognosis of the disease.RESULTS:Eight MMPs were significantly different expression levels between normal and the tumor tissues.MMP-2 and MMP-28 were selected to construct a risk-score system and divided patients accordingly into high-and low-risk groups.The prediction model based on the risk-score achieved an accuracy of approximately 80%at 1-,3-,and 5-year after diagnosis.Besides,a Nomogram prognostic prediction model which based on risk-score and pathological type(independent prognostic factors after Cox regression analysis)demonstrated good consistency between the predicted outcomes at 1-,3-,and 5-year after diagnosis and the actual prognosis of patients.TME analysis revealed that the high-risk group exhibited higher immune and stromal scores and increased infiltration of tumor-associated macrophages(TAMs)and regulatory T cells compared to the low-risk group.CONCLUSION:Based on MMP-2 and MMP-28 expression levels,our prediction model demonstrates accurate long-term prognosis prediction for UM patients.The aggregation of TAMs and regulatory T cells in the TME of UM may be associated with an unfavorable prognosis.展开更多
BACKGROUND Colorectal polyps(CPs)are important precursor lesions of colorectal cancer,and endoscopic surgery remains the primary treatment option.However,the shortterm recurrence rate post-surgery is high,and the risk...BACKGROUND Colorectal polyps(CPs)are important precursor lesions of colorectal cancer,and endoscopic surgery remains the primary treatment option.However,the shortterm recurrence rate post-surgery is high,and the risk factors for recurrence remain unknown.AIM To comprehensively explore risk factors for short-term recurrence of CPs after endoscopic surgery and develop a nomogram prediction model.METHODS Overall,362 patients who underwent endoscopic polypectomy between January 2022 and January 2024 at Nanjing Jiangbei Hospital were included.We screened basic demographic data,clinical and polyp characteristics,surgery-related information,and independent risk factors for CPs recurrence using univariate and multivariate logistic regression analyses.The multivariate analysis results were used to construct a nomogram prediction model,internally validated using Bootstrapping,with performance evaluated using area under the curve(AUC),calibration curve,and decision curve analysis.RESULTS CP re-occurred in 166(45.86%)of the 362 patients within 1 year post-surgery.Multivariate logistic regression analysis showed that age(OR=1.04,P=0.002),alcohol consumption(OR=2.07,P=0.012),Helicobacter pylori infection(OR=2.34,P<0.001),polyp number>2(OR=1.98,P=0.005),sessile polyps(OR=2.10,P=0.006),and adenomatous pathological type(OR=3.02,P<0.001)were independent risk factors for post-surgery recurrence.The nomogram prediction model showed good discriminatory(AUC=0.73)and calibrating power,and decision curve analysis showed that the model had good clinical benefit at risk probabilities>20%.CONCLUSION We identified multiple independent risk factors for short-term recurrence after endoscopic surgery.The nomogram prediction model showed a certain degree of differentiation,calibration,and potential clinical applicability.展开更多
The prediction of the rolling force and thickness ratio plays an important role in the development and application of bimetallic composite plates.To analyze the rolling force of the bimetallic composite plate more acc...The prediction of the rolling force and thickness ratio plays an important role in the development and application of bimetallic composite plates.To analyze the rolling force of the bimetallic composite plate more accurately,a novel hypothesis based on Orowan's theory was proposed.The variation in the thickness of each differential element at different positions was considered to establish the analytical model.According to the characteristics of bimetallic composite plate rolling,the rolling deformation can be divided into forward and backward slip zones.The initial thickness ratio after rolling was predetermined by the thickness ratio before rolling;the rolling force balance of the upper and lower rollers was considered the convergence condition;and the final thickness ratio of the bimetallic composite plate was obtained by iterative calculation.The calculation results of the analytical model were compared with the measured and simulated data.The results showed that the errors in the calculation of the rolling force and thickness ratio were both less than 10%.The analytical model has high precision,meets engineering requirements,and has important reference significance for rolling process optimization and thickness ratio prediction.展开更多
Systematic bias is a type of model error that can affect the accuracy of data assimilation and forecasting that must be addressed.An online bias correction scheme called the sequential bias correction scheme(SBCS),was...Systematic bias is a type of model error that can affect the accuracy of data assimilation and forecasting that must be addressed.An online bias correction scheme called the sequential bias correction scheme(SBCS),was developed using the6 h average bias to correct the systematic bias during model integration.The primary purpose of this study is to investigate the impact of the SBCS in the high-resolution China Meteorological Administration Meso-scale(CMA-MESO)numerical weather prediction(NWP)model to reduce the systematic bias and to improve the data assimilation and forecast results through this method.The SBCS is improved upon and applied to the CMA-MESO 3-km model in this study.Four-week sequential data assimilation and forecast experiments,driven by rapid update and cycling(RUC),were conducted for the period from 2–29 May 2022.In terms of the characteristics of systematic bias,both the background and analysis show diurnal bias,and these large biases are affected by complex underlying surfaces(e.g.,oceans,coasts,and mountains).After the application of the SBCS,the results of the data assimilation show that the SBCS can reduce the systematic bias of the background and yield a neutral to slightly positive result for the analysis fields.In addition,the SBCS can reduce forecast errors and improve forecast results,especially for surface variables.The above results indicate that this scheme has good prospects for high-resolution regional NWP models.展开更多
BACKGROUND Rabies is a zoonotic viral disease affecting the central nervous system,caused by the rabies virus,with a case-fatality rate of 100%once symptoms appear.AIM To analyze high-risk factors associated with ment...BACKGROUND Rabies is a zoonotic viral disease affecting the central nervous system,caused by the rabies virus,with a case-fatality rate of 100%once symptoms appear.AIM To analyze high-risk factors associated with mental disorders induced by rabies vaccination and to construct a risk prediction model to inform strategies for improving patients’mental health.METHODS Patients who received rabies vaccinations at the Department of Infusion Yiwu Central Hospital between August 2024 and July 2025 were included,totaling 384 cases.Data were collected from medical records and included demographic characteristics(age,gender,occupation),lifestyle habits,and details regarding vaccine type,dosage,and injection site.The incidence of psychiatric disorders following vaccination was assessed using standardized anxiety and depression rating scales.Patients were categorized into two groups based on the presence or absence of anxiety and depression symptoms:The psychiatric disorder group and the non-psychiatric disorder group.Differences between the two groups were compared,and high-risk factors were identified using multivariate logistic regression analysis.A predictive model was then developed based on these factors to evaluate its predictive performance.RESULTS Among the 384 patients who received rabies vaccinations,36 cases(9.38%)were diagnosed with anxiety,52 cases(13.54%)with depression,and 88 cases(22.92%)with either condition.Logistic regression analysis identified the following signi ficant risk factors for psychiatric disorders:Education level of primary school or below,exposure site at the head and neck,exposure classified as grade III,family status of divorced/widowed/unmarried/living alone,number of wounds greater than one,and low awareness of rabies prevention and control(P<0.05).The risk prediction model demonstrated good performance,with an area under the receiver operating characteristic curve of 0.859,a specificity of 74.42%,and a sensitivity of 93.02%.CONCLUSION In real-world settings,psychiatric disorders following rabies vaccination are relatively common and are associated with factors such as lower education level,higher exposure severity,vulnerable family status,and limited awareness of rabies prevention and control.The developed risk prediction model may aid in early identification of high-risk individuals and support timely clinical intervention.展开更多
Machine learning(ML)models are widely used for predicting undrained shear strength(USS),but interpretability has been a limitation in various studies.Therefore,this study introduced shapley additive explanations(SHAP)...Machine learning(ML)models are widely used for predicting undrained shear strength(USS),but interpretability has been a limitation in various studies.Therefore,this study introduced shapley additive explanations(SHAP)to clarify the contribution of each input feature in USS prediction.Three ML models,artificial neural network(ANN),extreme gradient boosting(XGBoost),and random forest(RF),were employed,with accuracy evaluated using mean squared error,mean absolute error,and coefficient of determination(R^(2)).The RF achieved the highest performance with an R^(2) of 0.82.SHAP analysis identified pre-consolidation stress as a key contributor to USS prediction.SHAP dependence plots reveal that the ANN captures smoother,linear feature-output relationships,while the RF handles complex,non-linear interactions more effectively.This suggests a non-linear relationship between USS and input features,with RF outperforming ANN.These findings highlight SHAP’s role in enhancing interpretability and promoting transparency and reliability in ML predictions for geotechnical applications.展开更多
Predicting information dissemination on social media,specifcally users’reposting behavior,is crucial for applications such as advertising campaigns.Conventional methods use deep neural networks to make predictions ba...Predicting information dissemination on social media,specifcally users’reposting behavior,is crucial for applications such as advertising campaigns.Conventional methods use deep neural networks to make predictions based on features related to user topic interests and social preferences.However,these models frequently fail to account for the difculties arising from limited training data and model size,which restrict their capacity to learn and capture the intricate patterns within microblogging data.To overcome this limitation,we introduce a novel model Adapt pre-trained Large Language model for Reposting Prediction(ALL-RP),which incorporates two key steps:(1)extracting features from post content and social interactions using a large language model with extensive parameters and trained on a vast corpus,and(2)performing semantic and temporal adaptation to transfer the large language model’s knowledge of natural language,vision,and graph structures to reposting prediction tasks.Specifcally,the temporal adapter in the ALL-RP model captures multi-dimensional temporal information from evolving patterns of user topic interests and social preferences,thereby providing a more realistic refection of user attributes.Additionally,to enhance the robustness of feature modeling,we introduce a variant of the temporal adapter that implements multiple temporal adaptations in parallel while maintaining structural simplicity.Experimental results on real-world datasets demonstrate that the ALL-RP model surpasses state-of-the-art models in predicting both individual user reposting behavior and group sharing behavior,with performance gains of 2.81%and 4.29%,respectively.展开更多
The Sawayaerdun gold deposit is the only extremely large deposit occurring in the giant gold metallogenic belt of the Central Asian Tianshan Orogenic Belt.Breakthroughs in deep and peripheral exploration are of great ...The Sawayaerdun gold deposit is the only extremely large deposit occurring in the giant gold metallogenic belt of the Central Asian Tianshan Orogenic Belt.Breakthroughs in deep and peripheral exploration are of great significance for the sustainable development of the region.In this study,a comprehensive prospecting and exploration model for gold exploration in the high-cold and high-altitude areas of the southwestern Tianshan Mountains was developed by systematically evaluating the metallogenic geological conditions of the deposit and integrating geological,geochemical,and geophysical exploration multi-source data.Both the shallow metamorphic carbonaceous fine clastic rock and ductile shear zones controlled the Au-mineralized zone.Moreover,mineralized alteration,Au-Sb-As element chemical anomalies,high magnetic anomalies,and medium-high values from low-wave impedance were also important components of the model.Three-dimensional(3-D)geological attribute models of various ore-controlling factors were established,revealing the spatial distribution patterns of the deep structural frameworks and hidden mineralization.Geostatistical methods were used to delineate the three edges and two deep-mineral exploration areas.A comprehensive evaluation showed that anomalous variables were well confirmed in geological understanding,highlighting the effectiveness and accuracy of the predictions.These results are significant for deep-edge exploration.展开更多
Objective:To construct a clinical prediction model of acupuncture treatment for diminished ovarian reserve(DOR)based on a machine learning algorithm to provide a clinical prediction of acupuncture for ameliorating pre...Objective:To construct a clinical prediction model of acupuncture treatment for diminished ovarian reserve(DOR)based on a machine learning algorithm to provide a clinical prediction of acupuncture for ameliorating pregnancy outcomes in DOR.Methods:We enrolled 377 DOR patients treated with acupuncture and with records of pregnancy outcomes(139 cases of pregnancy and 238 cases failed)exported from the International Patient Registry Platform of Acupuncture-moxibustion(IPRPAM).The predictive variables were determined using Spearman’s correlation analysis and feature engineering methods.The model was constructed by adopting logistic regression,naïve Bayes,random forest,support vector machine,extreme gradient boosting,the knearest neighbor algorithm,linear discriminant analysis,and neural network methods.The models were validated by the area under the curve(AUC),accuracy(ACC),and importance sequencing,and individual pregnancy prediction was conducted for the best-performing model.Results:The key factors determining pregnancy after acupuncture in patients with DOR were age,luteinizing hormone(LH)level after treatment,follicle-stimulating hormone(FSH)level after treatment,the ratio of FSH to LH(FSH/LH)after treatment,and history of acupuncture treatment.Random forest model ACC was 0.95,Fβwas 0.93,Logloss was 0.30,Logloss value was the lowest,the model variables exhibited the highest accuracy and precision.Conclusion:The random forest model for the effects of acupuncture on pregnancy outcomes in patients with DOR,constructed based on the IPRPAM,presents a favorable value for clinical application.展开更多
Digital modeling and autonomous control of the die forging process are significant challenges in realizing high-quality intelli-gent forging of components.Using the die forging of AA2014 aluminum alloy as a case study...Digital modeling and autonomous control of the die forging process are significant challenges in realizing high-quality intelli-gent forging of components.Using the die forging of AA2014 aluminum alloy as a case study,a machine-learning-assisted method for di-gital modeling of the forging force and autonomous control in response to forging parameter disturbances was proposed.First,finite ele-ment simulations of the forging processes were conducted under varying friction factors,die temperatures,billet temperatures,and for-ging velocities,and the sample data,including process parameters and forging force under different forging strokes,were gathered.Pre-diction models for the forging force were established using the support vector regression algorithm.The prediction error of F_(f),that is,the forging force required to fill the die cavity fully,was as low as 4.1%.To further improve the prediction accuracy of the model for the ac-tual F_(f),two rounds of iterative forging experiments were conducted using the Bayesian optimization algorithm,and the prediction error of F_(f) in the forging experiments was reduced from 6.0%to 1.5%.Finally,the prediction model of F_(f) combined with a genetic algorithm was used to establish an autonomous optimization strategy for the forging velocity at each stage of the forging stroke,when the billet and die temperatures were disturbed,which realized the autonomous control in response to disturbances.In cases of−20 or−40℃ reductions in the die and billet temperatures,forging experiments conducted with the autonomous optimization strategy maintained the measured F_(f) around the target value of 180 t,with the relative error ranging from−1.3%to+3.1%.This work provides a reference for the study of di-gital modeling and autonomous optimization control of quality factors in the forging process.展开更多
文摘Customer churn is the rate at which customers discontinue doing business with a company over a given time period.It is an essential measure for businesses to monitor high churn rates,as they often indicate underlying issues with services,products,or customer experience,resulting in considerable income loss.Prediction of customer churn is a crucial task aimed at retaining customers and maintaining revenue growth.Traditional machine learning(ML)models often struggle to capture complex temporal dependencies in client behavior data.To address this,an optimized deep learning(DL)approach using a Regularized Bidirectional Long Short-Term Memory(RBiLSTM)model is proposed to mitigate overfitting and improve generalization error.The model integrates dropout,L2-regularization,and early stopping to enhance predictive accuracy while preventing over-reliance on specific patterns.Moreover,this study investigates the effect of optimization techniques on boosting the training efficiency of the developed model.Experimental results on a recent public customer churn dataset demonstrate that the trained model outperforms the traditional ML models and some other DL models,such as Long Short-Term Memory(LSTM)and Deep Neural Network(DNN),in churn prediction performance and stability.The proposed approach achieves 96.1%accuracy,compared with LSTM and DNN,which attain 94.5%and 94.1%accuracy,respectively.These results confirm that the proposed approach can be used as a valuable tool for businesses to identify at-risk consumers proactively and implement targeted retention strategies.
基金financially supported by the National Key Research and Development Program of China (No. 2023YFB3812601)the National Natural Science Foundation of China (No. 51925401)the Young Elite Scientists Sponsorship Program by CAST, China (No. 2022QNRC001)。
文摘Machine learning-assisted methods for rapid and accurate prediction of temperature field,mushy zone,and grain size were proposed for the heating−cooling combined mold(HCCM)horizontal continuous casting of C70250 alloy plates.First,finite element simulations of casting processes were carried out with various parameters to build a dataset.Subsequently,different machine learning algorithms were employed to achieve high precision in predicting temperature fields,mushy zone locations,mushy zone inclination angle,and billet grain size.Finally,the process parameters were quickly optimized using a strategy consisting of random generation,prediction,and screening,allowing the mushy zone to be controlled to the desired target.The optimized parameters are 1234℃for heating mold temperature,47 mm/min for casting speed,and 10 L/min for cooling water flow rate.The optimized mushy zone is located in the middle of the second heat insulation section and has an inclination angle of roughly 7°.
基金supported by the National Key Research and Development Program of China[grant number 2022YFE0106800]an Innovation Group Project of the Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)[grant number 311024001]+3 种基金a project supported by the Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)[grant number SML2023SP209]a Research Council of Norway funded project(MAPARC)[grant number 328943]a Nansen Center´s basic institutional funding[grant number 342624]the high-performance computing support from the School of Atmospheric Science at Sun Yat-sen University。
文摘Current shipping,tourism,and resource development requirements call for more accurate predictions of the Arctic sea-ice concentration(SIC).However,due to the complex physical processes involved,predicting the spatiotemporal distribution of Arctic SIC is more challenging than predicting its total extent.In this study,spatiotemporal prediction models for monthly Arctic SIC at 1-to 3-month leads are developed based on U-Net-an effective convolutional deep-learning approach.Based on explicit Arctic sea-ice-atmosphere interactions,11 variables associated with Arctic sea-ice variations are selected as predictors,including observed Arctic SIC,atmospheric,oceanic,and heat flux variables at 1-to 3-month leads.The prediction skills for the monthly Arctic SIC of the test set(from January 2018 to December 2022)are evaluated by examining the mean absolute error(MAE)and binary accuracy(BA).Results showed that the U-Net model had lower MAE and higher BA for Arctic SIC compared to two dynamic climate prediction systems(CFSv2 and NorCPM).By analyzing the relative importance of each predictor,the prediction accuracy relies more on the SIC at the 1-month lead,but on the surface net solar radiation flux at 2-to 3-month leads.However,dynamic models show limited prediction skills for surface net solar radiation flux and other physical processes,especially in autumn.Therefore,the U-Net model can be used to capture the connections among these key physical processes associated with Arctic sea ice and thus offers a significant advantage in predicting Arctic SIC.
基金supported by the National Natural Science Foundation of China(Grant No.U2342208)support from NSF/Climate Dynamics Award#2025057。
文摘Predicting monsoon climate is one of the major endeavors in climate science and is becoming increasingly challenging due to global warming. The accuracy of monsoon seasonal predictions significantly impacts the lives of billions who depend on or are affected by monsoons, as it is essential for the water cycle, food security, ecology, disaster prevention, and the economy of monsoon regions. Given the extensive literature on Asian monsoon climate prediction, we limit our focus to reviewing the seasonal prediction and predictability of the Asian Summer Monsoon (ASM). However, much of this review is also relevant to monsoon predictions in other seasons and regions. Over the past two decades, considerable progress has been made in the seasonal forecasting of the ASM, driven by an enhanced understanding of the sources of predictability and the dynamics of seasonal variability, along with advanced development in sophisticated models and technologies. This review centers on advances in understanding the physical foundation for monsoon climate prediction (section 2), significant findings and insights into the primary and regional sources of predictability arising from feedback processes among various climate components (sections 3 and 4), the effects of global warming and external forcings on predictability (section 5), developments in seasonal prediction models and techniques (section 6), the challenges and limitations of monsoon climate prediction (section 7), and emerging research trends with suggestions for future directions (section 8). We hope this review will stimulate creative activities to enhance monsoon climate prediction.
基金Funded by State Railway Administration Research Project(No.2023JS007)National Natural Science Foundation of China(No.52438002)+1 种基金Research and Development Programs for Science and Technology of China Railways Corporation(No.J2023G003)New Cornerstone Science Foundation through the XPLORER PRIZE。
文摘To investigate the influence of coarse aggregate parent rock properties on the elastic modulus of concrete,the mineralogical properties and stress-strain curves of granite and dolomite parent rocks,as well as the strength and elastic modulus of mortar and concrete prepared with mechanism aggregates of the corresponding lithology,and the stress-strain curves of concrete were investigated.In this paper,a coarse aggregate and mortar matrix bonding assumption is proposed,and a prediction model for the elastic modulus of mortar is established by considering the lithology of the mechanism sand and the slurry components.An equivalent coarse aggregate elastic modulus model was established by considering factors such as coarse aggregate particle size,volume fraction,and mortar thickness between coarse aggregates.Based on the elastic modulus of the equivalent coarse aggregate and the remaining mortar,a prediction model for the elastic modulus of the two and three components of concrete in series and then in parallel was established,and the predicted values differed from the measured values within 10%.It is proposed that the coarse aggregate elastic modulus in highstrength concrete is the most critical factor affecting the elastic modulus of concrete,and as the coarse aggregate elastic modulus increases by 27.7%,the concrete elastic modulus increases by 19.5%.
基金National Key Research and Development Program of China,No.2023YFC3006704National Natural Science Foundation of China,No.42171047CAS-CSIRO Partnership Joint Project of 2024,No.177GJHZ2023097MI。
文摘Accurate prediction of flood events is important for flood control and risk management.Machine learning techniques contributed greatly to advances in flood predictions,and existing studies mainly focused on predicting flood resource variables using single or hybrid machine learning techniques.However,class-based flood predictions have rarely been investigated,which can aid in quickly diagnosing comprehensive flood characteristics and proposing targeted management strategies.This study proposed a prediction approach of flood regime metrics and event classes coupling machine learning algorithms with clustering-deduced membership degrees.Five algorithms were adopted for this exploration.Results showed that the class membership degrees accurately determined event classes with class hit rates up to 100%,compared with the four classes clustered from nine regime metrics.The nonlinear algorithms(Multiple Linear Regression,Random Forest,and least squares-Support Vector Machine)outperformed the linear techniques(Multiple Linear Regression and Stepwise Regression)in predicting flood regime metrics.The proposed approach well predicted flood event classes with average class hit rates of 66.0%-85.4%and 47.2%-76.0%in calibration and validation periods,respectively,particularly for the slow and late flood events.The predictive capability of the proposed prediction approach for flood regime metrics and classes was considerably stronger than that of hydrological modeling approach.
基金the funding support from the National Natural Science Foundation of China(Grant No.52308340)Chongqing Talent Innovation and Entrepreneurship Demonstration Team Project(Grant No.cstc2024ycjh-bgzxm0012)the Science and Technology Projects supported by China Coal Technology and Engineering Chongqing Design and Research Institute(Group)Co.,Ltd..(Grant No.H20230317)。
文摘Influenced by complex external factors,the displacement-time curve of reservoir landslides demonstrates both short-term and long-term diversity and dynamic complexity.It is difficult for existing methods,including Regression models and Neural network models,to perform multi-characteristic coupled displacement prediction because they fail to consider landslide creep characteristics.This paper integrates the creep characteristics of landslides with non-linear intelligent algorithms and proposes a dynamic intelligent landslide displacement prediction method based on a combination of the Biological Growth model(BG),Convolutional Neural Network(CNN),and Long ShortTerm Memory Network(LSTM).This prediction approach improves three different biological growth models,thereby effectively extracting landslide creep characteristic parameters.Simultaneously,it integrates external factors(rainfall and reservoir water level)to construct an internal and external comprehensive dataset for data augmentation,which is input into the improved CNN-LSTM model.Thereafter,harnessing the robust feature extraction capabilities and spatial translation invariance of CNN,the model autonomously captures short-term local fluctuation characteristics of landslide displacement,and combines LSTM's efficient handling of long-term nonlinear temporal data to improve prediction performance.An evaluation of the Liangshuijing landslide in the Three Gorges Reservoir Area indicates that BG-CNN-LSTM exhibits high prediction accuracy,excellent generalization capabilities when dealing with various types of landslides.The research provides an innovative approach to achieving the whole-process,realtime,high-precision displacement predictions for multicharacteristic coupled landslides.
基金supported by the National Key R&D Program of China(No.2021YFB3400900)the National Natural Science Foundation of China(Nos.52175373,52205435)+1 种基金Natural Science Foundation of Hunan Province,China(No.2022JJ40621)the Innovation Fund of National Commercial Aircraft Manufacturing Engineering Technology Center,China(No.COMACSFGS-2022-1875)。
文摘A new unified constitutive model was developed to predict the two-stage creep-aging(TSCA)behavior of Al-Zn-Mg-Cu alloys.The particular bimodal precipitation feature was analyzed and modeled by considering the primary micro-variables evolution at different temperatures and their interaction.The dislocation density was incorporated into the model to capture the effect of creep deformation on precipitation.Quantitative transmission electron microscopy and experimental data obtained from a previous study were used to calibrate the model.Subsequently,the developed constitutive model was implemented in the finite element(FE)software ABAQUS via the user subroutines for TSCA process simulation and the springback prediction of an integral panel.A TSCA test was performed.The result shows that the maximum radius deviation between the formed plate and the simulation results is less than 0.4 mm,thus validating the effectiveness of the developed constitutive model and FE model.
文摘Background: Pancreatic cancer is one of the most lethal malignancies, with postoperative recurrence severely affecting patient survival and prognosis. This study aims to develop and validate a clinical prediction model for postoperative recurrence in pancreatic cancer patients, incorporating multiple preoperative, intraoperative, and postoperative factors to assist clinical decision-making. Methods: A retrospective study was conducted on 216 patients who underwent surgical treatment for pancreatic malignancy at the First Affiliated Hospital of Chongqing Medical University between January 2015 and January 2023. An independent external validation cohort of 76 patients from the Second Affiliated Hospital of Chongqing Medical University was used to validate the model. Seven independent risk factors for postoperative recurrence were identified through univariate and multivariate Cox regression analyses. The model’s performance was evaluated using the concordance index (C-index) and ROC curves, and its accuracy and clinical value were assessed using calibration curves and decision curve analysis (DCA). Results: The predictive model demonstrated good discriminatory power, with a C-index of 0.72 in the training cohort and 0.66 in the validation cohort. The ROC curves for predicting recurrence at 3, 6, and 12 months postoperatively showed AUC values ranging from 0.72 to 0.83, indicating strong predictive value. Calibration curves and DCA confirmed the model’s accuracy and clinical utility. Conclusion: This study successfully developed and validated a clinical prediction model that incorporates seven independent risk factors for postoperative recurrence in pancreatic cancer. The model provides a useful tool for predicting recurrence risk, aiding in the identification of high-risk patients, and informing clinical decision-making.
基金supported by General Scientific Research Funding of the Science and Technology Development Fund(FDCT)in Macao(No.0150/2022/A)the Faculty Research Grants of Macao University of Science and Technology(No.FRG-22-074-FIE).
文摘With the rapid development of economy,air pollution caused by industrial expansion has caused serious harm to human health and social development.Therefore,establishing an effective air pollution concentration prediction system is of great scientific and practical significance for accurate and reliable predictions.This paper proposes a combination of pointinterval prediction system for pollutant concentration prediction by leveraging neural network,meta-heuristic optimization algorithm,and fuzzy theory.Fuzzy information granulation technology is used in data preprocessing to transform numerical sequences into fuzzy particles for comprehensive feature extraction.The golden Jackal optimization algorithm is employed in the optimization stage to fine-tune model hyperparameters.In the prediction stage,an ensemble learning method combines training results frommultiplemodels to obtain final point predictions while also utilizing quantile regression and kernel density estimation methods for interval predictions on the test set.Experimental results demonstrate that the combined model achieves a high goodness of fit coefficient of determination(R^(2))at 99.3% and a maximum difference between prediction accuracy mean absolute percentage error(MAPE)and benchmark model at 12.6%.This suggests that the integrated learning system proposed in this paper can provide more accurate deterministic predictions as well as reliable uncertainty analysis compared to traditionalmodels,offering practical reference for air quality early warning.
基金Supported by the National Natural Science Foundation of China(No.82220108017,No.82141128,No.82101180)Beijing Natural Science Foundation(No.Z220012)+3 种基金The Capital Health Research and Development of Special(No.2020-1-2052)Science&Technology Project of Beijing Municipal Science&Technology Commission(No.Z201100005520045)Sanming Project of Medicine in Shenzhen(No.SZSM202311018)Beijing Science&Technology Development of TCM(No.BJZYYB-2023-17).
文摘AIM:To explore the relationship between matrix metalloproteinases(MMPs)expression levels in the tumor and the prognosis of uveal melanoma(UM)and to construct prognostic prediction models.METHODS:Transcriptome sequencing data from 17 normal choroid tissues and 53 UM tumor tissues were collected.Based on the differential gene expression levels and their function,MMPs family was selected for establishing risk-score system and prognostic prediction model with machine learning.Tumor microenvironment(TME)analysis was also applied for the impact of immune cell infiltration on prognosis of the disease.RESULTS:Eight MMPs were significantly different expression levels between normal and the tumor tissues.MMP-2 and MMP-28 were selected to construct a risk-score system and divided patients accordingly into high-and low-risk groups.The prediction model based on the risk-score achieved an accuracy of approximately 80%at 1-,3-,and 5-year after diagnosis.Besides,a Nomogram prognostic prediction model which based on risk-score and pathological type(independent prognostic factors after Cox regression analysis)demonstrated good consistency between the predicted outcomes at 1-,3-,and 5-year after diagnosis and the actual prognosis of patients.TME analysis revealed that the high-risk group exhibited higher immune and stromal scores and increased infiltration of tumor-associated macrophages(TAMs)and regulatory T cells compared to the low-risk group.CONCLUSION:Based on MMP-2 and MMP-28 expression levels,our prediction model demonstrates accurate long-term prognosis prediction for UM patients.The aggregation of TAMs and regulatory T cells in the TME of UM may be associated with an unfavorable prognosis.
文摘BACKGROUND Colorectal polyps(CPs)are important precursor lesions of colorectal cancer,and endoscopic surgery remains the primary treatment option.However,the shortterm recurrence rate post-surgery is high,and the risk factors for recurrence remain unknown.AIM To comprehensively explore risk factors for short-term recurrence of CPs after endoscopic surgery and develop a nomogram prediction model.METHODS Overall,362 patients who underwent endoscopic polypectomy between January 2022 and January 2024 at Nanjing Jiangbei Hospital were included.We screened basic demographic data,clinical and polyp characteristics,surgery-related information,and independent risk factors for CPs recurrence using univariate and multivariate logistic regression analyses.The multivariate analysis results were used to construct a nomogram prediction model,internally validated using Bootstrapping,with performance evaluated using area under the curve(AUC),calibration curve,and decision curve analysis.RESULTS CP re-occurred in 166(45.86%)of the 362 patients within 1 year post-surgery.Multivariate logistic regression analysis showed that age(OR=1.04,P=0.002),alcohol consumption(OR=2.07,P=0.012),Helicobacter pylori infection(OR=2.34,P<0.001),polyp number>2(OR=1.98,P=0.005),sessile polyps(OR=2.10,P=0.006),and adenomatous pathological type(OR=3.02,P<0.001)were independent risk factors for post-surgery recurrence.The nomogram prediction model showed good discriminatory(AUC=0.73)and calibrating power,and decision curve analysis showed that the model had good clinical benefit at risk probabilities>20%.CONCLUSION We identified multiple independent risk factors for short-term recurrence after endoscopic surgery.The nomogram prediction model showed a certain degree of differentiation,calibration,and potential clinical applicability.
基金Supported by National Key Research and Development Program of China(Grant No.2018YFA0707300)Major Program of National Natural Science Foundation of China(Grant No.U22A20188)+1 种基金General Program of National Natural Science Foundation of China(Grant No.51974196)Postdoctoral Science Foundation of China(Grant No.201903D421047)。
文摘The prediction of the rolling force and thickness ratio plays an important role in the development and application of bimetallic composite plates.To analyze the rolling force of the bimetallic composite plate more accurately,a novel hypothesis based on Orowan's theory was proposed.The variation in the thickness of each differential element at different positions was considered to establish the analytical model.According to the characteristics of bimetallic composite plate rolling,the rolling deformation can be divided into forward and backward slip zones.The initial thickness ratio after rolling was predetermined by the thickness ratio before rolling;the rolling force balance of the upper and lower rollers was considered the convergence condition;and the final thickness ratio of the bimetallic composite plate was obtained by iterative calculation.The calculation results of the analytical model were compared with the measured and simulated data.The results showed that the errors in the calculation of the rolling force and thickness ratio were both less than 10%.The analytical model has high precision,meets engineering requirements,and has important reference significance for rolling process optimization and thickness ratio prediction.
基金supported by the National Natural Science Foundation of China(Grant Nos.U2242213,U2142213,42305167,42175105)。
文摘Systematic bias is a type of model error that can affect the accuracy of data assimilation and forecasting that must be addressed.An online bias correction scheme called the sequential bias correction scheme(SBCS),was developed using the6 h average bias to correct the systematic bias during model integration.The primary purpose of this study is to investigate the impact of the SBCS in the high-resolution China Meteorological Administration Meso-scale(CMA-MESO)numerical weather prediction(NWP)model to reduce the systematic bias and to improve the data assimilation and forecast results through this method.The SBCS is improved upon and applied to the CMA-MESO 3-km model in this study.Four-week sequential data assimilation and forecast experiments,driven by rapid update and cycling(RUC),were conducted for the period from 2–29 May 2022.In terms of the characteristics of systematic bias,both the background and analysis show diurnal bias,and these large biases are affected by complex underlying surfaces(e.g.,oceans,coasts,and mountains).After the application of the SBCS,the results of the data assimilation show that the SBCS can reduce the systematic bias of the background and yield a neutral to slightly positive result for the analysis fields.In addition,the SBCS can reduce forecast errors and improve forecast results,especially for surface variables.The above results indicate that this scheme has good prospects for high-resolution regional NWP models.
基金Supported by the 2024 Yiwu City Research Plan Project,No.24-3-102.
文摘BACKGROUND Rabies is a zoonotic viral disease affecting the central nervous system,caused by the rabies virus,with a case-fatality rate of 100%once symptoms appear.AIM To analyze high-risk factors associated with mental disorders induced by rabies vaccination and to construct a risk prediction model to inform strategies for improving patients’mental health.METHODS Patients who received rabies vaccinations at the Department of Infusion Yiwu Central Hospital between August 2024 and July 2025 were included,totaling 384 cases.Data were collected from medical records and included demographic characteristics(age,gender,occupation),lifestyle habits,and details regarding vaccine type,dosage,and injection site.The incidence of psychiatric disorders following vaccination was assessed using standardized anxiety and depression rating scales.Patients were categorized into two groups based on the presence or absence of anxiety and depression symptoms:The psychiatric disorder group and the non-psychiatric disorder group.Differences between the two groups were compared,and high-risk factors were identified using multivariate logistic regression analysis.A predictive model was then developed based on these factors to evaluate its predictive performance.RESULTS Among the 384 patients who received rabies vaccinations,36 cases(9.38%)were diagnosed with anxiety,52 cases(13.54%)with depression,and 88 cases(22.92%)with either condition.Logistic regression analysis identified the following signi ficant risk factors for psychiatric disorders:Education level of primary school or below,exposure site at the head and neck,exposure classified as grade III,family status of divorced/widowed/unmarried/living alone,number of wounds greater than one,and low awareness of rabies prevention and control(P<0.05).The risk prediction model demonstrated good performance,with an area under the receiver operating characteristic curve of 0.859,a specificity of 74.42%,and a sensitivity of 93.02%.CONCLUSION In real-world settings,psychiatric disorders following rabies vaccination are relatively common and are associated with factors such as lower education level,higher exposure severity,vulnerable family status,and limited awareness of rabies prevention and control.The developed risk prediction model may aid in early identification of high-risk individuals and support timely clinical intervention.
基金Ho Chi Minh City University of Technology (HCMUT), VNU-HCM for supporting this study
文摘Machine learning(ML)models are widely used for predicting undrained shear strength(USS),but interpretability has been a limitation in various studies.Therefore,this study introduced shapley additive explanations(SHAP)to clarify the contribution of each input feature in USS prediction.Three ML models,artificial neural network(ANN),extreme gradient boosting(XGBoost),and random forest(RF),were employed,with accuracy evaluated using mean squared error,mean absolute error,and coefficient of determination(R^(2)).The RF achieved the highest performance with an R^(2) of 0.82.SHAP analysis identified pre-consolidation stress as a key contributor to USS prediction.SHAP dependence plots reveal that the ANN captures smoother,linear feature-output relationships,while the RF handles complex,non-linear interactions more effectively.This suggests a non-linear relationship between USS and input features,with RF outperforming ANN.These findings highlight SHAP’s role in enhancing interpretability and promoting transparency and reliability in ML predictions for geotechnical applications.
文摘Predicting information dissemination on social media,specifcally users’reposting behavior,is crucial for applications such as advertising campaigns.Conventional methods use deep neural networks to make predictions based on features related to user topic interests and social preferences.However,these models frequently fail to account for the difculties arising from limited training data and model size,which restrict their capacity to learn and capture the intricate patterns within microblogging data.To overcome this limitation,we introduce a novel model Adapt pre-trained Large Language model for Reposting Prediction(ALL-RP),which incorporates two key steps:(1)extracting features from post content and social interactions using a large language model with extensive parameters and trained on a vast corpus,and(2)performing semantic and temporal adaptation to transfer the large language model’s knowledge of natural language,vision,and graph structures to reposting prediction tasks.Specifcally,the temporal adapter in the ALL-RP model captures multi-dimensional temporal information from evolving patterns of user topic interests and social preferences,thereby providing a more realistic refection of user attributes.Additionally,to enhance the robustness of feature modeling,we introduce a variant of the temporal adapter that implements multiple temporal adaptations in parallel while maintaining structural simplicity.Experimental results on real-world datasets demonstrate that the ALL-RP model surpasses state-of-the-art models in predicting both individual user reposting behavior and group sharing behavior,with performance gains of 2.81%and 4.29%,respectively.
基金supported by the Science&Technology Fundamental Resources Investigation Program(2022FY101705)China geological survey project(DD20240204805)market prospecting exploration project(CG-2024-HX-S012)。
文摘The Sawayaerdun gold deposit is the only extremely large deposit occurring in the giant gold metallogenic belt of the Central Asian Tianshan Orogenic Belt.Breakthroughs in deep and peripheral exploration are of great significance for the sustainable development of the region.In this study,a comprehensive prospecting and exploration model for gold exploration in the high-cold and high-altitude areas of the southwestern Tianshan Mountains was developed by systematically evaluating the metallogenic geological conditions of the deposit and integrating geological,geochemical,and geophysical exploration multi-source data.Both the shallow metamorphic carbonaceous fine clastic rock and ductile shear zones controlled the Au-mineralized zone.Moreover,mineralized alteration,Au-Sb-As element chemical anomalies,high magnetic anomalies,and medium-high values from low-wave impedance were also important components of the model.Three-dimensional(3-D)geological attribute models of various ore-controlling factors were established,revealing the spatial distribution patterns of the deep structural frameworks and hidden mineralization.Geostatistical methods were used to delineate the three edges and two deep-mineral exploration areas.A comprehensive evaluation showed that anomalous variables were well confirmed in geological understanding,highlighting the effectiveness and accuracy of the predictions.These results are significant for deep-edge exploration.
基金Supported by the Qihuang Scholars Program in 202114th Five-Year National Key R&D Program Project:2022YFC3500504。
文摘Objective:To construct a clinical prediction model of acupuncture treatment for diminished ovarian reserve(DOR)based on a machine learning algorithm to provide a clinical prediction of acupuncture for ameliorating pregnancy outcomes in DOR.Methods:We enrolled 377 DOR patients treated with acupuncture and with records of pregnancy outcomes(139 cases of pregnancy and 238 cases failed)exported from the International Patient Registry Platform of Acupuncture-moxibustion(IPRPAM).The predictive variables were determined using Spearman’s correlation analysis and feature engineering methods.The model was constructed by adopting logistic regression,naïve Bayes,random forest,support vector machine,extreme gradient boosting,the knearest neighbor algorithm,linear discriminant analysis,and neural network methods.The models were validated by the area under the curve(AUC),accuracy(ACC),and importance sequencing,and individual pregnancy prediction was conducted for the best-performing model.Results:The key factors determining pregnancy after acupuncture in patients with DOR were age,luteinizing hormone(LH)level after treatment,follicle-stimulating hormone(FSH)level after treatment,the ratio of FSH to LH(FSH/LH)after treatment,and history of acupuncture treatment.Random forest model ACC was 0.95,Fβwas 0.93,Logloss was 0.30,Logloss value was the lowest,the model variables exhibited the highest accuracy and precision.Conclusion:The random forest model for the effects of acupuncture on pregnancy outcomes in patients with DOR,constructed based on the IPRPAM,presents a favorable value for clinical application.
基金financially supported by the National Key Research and Development Program of China(No.2022YFB3706901)the National Natural Science Foundation of China(No.52090041)the Young Elite Scientists Sponsorship Program by CAST(No.2022QNRC 001).
文摘Digital modeling and autonomous control of the die forging process are significant challenges in realizing high-quality intelli-gent forging of components.Using the die forging of AA2014 aluminum alloy as a case study,a machine-learning-assisted method for di-gital modeling of the forging force and autonomous control in response to forging parameter disturbances was proposed.First,finite ele-ment simulations of the forging processes were conducted under varying friction factors,die temperatures,billet temperatures,and for-ging velocities,and the sample data,including process parameters and forging force under different forging strokes,were gathered.Pre-diction models for the forging force were established using the support vector regression algorithm.The prediction error of F_(f),that is,the forging force required to fill the die cavity fully,was as low as 4.1%.To further improve the prediction accuracy of the model for the ac-tual F_(f),two rounds of iterative forging experiments were conducted using the Bayesian optimization algorithm,and the prediction error of F_(f) in the forging experiments was reduced from 6.0%to 1.5%.Finally,the prediction model of F_(f) combined with a genetic algorithm was used to establish an autonomous optimization strategy for the forging velocity at each stage of the forging stroke,when the billet and die temperatures were disturbed,which realized the autonomous control in response to disturbances.In cases of−20 or−40℃ reductions in the die and billet temperatures,forging experiments conducted with the autonomous optimization strategy maintained the measured F_(f) around the target value of 180 t,with the relative error ranging from−1.3%to+3.1%.This work provides a reference for the study of di-gital modeling and autonomous optimization control of quality factors in the forging process.
