To better capture the characteristics of asymmetry and structural fluctuations observed in count time series,this study delves into the application of the quantile regression(QR)method for analyzing and forecasting no...To better capture the characteristics of asymmetry and structural fluctuations observed in count time series,this study delves into the application of the quantile regression(QR)method for analyzing and forecasting nonlinear integer-valued time series exhibiting a piecewise phenomenon.Specifically,we focus on the parameter estimation in the first-order Self-Exciting Threshold Integer-valued Autoregressive(SETINAR(2,1))process with symmetry,asymmetry,and contaminated innovations.We establish the asymptotic properties of the estimator under certain regularity conditions.Monte Carlo simulations demonstrate the superior performance of the QR method compared to the conditional least squares(CLS)approach.Furthermore,we validate the robustness of the proposed method through empirical quantile regression estimation and forecasting for larceny incidents and CAD drug call counts in Pittsburgh,showcasing its effectiveness across diverse levels of data heterogeneity.展开更多
The subset threshold auto regressive (SSTAR) model, which is capable of reproducing the limit cycle behavior of nonlinear time series, is introduced. The algorithm for fitting the sampled data with SSTAR model is pr...The subset threshold auto regressive (SSTAR) model, which is capable of reproducing the limit cycle behavior of nonlinear time series, is introduced. The algorithm for fitting the sampled data with SSTAR model is proposed and applied to model and forecast power load. Numerical example verifies that desirable accuracy of short term load forecasting can be achieved by using the SSTAR model.展开更多
BACKGROUND Histological changes after direct-acting antivirals(DAAs)therapy in hepatitis C virus(HCV)patients has not been elucidated.Whether the predominantly progressive,indeterminate and predominately regressive(P-...BACKGROUND Histological changes after direct-acting antivirals(DAAs)therapy in hepatitis C virus(HCV)patients has not been elucidated.Whether the predominantly progressive,indeterminate and predominately regressive(P-I-R)score,evaluating fibrosis activity in hepatitis B virus patients has predictive value in HCV patients has not been investigated.AIM To identify histological changes after DAAs therapy and to evaluate the predictive value of the P-I-R score in HCV patients.METHODS Chronic HCV patients with paired liver biopsy specimens before and after DAAs treatment were included.Sustained virologic response(SVR)was defined as an undetectable serum HCV RNA level at 24 wk after treatment cessation.The Ishak system and P-I-R score were assessed.Inflammation improvement and fibrosis regression were defined as a≥2-points decrease in the histology activity index(HAI)score and a≥1-point decrease in the Ishak fibrosis score,respectively.Fibrosis progression was defined as a≥1-point increase in the Ishak fibrosis score.Histologic improvement was defined as a≥2-points decrease in the HAI score without worsening of the Ishak fibrosis score after DAAs therapy.The P-I-R score was also assessed.“absolutely reversing or advancing”was defined as the same directionality implied by both change in the Ishak score and posttreatment P-I-R score;and“probably reversing or advancing”was defined as only one parameter showing directionality.RESULTS Thirty-eight chronic HCV patients with paired liver biopsy specimens before and after DAAs treatment were included.The mean age of these patients was 40.9±14.6 years and there were 53%(20/38)males.Thirty-four percent(13/38)of patients were cirrhotic.Eighty-two percent(31/38)of patients achieved inflammation improvement.The median HAI score decreased significantly after SVR(pretreatment 7.0 vs posttreatment 2.0,Z=-5.146,P=0.000).Thirty-seven percent(14/38)of patients achieved fibrosis improvement.The median Ishak score decreased significantly after SVR(pretreatment 4.0 vs posttreatment 3.0,Z=-2.354,P=0.019).Eighty-two percent(31/38)of patients showed histological improvement.The P-I-R score was evaluated in 61%(23/38)of patients.The progressive group showed lower platelet(P=0.024)and higher HAI scores(P=0.070)before treatment.In patients with stable Ishak stage after treatment:Progressive injury was seen in 22%(4/18)of patients,33%(6/18)were classified as indeterminate and regressive changes were seen in 44%(8/18)of patients who were judged as probably reversing by the Ishak and P-I-R systems.CONCLUSION Significant improvement of necroinflammation and partial remission of fibrosis in HCV patients occurred shortly after DAAs therapy.The P-I-R score has potential in predicting fibrosis in HCV patients.展开更多
The primary objective of the paper is to forecast the beta values of companies listed on Sensex,Bombay Stock Exchange(BSE).The BSE Sensex constitutes 30 top most companies listed which are popularly known as blue-chip...The primary objective of the paper is to forecast the beta values of companies listed on Sensex,Bombay Stock Exchange(BSE).The BSE Sensex constitutes 30 top most companies listed which are popularly known as blue-chip companies.To reach out the predefined objectives of the research,Auto Regressive Integrated Moving Average method is used to forecast the future risk and returns for 10 years of historical data from April 2007 to March 2017.Validation accomplished by comparison of forecasted and actual beta values for the hold back period of 2 years.Root-Mean-Square-Error and Mean-Absolute-Error both are used for accuracy measurement.The results revealed that out of 30 listed companies in the BSE Sensex,10 companies’exhibits high beta values,12 companies are with moderate and 8 companies are with low beta values.Further,it is to note that Housing Development Finance Corporation(HDFC)exhibits more inconsistency in terms of beta values though the average beta value is lowest among the companies under the study.A mixed trend is found in forecasted beta values of the BSE Sensex.In this analysis,all the p-values are less than the F-stat values except the case of Tata Steel and Wipro.Therefore,the null hypotheses were rejected leaving Tata Steel and Wipro.The values of actual and forecasted values are showing the almost same results with low error percentage.Therefore,it is concluded from the study that the estimation ARIMA could be acceptable,and forecasted beta values are accurate.So far,there are many studies on ARIMA model to forecast the returns of the stocks based on their historical data.But,hardly there are very few studies which attempt to forecast the returns on the basis of their beta values.Certainly,the attempt so made is a novel approach which has linked risk directly with return.On the basis of the present study,authors try to through light on investment decisions by linking it with beta values of respective stocks.Further,the outcomes of the present study undoubtedly useful to academicians,researchers,and policy makers in their respective area of studies.展开更多
The development of defect prediction plays a significant role in improving software quality. Such predictions are used to identify defective modules before the testing and to minimize the time and cost. The software w...The development of defect prediction plays a significant role in improving software quality. Such predictions are used to identify defective modules before the testing and to minimize the time and cost. The software with defects negatively impacts operational costs and finally affects customer satisfaction. Numerous approaches exist to predict software defects. However, the timely and accurate software bugs are the major challenging issues. To improve the timely and accurate software defect prediction, a novel technique called Nonparametric Statistical feature scaled QuAdratic regressive convolution Deep nEural Network (SQADEN) is introduced. The proposed SQADEN technique mainly includes two major processes namely metric or feature selection and classification. First, the SQADEN uses the nonparametric statistical Torgerson–Gower scaling technique for identifying the relevant software metrics by measuring the similarity using the dice coefficient. The feature selection process is used to minimize the time complexity of software fault prediction. With the selected metrics, software fault perdition with the help of the Quadratic Censored regressive convolution deep neural network-based classification. The deep learning classifier analyzes the training and testing samples using the contingency correlation coefficient. The softstep activation function is used to provide the final fault prediction results. To minimize the error, the Nelder–Mead method is applied to solve non-linear least-squares problems. Finally, accurate classification results with a minimum error are obtained at the output layer. Experimental evaluation is carried out with different quantitative metrics such as accuracy, precision, recall, F-measure, and time complexity. The analyzed results demonstrate the superior performance of our proposed SQADEN technique with maximum accuracy, sensitivity and specificity by 3%, 3%, 2% and 3% and minimum time and space by 13% and 15% when compared with the two state-of-the-art methods.展开更多
Capturing the distributed platform with remotely controlled compromised machines using botnet is extensively analyzed by various researchers.However,certain limitations need to be addressed efficiently.The provisionin...Capturing the distributed platform with remotely controlled compromised machines using botnet is extensively analyzed by various researchers.However,certain limitations need to be addressed efficiently.The provisioning of detection mechanism with learning approaches provides a better solution more broadly by saluting multi-objective constraints.The bots’patterns or features over the network have to be analyzed in both linear and non-linear manner.The linear and non-linear features are composed of high-level and low-level features.The collected features are maintained over the Bag of Features(BoF)where the most influencing features are collected and provided into the classifier model.Here,the linearity and non-linearity of the threat are evaluated with Support Vector Machine(SVM).Next,with the collected BoF,the redundant features are eliminated as it triggers overhead towards the predictor model.Finally,a novel Incoming data Redundancy Elimination-based learning model(RedE-L)is built to classify the network features to provide robustness towards BotNets detection.The simulation is carried out in MATLAB environment,and the evaluation of proposed RedE-L model is performed with various online accessible network traffic dataset(benchmark dataset).The proposed model intends to show better tradeoff compared to the existing approaches like conventional SVM,C4.5,RepTree and so on.Here,various metrics like Accuracy,detection rate,Mathews Correlation Coefficient(MCC),and some other statistical analysis are performed to show the proposed RedE-L model's reliability.The F1-measure is 99.98%,precision is 99.93%,Accuracy is 99.84%,TPR is 99.92%,TNR is 99.94%,FNR is 0.06 and FPR is 0.06 respectively.展开更多
Regression and autoregressive mixed models are classical models used to analyze the relationship between time series response variable and other covariates. The coefficients in traditional regression and autoregressiv...Regression and autoregressive mixed models are classical models used to analyze the relationship between time series response variable and other covariates. The coefficients in traditional regression and autoregressive mixed models are constants. However, for complicated data, the coefficients of covariates may change with time. In this article, we propose a kind of partial time-varying coefficient regression and autoregressive mixed model and obtain the local weighted least-square estimators of coefficient functions by the local polynomial technique. The asymptotic normality properties of estimators are derived under regularity conditions, and simulation studies are conducted to empirically examine the finite-sample performances of the proposed estimators. Finally, we use real data about Lake Shasta inflow to illustrate the application of the proposed model.展开更多
Regression and autoregressive mixed models are classical models used to analyze the relationship between time series response variable and other covariates. The coefficients in traditional regression and autoregressiv...Regression and autoregressive mixed models are classical models used to analyze the relationship between time series response variable and other covariates. The coefficients in traditional regression and autoregressive mixed models are constants. However, for complicated data, the coefficients of covariates may change with time. In this article, we propose a kind of partial time-varying coefficient regression and autoregressive mixed model and obtain the local weighted least-square estimators of coefficient functions by the local polynomial technique. The asymptotic normality properties of estimators are derived under regularity conditions, and simulation studies are conducted to empirically examine the finite-sample performances of the proposed estimators. Finally, we use real data about Lake Shasta inflow to illustrate the application of the proposed model.展开更多
To study the sensitivity of inter-subspecific hybrid rice to climatic conditions, the spikelet fertilized rate （SFR） of four types of rice including indica-japonica hybrid, intermediate hybrid, indica and japonica w...To study the sensitivity of inter-subspecific hybrid rice to climatic conditions, the spikelet fertilized rate （SFR） of four types of rice including indica-japonica hybrid, intermediate hybrid, indica and japonica were analyzed during 2000-2004. The inter-subspecific hybrids showed lower SFR, and much higher fluctuation under various climatic conditions than indica and japonica rice, showing the inter-subspecific hybrids were sensitive to ecological conditions. Among 12 climatic factors, the key factor affecting rice SFR was temperature, with the most significant factor being the average temperature of the seven days around panicle flowering （T7）. A regressive equation of SFR-temperature by T7, and a comprehensive synthetic model by four important temperature indices were put forward. The optimum temperature for inter-subspecific hybrids was estimated to be 26.1-26.6℃, and lower limit of safe temperature to be 22.5-23.3℃ for panicle flowering, showing higher by averagely 0.5℃ and 1.7℃, respectively, to be compared with indica and japonica rice. This suggested that inter-subspecific hybrids require proper climatic conditions. During panicle flowering, the suitable daily average temperature was 23.3-29.0℃, with the fittest one at 26.1-26.6℃. For an application example, optimum heading season for inter-subspecific hybrids in key rice growing areas in China was as same as common pure lines, while inferior limit for safe date of heading was about a ten-day period earlier than those of common pure lines.展开更多
The objective of this work is to model statistically the ultraviolet radiation index (UV Index) to make forecast (extrapolate) and analyze trends. The task is relevant, due to increased UV flux and high rate of cases ...The objective of this work is to model statistically the ultraviolet radiation index (UV Index) to make forecast (extrapolate) and analyze trends. The task is relevant, due to increased UV flux and high rate of cases non-melanoma skin cancer in northeast of Brazil. The methodology utilized an Autoregressive Distributed Lag model (ADL) or Dynamic Linear Regression model. The monthly data of UV index were measured in east coast of the Brazilian Northeast (City of Natal-Rio Grande do Norte). The Total Ozone is single explanatory variable to model and was obtained from the TOMS and OMI/AURA instruments. The Predictive Mean Matching (PMM) method was used to complete the missing data of UV Index. The results mean squared error (MSE) between the observed UV index and interpolated data by model was of 0.36 and for extrapolation was of 0.30 with correlations of 0.90 and 0.91 respectively. The forecast/extrapolation performed by model for a climatological period (2012-2042) indicated a trend of increased UV (Seasonal Man-Kendall test scored τ = 0.955 and p-value 0.001) if the Total Ozone remain on this tendency to reduce. In those circumstances, the model indicated an increase of almost one unit of UV index to year 2042.展开更多
A regressive correction method is presented with the primary goal of improving ENSO simulation in regional coupled GCM.It focuses on the correction of ocean-atmosphere exchanged fluxes.On the basis of numerical experi...A regressive correction method is presented with the primary goal of improving ENSO simulation in regional coupled GCM.It focuses on the correction of ocean-atmosphere exchanged fluxes.On the basis of numerical experiments and analysis,the method can be described as follows:first,driving the ocean model with heat and momentum flux computed from a long-term observation data set;the pro-duced SST is then applied to force the AGCM as its boundary condition;after that the AGCM’s simula-tion and the corresponding observation can be correlated by a linear regressive formula.Thus the re-gressive correction coefficients for the simulation with spatial and temporal variation could be obtained by linear fitting.Finally the coefficients are applied to redressing the variables used for the calculation of the exchanged air-sea flux in the coupled model when it starts integration.This method together with the anomaly coupling method is tested in a regional coupled model,which is composed of a global grid-point atmospheric general circulation model and a high-resolution tropical Pacific Ocean model.The comparison of the results shows that it is superior to the anomaly coupling both in reducing the coupled model‘climate drift’and in improving the ENSO simulation in the tropical Pacific Ocean.展开更多
There is a lack of studies when dealing with the comparison between regression methods and machine learning(ML)-type methods in terms of their ability to interpret and describe how the components of a bituminous mixtu...There is a lack of studies when dealing with the comparison between regression methods and machine learning(ML)-type methods in terms of their ability to interpret and describe how the components of a bituminous mixture affect mechanistic performance.At the same time,artificial intelligence(AI)-driven approaches are becoming more popular in analysing asphalt mixtures,yet there are limited comparisons of regression and machine learning(ML)models for mechanistic performance interpretation.Consequently,a comparison of AI and statistical approaches is presented in this study for predicting bituminous mixture properties such as stiffness,fatigue resistance,and tensile strength.Some of the important input features are bitumen content,crumb rubber content,and air void content.The research uses random forest model(RFM),linear regression model(LRM),and polynomial regression model(PRM).RFM and PRM achieved an R^(2) as high as 0.94,with mean absolute error(MAE)less than 2.5,and are,therefore,good predictive models.Interestingly,RFM works best in one-third of instances,particularly when dealing with outliers,whereas traditional statistical models work better in two-thirds of instances.The results highlight AI's value in bituminous mixture optimisation,where RFM showed good prediction accuracy.In 30%of the cases,AI models outperformed the conventional statistical approaches.At the same time,analyses show that model performance varies significantly with scenarios and that even if AI models capture complex nonlinear relationships,they must not override DOE principles.展开更多
Classical linear discriminant analysis(LDA)(Fisher,1936)implicitly assumes the classification boundary depends on only one linear combination of the predictors.This restriction can lead to poor classification in appli...Classical linear discriminant analysis(LDA)(Fisher,1936)implicitly assumes the classification boundary depends on only one linear combination of the predictors.This restriction can lead to poor classification in applications where the decision boundary depends on multiple linear combinations of the predictors.To overcome this challenge,the authors first project the predictors onto an envelope central space and then perform LDA based on the sufficient predictor.The performance of the proposed method in improving classification accuracy is demonstrated in both synthetic data and real applications.展开更多
This work addresses optimality aspects related to composite laminates having layers with different orientations.RegressionNeuralNetworks can model the mechanical behavior of these laminates,specifically the stressstra...This work addresses optimality aspects related to composite laminates having layers with different orientations.RegressionNeuralNetworks can model the mechanical behavior of these laminates,specifically the stressstrain relationship.If this model has strong generalization ability,it can be coupled with a metaheuristic algorithm–the PSO algorithm used in this article–to address an optimization problem(OP)related to the orientations of composite laminates.To solve OPs,this paper proposes an optimization framework(OFW)that connects the two components,the optimal solution search mechanism and the RNN model.The OFW has two modules:the search mechanism(Adaptive Hybrid Topology PSO)and the Prediction and Computation Module(PCM).The PCM undertakes all the activities concerning the OP at hand:the stress-strain model,constraints checking,and computation of the objective function.Two case studies about the layers’orientations of laminated specimens are conducted to validate the proposed framework.The specimens belong to“Off-axis oriented specimens”and are subjects of two OPs.The algorithms for AHTPSO and for the two PCMs(one for each problem)are proposed and implemented by MATLAB scripts and functions.Simulations are carried out for different initial conditions.The solutions demonstrated that the OFW is effective and has a highly acceptable computational complexity.The limitation of using the OFWis the generalization ability of the RNN model or any other regression models.To harness the RNN model efficiently,it must have a very good generalization power.If this condition ismet,the OFWcan be integrated into any design process to make optimal choices of the layers’orientations.展开更多
While parametric Software Reliability Growth Models(SRGMs)serve as a cornerstone in software reliability assessment,their reliance on known fault-detection time distributions often presents a significant limitation in...While parametric Software Reliability Growth Models(SRGMs)serve as a cornerstone in software reliability assessment,their reliance on known fault-detection time distributions often presents a significant limitation in practical software testing.In this study,the authors develop a novel shaperestricted spline estimator for quantifying software reliability.Compared with parametric SRGMs,the proposed estimator not only shares a key characteristic with parametric SRGMs,but also obviates the need for specifying fault-detection time distributions.More importantly,it effectively utilizes the critical shape information of the mean value function(MVF)of fault-detection process,a detail seldom considered in prior work.Moreover,the authors investigate the predictive performance of the proposed methods by employing the so-called one-step look-ahead prediction method.Furthermore,the authors show that under certain conditions,the shape-restricted spline estimator will attain the point-wise convergence rate O_P(n~(-3/7)).In numerical experiment,the authors show that spline estimators under restriction demonstrate competitive performance compared to parametric and certain non-parametric models.展开更多
Protective hardware is essential for mitigating damage caused by unavoidable falls in humanoid robots.Despite notable progress in fall protection hardware,the theoretical foundation for modeling and the feasibility of...Protective hardware is essential for mitigating damage caused by unavoidable falls in humanoid robots.Despite notable progress in fall protection hardware,the theoretical foundation for modeling and the feasibility of conducting full-scale fall experiments on robots or their surrogates remain somewhat limited.This paper proposes a method for optimizing the thickness of Expandable Polyethylene(EPE),which is used as back protection for the Chubao humanoid robot,based on small-scale impact test data to predict full-scale behavior.The optimal thickness is defined as a balance between compact design and protective effectiveness.An equivalent impact model characterized by four parameters:contact area S,mass m,fall height h,and cushioning material thickness d is introduced to describe impact conditions.The relationship between the peak impact acceleration ap and material thickness d,which forms the core of the method and gives rise to the name AP-D,is analyzed through their plotted curves.After introducing three characteristic parameters and two correction fac-tors,the relationship among the aforementioned variables is derived.Subsequently,both the optimal thickness do and its corresponding peak impact acceleration aop are predicted via nonlinear and linear regression models.Finally,the accuracy and effectiveness of the theoretically derived optimal thickness are validated on both a dummy and the actual robot.With the cushioning material applied,the peak chest acceleration is reduced to 41.57g for the dummy and 32.08g for the robot.展开更多
This paper examines whether the parametric regression model is correctly specified for both source and target data and whether the regression pattern in the source domain aligns with that of the target domain.This eva...This paper examines whether the parametric regression model is correctly specified for both source and target data and whether the regression pattern in the source domain aligns with that of the target domain.This evaluation is a critical prerequisite for applying model-based transfer learning methods under covariate shift assumptions.Traditional regression model checks and twosample regression tests are insufficient to address this issue.To overcome these limitations,the authors propose a novel adaptive-to-regression test statistic that is asymptotically distribution-free.Under the null hypothesis,the test follows a chi-square weak limit,preserving the significance level and enabling critical value determination without resampling techniques.Additionally,the authors systematically analyze the test's power performance,highlighting its sensitivity to different sub-local alternatives that deviate from the null hypothesis.Numerical studies,including simulations,assess finite-sample performance,and a real-world data example is provided for illustration.展开更多
BACKGROUND:Rapid identification of patients at risk of clinical deterioration(in-hospital mortality) in emergency settings is essential for timely and appropriate care.Existing prognostic scores,such as the Acute Phys...BACKGROUND:Rapid identification of patients at risk of clinical deterioration(in-hospital mortality) in emergency settings is essential for timely and appropriate care.Existing prognostic scores,such as the Acute Physiology and Chronic Health Evaluation IV(APACHE IV),Simplified Acute Physiology Score 3(SAPS 3),Sequential Organ Failure Assessment(SOFA),and National Early Warning Score 2(NEWS 2),have limitations in emergency scenarios,particularly in resource-limited settings.We aimed to develop a simple and efficient tool tailored to the Brazilian healthcare system.METHODS:This retrospective,multicenter,cohort study analyzed data from 50,709 adult patients admitted to 12 hospitals in southern and southeastern Brazil between 2019 and 2020.The BRASIL score(Brazilian Risk Assessment Severity Index and Length of stay) was constructed using demographic and clinical variables available at admission.Logistic regression was used to determine the weight of each variable,and each variable was assigned a point value based on its β-coefficient and clinical relevance,with thresholds defined according to established medical cutoffs and statistical performance.The score's predictive accuracy was validated using the area under the receiver operating characteristic curve(AUC) with comparative analysis against NEWS 2.RESULTS:The BRASIL score,including age,sex,respiratory rate,heart rate,oxygen saturation,blood pressure,and body temperature,was derived through variables independently associated with in-hospital mortality in a multicenter cohort.The total score was stratified into three risk categories — low(0–3 points),moderate(4–7 points),and high(>7 points) — using observed inflection points in mortality distribution to optimize discrimination.This stratification demonstrated a stepwise increase in mortality rates across categories and the discriminatory performance,with an overall AUC of 0.743(95% CI:0.726–0.761).Compared to NEWS 2(AUC 0.697,95% CI:0.683–0.711),the BRASIL score offered superior early risk identification,supporting timely clinical decisionmaking and resource allocation in the emergency setting.CONCLUSION:The BRASIL score is a novel tool for predicting in-hospital mortality in emergency departments.Its predictive performance and ease of use suggest that it has the potential to improve patient outcomes.展开更多
Traditional oilfields face increasing extraction challenges, primarily due to reservoir quality degradation and production decline, which are further exacerbated by volatile international crude oil prices—illustrated...Traditional oilfields face increasing extraction challenges, primarily due to reservoir quality degradation and production decline, which are further exacerbated by volatile international crude oil prices—illustrated by Brent Crude’s trajectory from pandemic-induced negative pricing to geopolitically driven surges exceeding USD 100 per barrel. This study addresses these complexities through an integrated methodological framework applied to medium-permeability sandstone reservoirs in the Xinjiang oilfield by combining advanced numerical simulations with multivariate regression analysis. The methodology employs Latin Hypercube Sampling (LHS) to stratify geological parameter distributions and constructs heterogeneous reservoir models using Petrel software, rigorously validated through historical production data matching. Production forecasting integrates numerical simulation and Decline Curve Analysis (DCA), while investment estimation utilizes Ordinary Least Squares (OLS) regression to correlate engineering parameters with drilling and completion costs. Economic evaluation incorporates Discounted Cash Flow (DCF) modeling and breakeven analysis, establishing techno-economic boundaries via oil price sensitivity analysis ranging from USD 40 to 90 per barrel. Visualization tools, including 3D heatmaps, delineate nonlinear interactions among engineering, geological, and investment datasets under economic constraints. Key findings demonstrate that for the target reservoirs, as oil prices increase from USD 40 to USD 90 per barrel, the minimum economic thickness threshold decreases from approximately 5.7 m to about 2.5 m, with model prediction errors consistently below 25% across validation datasets. This framework provides scientifically grounded decision support for optimizing capital allocation and offers actionable insights to enhance undeveloped hydrocarbon development planning amid market uncertainty. Ultimately, it supports national energy security through technically robust and economically viable resource exploitation strategies.展开更多
High-dimensional data causes difficulties in machine learning due to high time consumption and large memory requirements.In particular,in amulti-label environment,higher complexity is required asmuch as the number of ...High-dimensional data causes difficulties in machine learning due to high time consumption and large memory requirements.In particular,in amulti-label environment,higher complexity is required asmuch as the number of labels.Moreover,an optimization problem that fully considers all dependencies between features and labels is difficult to solve.In this study,we propose a novel regression-basedmulti-label feature selectionmethod that integrates mutual information to better exploit the underlying data structure.By incorporating mutual information into the regression formulation,the model captures not only linear relationships but also complex non-linear dependencies.The proposed objective function simultaneously considers three types of relationships:(1)feature redundancy,(2)featurelabel relevance,and(3)inter-label dependency.These three quantities are computed usingmutual information,allowing the proposed formulation to capture nonlinear dependencies among variables.These three types of relationships are key factors in multi-label feature selection,and our method expresses them within a unified formulation,enabling efficient optimization while simultaneously accounting for all of them.To efficiently solve the proposed optimization problem under non-negativity constraints,we develop a gradient-based optimization algorithm with fast convergence.Theexperimental results on sevenmulti-label datasets show that the proposed method outperforms existingmulti-label feature selection techniques.展开更多
基金supported by Social Science Planning Foundation of Liaoning Province(Grand No.L22ZD065)National Natural Science Foundation of China(Grand Nos.12271231,1247012719,12001229)。
文摘To better capture the characteristics of asymmetry and structural fluctuations observed in count time series,this study delves into the application of the quantile regression(QR)method for analyzing and forecasting nonlinear integer-valued time series exhibiting a piecewise phenomenon.Specifically,we focus on the parameter estimation in the first-order Self-Exciting Threshold Integer-valued Autoregressive(SETINAR(2,1))process with symmetry,asymmetry,and contaminated innovations.We establish the asymptotic properties of the estimator under certain regularity conditions.Monte Carlo simulations demonstrate the superior performance of the QR method compared to the conditional least squares(CLS)approach.Furthermore,we validate the robustness of the proposed method through empirical quantile regression estimation and forecasting for larceny incidents and CAD drug call counts in Pittsburgh,showcasing its effectiveness across diverse levels of data heterogeneity.
文摘The subset threshold auto regressive (SSTAR) model, which is capable of reproducing the limit cycle behavior of nonlinear time series, is introduced. The algorithm for fitting the sampled data with SSTAR model is proposed and applied to model and forecast power load. Numerical example verifies that desirable accuracy of short term load forecasting can be achieved by using the SSTAR model.
基金The National Natural Science Foundation of China,No.81870406the Beijing Natural Science Foundation,No.7182174and the China National Science and Technology Major Project for Infectious Diseases Control during the 13th Five-Year Plan Period,No.2017ZX10202202.
文摘BACKGROUND Histological changes after direct-acting antivirals(DAAs)therapy in hepatitis C virus(HCV)patients has not been elucidated.Whether the predominantly progressive,indeterminate and predominately regressive(P-I-R)score,evaluating fibrosis activity in hepatitis B virus patients has predictive value in HCV patients has not been investigated.AIM To identify histological changes after DAAs therapy and to evaluate the predictive value of the P-I-R score in HCV patients.METHODS Chronic HCV patients with paired liver biopsy specimens before and after DAAs treatment were included.Sustained virologic response(SVR)was defined as an undetectable serum HCV RNA level at 24 wk after treatment cessation.The Ishak system and P-I-R score were assessed.Inflammation improvement and fibrosis regression were defined as a≥2-points decrease in the histology activity index(HAI)score and a≥1-point decrease in the Ishak fibrosis score,respectively.Fibrosis progression was defined as a≥1-point increase in the Ishak fibrosis score.Histologic improvement was defined as a≥2-points decrease in the HAI score without worsening of the Ishak fibrosis score after DAAs therapy.The P-I-R score was also assessed.“absolutely reversing or advancing”was defined as the same directionality implied by both change in the Ishak score and posttreatment P-I-R score;and“probably reversing or advancing”was defined as only one parameter showing directionality.RESULTS Thirty-eight chronic HCV patients with paired liver biopsy specimens before and after DAAs treatment were included.The mean age of these patients was 40.9±14.6 years and there were 53%(20/38)males.Thirty-four percent(13/38)of patients were cirrhotic.Eighty-two percent(31/38)of patients achieved inflammation improvement.The median HAI score decreased significantly after SVR(pretreatment 7.0 vs posttreatment 2.0,Z=-5.146,P=0.000).Thirty-seven percent(14/38)of patients achieved fibrosis improvement.The median Ishak score decreased significantly after SVR(pretreatment 4.0 vs posttreatment 3.0,Z=-2.354,P=0.019).Eighty-two percent(31/38)of patients showed histological improvement.The P-I-R score was evaluated in 61%(23/38)of patients.The progressive group showed lower platelet(P=0.024)and higher HAI scores(P=0.070)before treatment.In patients with stable Ishak stage after treatment:Progressive injury was seen in 22%(4/18)of patients,33%(6/18)were classified as indeterminate and regressive changes were seen in 44%(8/18)of patients who were judged as probably reversing by the Ishak and P-I-R systems.CONCLUSION Significant improvement of necroinflammation and partial remission of fibrosis in HCV patients occurred shortly after DAAs therapy.The P-I-R score has potential in predicting fibrosis in HCV patients.
文摘The primary objective of the paper is to forecast the beta values of companies listed on Sensex,Bombay Stock Exchange(BSE).The BSE Sensex constitutes 30 top most companies listed which are popularly known as blue-chip companies.To reach out the predefined objectives of the research,Auto Regressive Integrated Moving Average method is used to forecast the future risk and returns for 10 years of historical data from April 2007 to March 2017.Validation accomplished by comparison of forecasted and actual beta values for the hold back period of 2 years.Root-Mean-Square-Error and Mean-Absolute-Error both are used for accuracy measurement.The results revealed that out of 30 listed companies in the BSE Sensex,10 companies’exhibits high beta values,12 companies are with moderate and 8 companies are with low beta values.Further,it is to note that Housing Development Finance Corporation(HDFC)exhibits more inconsistency in terms of beta values though the average beta value is lowest among the companies under the study.A mixed trend is found in forecasted beta values of the BSE Sensex.In this analysis,all the p-values are less than the F-stat values except the case of Tata Steel and Wipro.Therefore,the null hypotheses were rejected leaving Tata Steel and Wipro.The values of actual and forecasted values are showing the almost same results with low error percentage.Therefore,it is concluded from the study that the estimation ARIMA could be acceptable,and forecasted beta values are accurate.So far,there are many studies on ARIMA model to forecast the returns of the stocks based on their historical data.But,hardly there are very few studies which attempt to forecast the returns on the basis of their beta values.Certainly,the attempt so made is a novel approach which has linked risk directly with return.On the basis of the present study,authors try to through light on investment decisions by linking it with beta values of respective stocks.Further,the outcomes of the present study undoubtedly useful to academicians,researchers,and policy makers in their respective area of studies.
文摘The development of defect prediction plays a significant role in improving software quality. Such predictions are used to identify defective modules before the testing and to minimize the time and cost. The software with defects negatively impacts operational costs and finally affects customer satisfaction. Numerous approaches exist to predict software defects. However, the timely and accurate software bugs are the major challenging issues. To improve the timely and accurate software defect prediction, a novel technique called Nonparametric Statistical feature scaled QuAdratic regressive convolution Deep nEural Network (SQADEN) is introduced. The proposed SQADEN technique mainly includes two major processes namely metric or feature selection and classification. First, the SQADEN uses the nonparametric statistical Torgerson–Gower scaling technique for identifying the relevant software metrics by measuring the similarity using the dice coefficient. The feature selection process is used to minimize the time complexity of software fault prediction. With the selected metrics, software fault perdition with the help of the Quadratic Censored regressive convolution deep neural network-based classification. The deep learning classifier analyzes the training and testing samples using the contingency correlation coefficient. The softstep activation function is used to provide the final fault prediction results. To minimize the error, the Nelder–Mead method is applied to solve non-linear least-squares problems. Finally, accurate classification results with a minimum error are obtained at the output layer. Experimental evaluation is carried out with different quantitative metrics such as accuracy, precision, recall, F-measure, and time complexity. The analyzed results demonstrate the superior performance of our proposed SQADEN technique with maximum accuracy, sensitivity and specificity by 3%, 3%, 2% and 3% and minimum time and space by 13% and 15% when compared with the two state-of-the-art methods.
文摘Capturing the distributed platform with remotely controlled compromised machines using botnet is extensively analyzed by various researchers.However,certain limitations need to be addressed efficiently.The provisioning of detection mechanism with learning approaches provides a better solution more broadly by saluting multi-objective constraints.The bots’patterns or features over the network have to be analyzed in both linear and non-linear manner.The linear and non-linear features are composed of high-level and low-level features.The collected features are maintained over the Bag of Features(BoF)where the most influencing features are collected and provided into the classifier model.Here,the linearity and non-linearity of the threat are evaluated with Support Vector Machine(SVM).Next,with the collected BoF,the redundant features are eliminated as it triggers overhead towards the predictor model.Finally,a novel Incoming data Redundancy Elimination-based learning model(RedE-L)is built to classify the network features to provide robustness towards BotNets detection.The simulation is carried out in MATLAB environment,and the evaluation of proposed RedE-L model is performed with various online accessible network traffic dataset(benchmark dataset).The proposed model intends to show better tradeoff compared to the existing approaches like conventional SVM,C4.5,RepTree and so on.Here,various metrics like Accuracy,detection rate,Mathews Correlation Coefficient(MCC),and some other statistical analysis are performed to show the proposed RedE-L model's reliability.The F1-measure is 99.98%,precision is 99.93%,Accuracy is 99.84%,TPR is 99.92%,TNR is 99.94%,FNR is 0.06 and FPR is 0.06 respectively.
文摘Regression and autoregressive mixed models are classical models used to analyze the relationship between time series response variable and other covariates. The coefficients in traditional regression and autoregressive mixed models are constants. However, for complicated data, the coefficients of covariates may change with time. In this article, we propose a kind of partial time-varying coefficient regression and autoregressive mixed model and obtain the local weighted least-square estimators of coefficient functions by the local polynomial technique. The asymptotic normality properties of estimators are derived under regularity conditions, and simulation studies are conducted to empirically examine the finite-sample performances of the proposed estimators. Finally, we use real data about Lake Shasta inflow to illustrate the application of the proposed model.
文摘Regression and autoregressive mixed models are classical models used to analyze the relationship between time series response variable and other covariates. The coefficients in traditional regression and autoregressive mixed models are constants. However, for complicated data, the coefficients of covariates may change with time. In this article, we propose a kind of partial time-varying coefficient regression and autoregressive mixed model and obtain the local weighted least-square estimators of coefficient functions by the local polynomial technique. The asymptotic normality properties of estimators are derived under regularity conditions, and simulation studies are conducted to empirically examine the finite-sample performances of the proposed estimators. Finally, we use real data about Lake Shasta inflow to illustrate the application of the proposed model.
文摘To study the sensitivity of inter-subspecific hybrid rice to climatic conditions, the spikelet fertilized rate （SFR） of four types of rice including indica-japonica hybrid, intermediate hybrid, indica and japonica were analyzed during 2000-2004. The inter-subspecific hybrids showed lower SFR, and much higher fluctuation under various climatic conditions than indica and japonica rice, showing the inter-subspecific hybrids were sensitive to ecological conditions. Among 12 climatic factors, the key factor affecting rice SFR was temperature, with the most significant factor being the average temperature of the seven days around panicle flowering （T7）. A regressive equation of SFR-temperature by T7, and a comprehensive synthetic model by four important temperature indices were put forward. The optimum temperature for inter-subspecific hybrids was estimated to be 26.1-26.6℃, and lower limit of safe temperature to be 22.5-23.3℃ for panicle flowering, showing higher by averagely 0.5℃ and 1.7℃, respectively, to be compared with indica and japonica rice. This suggested that inter-subspecific hybrids require proper climatic conditions. During panicle flowering, the suitable daily average temperature was 23.3-29.0℃, with the fittest one at 26.1-26.6℃. For an application example, optimum heading season for inter-subspecific hybrids in key rice growing areas in China was as same as common pure lines, while inferior limit for safe date of heading was about a ten-day period earlier than those of common pure lines.
文摘The objective of this work is to model statistically the ultraviolet radiation index (UV Index) to make forecast (extrapolate) and analyze trends. The task is relevant, due to increased UV flux and high rate of cases non-melanoma skin cancer in northeast of Brazil. The methodology utilized an Autoregressive Distributed Lag model (ADL) or Dynamic Linear Regression model. The monthly data of UV index were measured in east coast of the Brazilian Northeast (City of Natal-Rio Grande do Norte). The Total Ozone is single explanatory variable to model and was obtained from the TOMS and OMI/AURA instruments. The Predictive Mean Matching (PMM) method was used to complete the missing data of UV Index. The results mean squared error (MSE) between the observed UV index and interpolated data by model was of 0.36 and for extrapolation was of 0.30 with correlations of 0.90 and 0.91 respectively. The forecast/extrapolation performed by model for a climatological period (2012-2042) indicated a trend of increased UV (Seasonal Man-Kendall test scored τ = 0.955 and p-value 0.001) if the Total Ozone remain on this tendency to reduce. In those circumstances, the model indicated an increase of almost one unit of UV index to year 2042.
基金the National Natural Science Foundation of China(Grant Nos.40523001,40631005,and 40620130113)
文摘A regressive correction method is presented with the primary goal of improving ENSO simulation in regional coupled GCM.It focuses on the correction of ocean-atmosphere exchanged fluxes.On the basis of numerical experiments and analysis,the method can be described as follows:first,driving the ocean model with heat and momentum flux computed from a long-term observation data set;the pro-duced SST is then applied to force the AGCM as its boundary condition;after that the AGCM’s simula-tion and the corresponding observation can be correlated by a linear regressive formula.Thus the re-gressive correction coefficients for the simulation with spatial and temporal variation could be obtained by linear fitting.Finally the coefficients are applied to redressing the variables used for the calculation of the exchanged air-sea flux in the coupled model when it starts integration.This method together with the anomaly coupling method is tested in a regional coupled model,which is composed of a global grid-point atmospheric general circulation model and a high-resolution tropical Pacific Ocean model.The comparison of the results shows that it is superior to the anomaly coupling both in reducing the coupled model‘climate drift’and in improving the ENSO simulation in the tropical Pacific Ocean.
基金sustained them with this research(including Eng.Giuseppe Colicchio)and the European Commission for its financial contribution to the LIFE SILENT project“Sustainable Innovations for Long-life Environmental Noise Technologies”(LIFE22-ENV-IT-LIFE-SILENT/101114310.Acronym:LIFE22-ENV-ITLIFE SILENT)the LIFE SNEAK Project“Optimised Surfaces Against Noise and Vibrations Produced by Tramway Track and Road Traffic”(LIFE20 ENV/IT/000181.Acronym:LIFE SNEAK).
文摘There is a lack of studies when dealing with the comparison between regression methods and machine learning(ML)-type methods in terms of their ability to interpret and describe how the components of a bituminous mixture affect mechanistic performance.At the same time,artificial intelligence(AI)-driven approaches are becoming more popular in analysing asphalt mixtures,yet there are limited comparisons of regression and machine learning(ML)models for mechanistic performance interpretation.Consequently,a comparison of AI and statistical approaches is presented in this study for predicting bituminous mixture properties such as stiffness,fatigue resistance,and tensile strength.Some of the important input features are bitumen content,crumb rubber content,and air void content.The research uses random forest model(RFM),linear regression model(LRM),and polynomial regression model(PRM).RFM and PRM achieved an R^(2) as high as 0.94,with mean absolute error(MAE)less than 2.5,and are,therefore,good predictive models.Interestingly,RFM works best in one-third of instances,particularly when dealing with outliers,whereas traditional statistical models work better in two-thirds of instances.The results highlight AI's value in bituminous mixture optimisation,where RFM showed good prediction accuracy.In 30%of the cases,AI models outperformed the conventional statistical approaches.At the same time,analyses show that model performance varies significantly with scenarios and that even if AI models capture complex nonlinear relationships,they must not override DOE principles.
文摘Classical linear discriminant analysis(LDA)(Fisher,1936)implicitly assumes the classification boundary depends on only one linear combination of the predictors.This restriction can lead to poor classification in applications where the decision boundary depends on multiple linear combinations of the predictors.To overcome this challenge,the authors first project the predictors onto an envelope central space and then perform LDA based on the sufficient predictor.The performance of the proposed method in improving classification accuracy is demonstrated in both synthetic data and real applications.
基金supported by the Ministry of Research,Innovation and Digitization,CNCS/CCCDI–UEFISCDI(Romania),Nr.11/2024,within PNCDI IV.The APC received no external funding.
文摘This work addresses optimality aspects related to composite laminates having layers with different orientations.RegressionNeuralNetworks can model the mechanical behavior of these laminates,specifically the stressstrain relationship.If this model has strong generalization ability,it can be coupled with a metaheuristic algorithm–the PSO algorithm used in this article–to address an optimization problem(OP)related to the orientations of composite laminates.To solve OPs,this paper proposes an optimization framework(OFW)that connects the two components,the optimal solution search mechanism and the RNN model.The OFW has two modules:the search mechanism(Adaptive Hybrid Topology PSO)and the Prediction and Computation Module(PCM).The PCM undertakes all the activities concerning the OP at hand:the stress-strain model,constraints checking,and computation of the objective function.Two case studies about the layers’orientations of laminated specimens are conducted to validate the proposed framework.The specimens belong to“Off-axis oriented specimens”and are subjects of two OPs.The algorithms for AHTPSO and for the two PCMs(one for each problem)are proposed and implemented by MATLAB scripts and functions.Simulations are carried out for different initial conditions.The solutions demonstrated that the OFW is effective and has a highly acceptable computational complexity.The limitation of using the OFWis the generalization ability of the RNN model or any other regression models.To harness the RNN model efficiently,it must have a very good generalization power.If this condition ismet,the OFWcan be integrated into any design process to make optimal choices of the layers’orientations.
文摘While parametric Software Reliability Growth Models(SRGMs)serve as a cornerstone in software reliability assessment,their reliance on known fault-detection time distributions often presents a significant limitation in practical software testing.In this study,the authors develop a novel shaperestricted spline estimator for quantifying software reliability.Compared with parametric SRGMs,the proposed estimator not only shares a key characteristic with parametric SRGMs,but also obviates the need for specifying fault-detection time distributions.More importantly,it effectively utilizes the critical shape information of the mean value function(MVF)of fault-detection process,a detail seldom considered in prior work.Moreover,the authors investigate the predictive performance of the proposed methods by employing the so-called one-step look-ahead prediction method.Furthermore,the authors show that under certain conditions,the shape-restricted spline estimator will attain the point-wise convergence rate O_P(n~(-3/7)).In numerical experiment,the authors show that spline estimators under restriction demonstrate competitive performance compared to parametric and certain non-parametric models.
基金Natural Science Foundation of Beijing Municipality under Grant L243004the National Natural Science Foundation of China under Grant 62403060.
文摘Protective hardware is essential for mitigating damage caused by unavoidable falls in humanoid robots.Despite notable progress in fall protection hardware,the theoretical foundation for modeling and the feasibility of conducting full-scale fall experiments on robots or their surrogates remain somewhat limited.This paper proposes a method for optimizing the thickness of Expandable Polyethylene(EPE),which is used as back protection for the Chubao humanoid robot,based on small-scale impact test data to predict full-scale behavior.The optimal thickness is defined as a balance between compact design and protective effectiveness.An equivalent impact model characterized by four parameters:contact area S,mass m,fall height h,and cushioning material thickness d is introduced to describe impact conditions.The relationship between the peak impact acceleration ap and material thickness d,which forms the core of the method and gives rise to the name AP-D,is analyzed through their plotted curves.After introducing three characteristic parameters and two correction fac-tors,the relationship among the aforementioned variables is derived.Subsequently,both the optimal thickness do and its corresponding peak impact acceleration aop are predicted via nonlinear and linear regression models.Finally,the accuracy and effectiveness of the theoretically derived optimal thickness are validated on both a dummy and the actual robot.With the cushioning material applied,the peak chest acceleration is reduced to 41.57g for the dummy and 32.08g for the robot.
基金supported by the Open Research Fund of Key Laboratory of Advanced Theory and Application in Statistics and Data Science(East China Normal University),Ministry of Educationsupported by the National Natural Scientific Foundation of China under Grant No.NSFC12131006the Scientific and Technological Innovation Project of China Academy of Chinese Medical Science under Grant No.CI2023C063YLL。
文摘This paper examines whether the parametric regression model is correctly specified for both source and target data and whether the regression pattern in the source domain aligns with that of the target domain.This evaluation is a critical prerequisite for applying model-based transfer learning methods under covariate shift assumptions.Traditional regression model checks and twosample regression tests are insufficient to address this issue.To overcome these limitations,the authors propose a novel adaptive-to-regression test statistic that is asymptotically distribution-free.Under the null hypothesis,the test follows a chi-square weak limit,preserving the significance level and enabling critical value determination without resampling techniques.Additionally,the authors systematically analyze the test's power performance,highlighting its sensitivity to different sub-local alternatives that deviate from the null hypothesis.Numerical studies,including simulations,assess finite-sample performance,and a real-world data example is provided for illustration.
文摘BACKGROUND:Rapid identification of patients at risk of clinical deterioration(in-hospital mortality) in emergency settings is essential for timely and appropriate care.Existing prognostic scores,such as the Acute Physiology and Chronic Health Evaluation IV(APACHE IV),Simplified Acute Physiology Score 3(SAPS 3),Sequential Organ Failure Assessment(SOFA),and National Early Warning Score 2(NEWS 2),have limitations in emergency scenarios,particularly in resource-limited settings.We aimed to develop a simple and efficient tool tailored to the Brazilian healthcare system.METHODS:This retrospective,multicenter,cohort study analyzed data from 50,709 adult patients admitted to 12 hospitals in southern and southeastern Brazil between 2019 and 2020.The BRASIL score(Brazilian Risk Assessment Severity Index and Length of stay) was constructed using demographic and clinical variables available at admission.Logistic regression was used to determine the weight of each variable,and each variable was assigned a point value based on its β-coefficient and clinical relevance,with thresholds defined according to established medical cutoffs and statistical performance.The score's predictive accuracy was validated using the area under the receiver operating characteristic curve(AUC) with comparative analysis against NEWS 2.RESULTS:The BRASIL score,including age,sex,respiratory rate,heart rate,oxygen saturation,blood pressure,and body temperature,was derived through variables independently associated with in-hospital mortality in a multicenter cohort.The total score was stratified into three risk categories — low(0–3 points),moderate(4–7 points),and high(>7 points) — using observed inflection points in mortality distribution to optimize discrimination.This stratification demonstrated a stepwise increase in mortality rates across categories and the discriminatory performance,with an overall AUC of 0.743(95% CI:0.726–0.761).Compared to NEWS 2(AUC 0.697,95% CI:0.683–0.711),the BRASIL score offered superior early risk identification,supporting timely clinical decisionmaking and resource allocation in the emergency setting.CONCLUSION:The BRASIL score is a novel tool for predicting in-hospital mortality in emergency departments.Its predictive performance and ease of use suggest that it has the potential to improve patient outcomes.
文摘Traditional oilfields face increasing extraction challenges, primarily due to reservoir quality degradation and production decline, which are further exacerbated by volatile international crude oil prices—illustrated by Brent Crude’s trajectory from pandemic-induced negative pricing to geopolitically driven surges exceeding USD 100 per barrel. This study addresses these complexities through an integrated methodological framework applied to medium-permeability sandstone reservoirs in the Xinjiang oilfield by combining advanced numerical simulations with multivariate regression analysis. The methodology employs Latin Hypercube Sampling (LHS) to stratify geological parameter distributions and constructs heterogeneous reservoir models using Petrel software, rigorously validated through historical production data matching. Production forecasting integrates numerical simulation and Decline Curve Analysis (DCA), while investment estimation utilizes Ordinary Least Squares (OLS) regression to correlate engineering parameters with drilling and completion costs. Economic evaluation incorporates Discounted Cash Flow (DCF) modeling and breakeven analysis, establishing techno-economic boundaries via oil price sensitivity analysis ranging from USD 40 to 90 per barrel. Visualization tools, including 3D heatmaps, delineate nonlinear interactions among engineering, geological, and investment datasets under economic constraints. Key findings demonstrate that for the target reservoirs, as oil prices increase from USD 40 to USD 90 per barrel, the minimum economic thickness threshold decreases from approximately 5.7 m to about 2.5 m, with model prediction errors consistently below 25% across validation datasets. This framework provides scientifically grounded decision support for optimizing capital allocation and offers actionable insights to enhance undeveloped hydrocarbon development planning amid market uncertainty. Ultimately, it supports national energy security through technically robust and economically viable resource exploitation strategies.
基金supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(RS-2020-NR049579).
文摘High-dimensional data causes difficulties in machine learning due to high time consumption and large memory requirements.In particular,in amulti-label environment,higher complexity is required asmuch as the number of labels.Moreover,an optimization problem that fully considers all dependencies between features and labels is difficult to solve.In this study,we propose a novel regression-basedmulti-label feature selectionmethod that integrates mutual information to better exploit the underlying data structure.By incorporating mutual information into the regression formulation,the model captures not only linear relationships but also complex non-linear dependencies.The proposed objective function simultaneously considers three types of relationships:(1)feature redundancy,(2)featurelabel relevance,and(3)inter-label dependency.These three quantities are computed usingmutual information,allowing the proposed formulation to capture nonlinear dependencies among variables.These three types of relationships are key factors in multi-label feature selection,and our method expresses them within a unified formulation,enabling efficient optimization while simultaneously accounting for all of them.To efficiently solve the proposed optimization problem under non-negativity constraints,we develop a gradient-based optimization algorithm with fast convergence.Theexperimental results on sevenmulti-label datasets show that the proposed method outperforms existingmulti-label feature selection techniques.
