An ensemble learning with sequential model-based optimization approach for pavement roughness estimation using smartphone sensor data

Use of claims data to predict the inpatient length of stay among U.S. stroke patients

Optimized machine learning models for predicting crown convergence of plateau mountain tunnels

Machine learning-based design of target property-oriented fuels using explainable artificial intelligence

Heavy metals such as arsenic can be effectively removed through adsorption. Through material property evaluation and adsorption parameter optimization, machine learning (ML) modeling provides an alternative to lengthy laboratory experimentation. In this work, adsorption data from an earlier study employing a waste-material composite were used. To create prediction models, four non-neural network algorithms - support vector machines (SVM), Gaussian process regression (GPR), linear regression, and ensemble approaches - were used and contrasted with neural network algorithms. Nine predictors were utilized, ranging from adsorbent composition alterations to experimental circumstances. Using principal component analysis (PCA) and feature selection, together with the F-test and minimum redundancy maximum relevance (MRMR) algorithms for feature reduction, optimization was accomplished. With an R-squared of 0.939, mean absolute error (MAE) of 5.778, and root mean squared error (RMSE) of 7.119 for training and an R-squared of 0.942, MAE of 5.450, and RMSE of 6.870 for testing, the optimized GPR method offered the best predictive performance. The best R-squared values found for other algorithms were: SVM (0.922), linear regression (0.925), and ensemble (0.927). The most important variables influencing adsorption efficiency were initial arsenic concentration, time, and the iron salt content. Local interpretable model-agnostic explanations (LIME), partial dependence plot (PDP), and Shapley additive explanations (SHAP) plots were used to explain these results. This work shows that, based on model-derived parameters, non-neural network algorithms may efficiently simulate and optimize arsenic adsorption tests, providing a trustworthy substitute for neural network techniques and markedly increasing adsorption efficiency.

Compressive strength is an important mechanical property of high-strength concrete (HSC), but testing methods are usually uneconomical, time-consuming, and labor-intensive. To this end, in this paper, a long short-term memory (LSTM) model was proposed to predict the HSC compressive strength using 324 data sets with five input independent variables, namely water, cement, fine aggregate, coarse aggregate, and superplasticizer. The prediction results were compared with those of the conventional support vector regression (SVR) model using four metrics, root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and correlation coefficient (R2). The results showed that the prediction accuracy and reliability of LSTM were higher with R2 = 0.997, RMSE = 0.508, MAE = 0.08, and MAPE = 0.653 compared to the evaluation metrics R2 = 0.973, RMSE = 1.595, MAE = 0.312, MAPE = 2.469 of the SVR model. The LSTM model is recommended for the pre-estimation of HSC compressive strength under a given mix ratio before the laboratory compression test. Additionally, the Shapley additive explanations (SHAP)-based approach was performed to analyze the relative importance and contribution of the input variables to the output compressive strength.

This study focuses on optimizing C2 yields in the oxidative coupling of methane (OCM), a pivotal process for sustainable chemical production. By harnessing advanced machine learning (ML) techniques, this research aimed to predict C2 yields and identify the factors that drive catalytic performance. The Extra Trees Regressor emerged as the most effective model after a comprehensive evaluation across multiple datasets and methodologies. Key to the method was the use of an innovative Aggregated Catalyst Physicochemical Descriptor (ACPD) and stratified cross-validation, which effectively addressed feature complexity and target skewness. Hyperparameter optimization using Modified Sequential Model-Based Optimization (SMBO) further enhanced the model’s performance, achieving optimized R2 values of 61.7%, 75.9%, and 92.0% for datasets A, B, and C, respectively, with corresponding reductions in the Mean Squared Error (MSE) and Root Mean Squared Error (RMSE). Additionally, SHAP (SHapley Additive exPlanations) analysis provided a detailed understanding of the model’s decision-making process, revealing the relative importance of individual features and their contributions to the predictive outcomes. This research not only achieved state-of-the-art predictive accuracy, but also deepened our understanding of the underlying chemical dynamics, offering practical guidance for catalyst design and operational optimization. These findings mark a significant advancement in catalysis, paving the way for future innovations in sustainable chemical manufacturing.

The technology known as cemented paste backfill (CPB) has gained considerable popularity worldwide. Yield stress (YS) is a significant factor considered in the assessment of CPB’s flowability or transportability. The minimal shear stress necessary to start the flow is known as Yield stress (YS), and it serves as an excellent measure of the strength of the particle-particle interaction. The traditional evaluation and measurement of YS performed by experimental tests are time-consuming and costly, which induces delays in construction projects. Moreover, the YS of CPB depends on numerous factors such as cement/tailing ratio, solid content and oxide content of tailing. Therefore, in order to simplify YS estimation and evaluation, the Artificial Intelligence (AI) approaches including eight Machine Learning techniques such as the Extreme Gradient Boosting algorithm, Gradient Boosting algorithm, Random Forest algorithm, Decision Trees, K-Nearest Neighbor, Support Vector Machine, Multivariate Adaptive Regression Splines and Gaussian Process are used to build the soft-computing model in predicting the YS of CPB. The performance of these models is evaluated by three metrics coefficient of determination (R2), Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The 3 best models were found to predict the Yield Stress of CPB (Gradient Boosting (GB), Extreme Gradient Boosting (XGB) and Random Forest (RF), respectively) with the 3 metrics of the three models, respectively, GB {R2 = 0.9811, RMSE = 0.1327 MPa, MAE = 0.0896 MPa}, XGB {R2 = 0.9034, RMSE = 0.3004 MPa, MAE = 0.1696 MPa} and RF {R2 = 0.8534, RMSE = 0.3700 MPa, MAE = 0.1786 MPa}, for the testing dataset. Based on the best performance model including GB, XG and RF, the other AI techniques such as SHapley Additive exPlanations (SHAP), Permutation Importance, and Individual Conditional Expectation (ICE) are also used for evaluating the factor effect on the YS of CPB. The results of this investigation can help the engineers to accelerate the mixed design of CPB.

To overcome the limitations of single models in addressing complex, nonlinear problems in predicting rock shear strength parameters and the hyperparameter random selection problem, this study constructed a novel prediction framework for rock shear strength parameters. First, the light gradient boosting machine (LightGBM), extreme gradient boosting (XGBoost), categorical boosting (CatBoost), and random forest (RF) algorithms are employed as the base-learners for the ensemble model, with XGBoost serving as the meta-learner to build a stacking ensemble model. On the basis of the sparrow search algorithm (SSA), tent chaotic mapping is used to initialize the sparrow population, the Cauchy‒Gaussian hybrid mutation mechanism is used to dynamically select the probability control mutation type, the dynamic adaptive weight is used to adjust the balance between global exploration and local development, and Levy flight is used to help the sparrow population individuals jump out of the local optimum to construct the chaos-improved sparrow search algorithm (CISSA) to optimize the hyperparameters of the stacking model. Second, based on the 199 datasets of different rock types, the model was trained via fivefold cross-validation and evaluated based on the coefficient of determination (R²), root mean square error (RMSE) and mean absolute error (MAE). Concurrently, the Shapley additive explanations (SHAP) method was employed to analyse the degree of contribution of each predictive index. The results demonstrate that the CISSA-Stacking model achieves R² values of 0.9936 and 0.9744 for c and φ, respectively, with corresponding RMSE of 0.4303 and 0.7635 and MAE of 0.2161 and 0.5867, indicating significantly superior overall performance compared with benchmark models. SHAP interpretability analysis revealed that the importance rankings for c are Vp, UCS, BTS, and ρ, whereas those for φ are ρ, UCS, Vp, and BTS. Finally, intelligent prediction software based on the CISSA-Stacking model was developed. The software is simple in operation, intuitive in results and excellent in performance, enables rapid and accurate prediction of c and φ through manual input of the Vp, ρ, UCS, and BTS indices or by importing tabular data containing these four indices. The engineering application further confirmed the accuracy and practical utility of both the model and the software, providing a new efficient method for engineers to quickly and accurately estimate rock shear strength parameters.Supplementary InformationThe online version contains supplementary material available at 10.1038/s41598-025-32687-3.

An experimental investigation to predict the compressive strength of lightweight Ceramsite aggregate UHPC using boosting and bagging techniques

Gross motor coordination is a fundamental component of children's physical development and motor skill acquisition, closely associated with physical fitness, cognitive function, and overall health. This study aimed to examine the influence of physical fitness, basic coordination, and executive function (EF) on gross motor coordination, and to evaluate the predictive performance of machine learning models compared with traditional multiple linear regression (MLR). A total of 167 children (85 boys and 82 girls), aged 9-10 years, participated in the study. Gross motor coordination was assessed using the Körperkoordinationtest für Kinder (KTK). Physical fitness (e.g., 50 m sprint, standing long jump, sit-ups), basic coordination (e.g., kinesthetic differentiation, spatial orientation, balance), and EF (e.g., inhibitory control, working memory) were measured as predictors. Model performance was evaluated using R2, root mean square error (RMSE), and mean absolute error (MAE). SHapley Additive exPlanations (SHAP) were applied to interpret the best-performing model and analyze feature importance and nonlinear effects. Among the models, Random Forest Regression (RFR) achieved the highest performance (R 2 = 0.533, RMSE = 6.075, MAE = 4.850). SHAP analysis revealed that spatial orientation, body mass index (BMI), dynamic balance, standing long jump, and closed-eye balance were the most important predictors, with spatial orientation, BMI, and closed-eye balance showing notable nonlinear effects. EF contributed minimally to prediction. Spatial-body integration, physical fitness, and postural control are primary determinants of gross motor coordination in children, while cognitive regulation plays a secondary role. Training programs aiming to enhance gross motor coordination should emphasize spatial orientation, body weight management, balance, and lower-limb strength.

The interlayer bonding condition in asphalt pavement significantly affects pavement performance. This study employed machine learning techniques to predict interlayer shear strength (ISS). Feed-forward artificial neural networks (ANN) and random forest (RF) models were developed and compared with traditional multiple linear regression (MLR). Utilizing 156 datasets, divided into 70% training and 30% testing, model performance was assessed using R-squared, mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE). SHapley Additive exPlanations (SHAP) was utilized for model interpretation. The results indicated that the ANN and RF models outperformed MLR, explaining over 95% of experimental data. RF exhibited superior performance with lowest MSE, RMSE, and MAE (0.0029, 0.0538, and 0.0376 MPa). SHAP analysis highlighted the significance of temperature, normal stress, shear deformation rate, and curing time as influential variables in ISS prediction. Elevated temperature adversely influenced ISS, while normal stress, shear deformation rate, and curing time positively contributed to ISS.

The precise control of droplet generation in microfluidic systems has enabled breakthroughs in fields such as drug delivery and nanomaterial synthesis. Step emulsification, a pivotal method within this field, offers high-throughput production while generating highly uniform droplets, making it a proper technique for these applications. This study presents the first integration of machine learning with step emulsification, enabling precise predictions of droplet diameter and generation rate. Unlike previous approaches, which relied on simplified equations with limited accuracy, our method uses a large-scale dataset of 1244 samples generated through three-dimensional numerical simulations. This comprehensive dataset incorporates all influential factors in step emulsification, providing the most accurate prediction setup to date. The artificial neural network (ANN) model was developed and trained on this dataset and achieved an R 2 score of 0.989 for droplet diameter and 0.972 for generation rate, accompanied by low root mean squared error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) values, validating its high accuracy. Furthermore, sensitivity analysis using SHapley Additive exPlanations (SHAP) method was conducted to determine and discuss the most influential factors in step emulsification. Subsequently, to streamline the iterative process of achieving target droplet sizes and generation rates for researchers and industry, we developed a graphical user interface (GUI), allowing users to input parameters such as fluid properties and device geometry, generate real-time predictions, and display results. This pioneering integration of machine learning and step emulsification accelerates microfluidic design optimization, minimizing reliance on extensive trials and enabling advancements in precision-controlled droplet generation.

Accurately predicting the carbonation depth of recycled aggregate (RA) concrete is essential for durability assessment. Based on a dataset of 682 experimental samples, this study employed seven machine learning algorithms to develop prediction models for the carbonation depth of RA concrete. The Optuna framework was utilized to conduct 500 trials of hyperparameter optimization for these models, with the objective of minimizing the 5-fold cross-validated mean squared error. Results indicate that model performance improved significantly after optimization. Among them, the XGBoost model achieved the best performance, with a coefficient of determination (R2) of 0.9789, root mean squared error (RMSE) of 1.0811, mean absolute error (MAE) of 0.6972, mean absolute percentage error (MAPE) of 8.7932%, variance accounted for (VAF) of 97.8966%, and mean bias error (MBE) of 0.0641 on the test set. Explainability analysis using SHapley Additive exPlanations (SHAP) further revealed that exposure time is the most significant factor influencing the carbonation depth prediction. Additionally, considering that the database incorporates both natural and accelerated carbonation conditions, the samples were partitioned based on CO2 concentration and conducts a stratified performance evaluation. The results demonstrate that the model maintains high predictive accuracy under natural carbonation as well as across different accelerated carbonation intervals, indicating that, within the scope covered by the current dataset, the proposed approach provides a highly accurate and interpretable tool for predicting the carbonation depth of recycled aggregate concrete.

Prediction of stock closing price plays a critical role in financial planning, risk management, and informed investment decision-making. In this study, we propose a novel model that synergistically amalgamates Bidirectional GRU (BiGRU) with three complementary attention techniques—Top-k Sparse, Global, and Bahdanau Attention—to tackle the complex, intricate, and non-linear temporal dependencies in financial time series. The proposed Fused Attention Model is validated on two highly volatile, non-linear, and complex- patterned stock indices: NIFTY 50 and S&P 500, with 80% of the historical price data used for model learning and the remaining 20% for testing. A comprehensive analysis of the results, benchmarked against various baseline and hybrid deep learning architectures across multiple regression performance metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and R2 Score, demonstrates the superiority and noteworthiness of our proposed Fused Attention Model. Most significantly, the proposed model yields the highest prediction accuracy and generalization capability, with R2 scores of 0.9955 on NIFTY 50 and 0.9961 on S&P 500. Additionally, to mitigate the issues of interpretability and transparency of the deep learning model for financial forecasting, we utilized three different Explainable Artificial Intelligence (XAI) techniques, namely Integrated Gradients, SHapley Additive exPlanations (SHAP), and Attention Weight Analysis. The results of these three XAI techniques validated the utilization of three attention techniques along with the BiGRU model. The explainability of the proposed model named as BiGRU based Fused Attention (BiG-FA), in addition to its superior performance, thus offers a robust and interpretable deep learning model for time-series prediction, making it applicable beyond the financial domain.

Cost overruns remain one of the most persistent challenges in construction and infrastructure project management, often undermining efficiency, sustainability, and stakeholder trust. With the rise of digital transformation, artificial intelligence (AI) and machine learning (ML) provide new opportunities to enhance predictive decision-making and strengthen project control. This study introduces a digital project management framework that integrates the Pelican Optimization Algorithm (POA) with Light Gradient Boosting Machine (LGBM) to deliver reliable and interpretable cost overrun forecasting. The proposed POA-LightGBM model leverages metaheuristic-driven hyperparameter optimization to improve predictive performance and generalization. A comprehensive evaluation using multiple error metrics Coefficient of Determination (R2), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) demonstrates that POA-LGBM significantly outperformed baseline LGBM and alternative metaheuristic configurations, achieving an average R2 of 0.9786. To support transparency in digital project environments, SHapley Additive exPlanations (SHAPs) were employed to identify dominant drivers of cost overruns, including actual project cost, energy consumption, schedule deviation, and material usage. By embedding AI-enabled predictive analytics into digital project management practices, this study contributes to advancing digital transformation in project delivery, offering actionable insights for cost control, risk management, and sustainable infrastructure development.