Enhancing software effort estimation with random forest tuning and adaptive decision strategies.

BackgroundInfections caused by multidrug-resistant organisms (MDROs) continue to pose serious challenges for hospital infection control, often resulting in longer hospitalizations, increased patient morbidity, and higher healthcare costs. While time series forecasting has gained traction as a tool for anticipating MDROs trends, there remains a lack of real-world studies comparing the effectiveness of different modeling approaches using hospital-based data.ObjectiveThis study aimed to evaluate and compare the predictive performance of four time series models—SARIMA, ETS, Prophet, and NNETAR—using monthly MDROs infection data collected from a tertiary hospital in China between 2014 and 2023, with the goal of forecasting trends for 2024.MethodsMonthly MDROs infection rates from January 2014 to December 2023 were analyzed using R software. Stationarity was assessed through unit root tests, and appropriate differencing was applied as needed. Each model was fitted to the training dataset and used to forecast infection rates for the year 2024. Model accuracy was assessed by comparing forecasted values with actual 2024 data using root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), symmetric mean absolute percentage error (sMAPE), and mean absolute scaled error (MASE).ResultsAmong the models, SARIMA produced the most consistent and reliable forecasts (RMSE = 0.0469, MAE = 0.0424, MAPE = 20.74%, sMAPE = 21.27%, MASE = 0.932), with residuals satisfying tests for independence and normality. Although the ETS model achieved lower numerical point errors (RMSE = 0.0367, MAE = 0.0305, MAPE = 14.46%, sMAPE = 14.81%, MASE = 0.670), its residual diagnostics raised concerns regarding robustness. The Prophet (RMSE = 0.0499, MAE = 0.0439, MAPE = 20.41%, sMAPE = 22.15%, MASE = 0.563) and NNETAR (RMSE = 0.0697, MAPE = 30.60%, sMAPE = 30.60%, MASE = 0.072) models captured certain aspects of the data dynamics but showed lower overall robustness compared with SARIMA.ConclusionBased on its overall robustness and diagnostic consistency, SARIMA is recommended for short- to medium-term forecasting of MDROs infection trends. The other models, while less reliable on their own, may still be valuable for validating trends and conducting sensitivity analyses to support hospital infection control planning.

Malaria is a major public health concern in tropics and subtropics. Accurate malaria prediction is critical for reporting ongoing incidences of infection and its control. Hence, the purpose of this investigation was to evaluate the performances of different models of predicting malaria incidence in Marodijeh region, Somaliland. The study used monthly historical data from January 2011 to December 2020. Five deterministic and stochastic models, i.e. Seasonal Autoregressive Moving Average (SARIMA), Holt-Winters' Exponential Smoothing, Harmonic Model, Seasonal and Trend Decomposition using Loess (STL) and Artificial Neural Networks (ANN), were fitted to the malaria incidence data. The study employed Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Scaled Error (MASE) to measure the accuracy of each model. The results indicated that the artificial neural network (ANN) model outperformed other models in terms of the lowest values of RMSE (39.4044), MAE (29.1615), MAPE (31.3611) and MASE (0.6618). The study also incorporated three meteorological variables (Humidity, Rainfall and Temperature) into the ANN model. The incorporation of these variables into the model enhanced the prediction of malaria incidence in terms of achieving better prediction accuracy measures (RMSE = 8.6565, MAE = 6.1029, MAPE = 7.4526 and MASE = 0.1385). The 2-year generated forecasts based on the ANN model implied a significant increasing trend. The study recommends the ANN model for forecasting malaria cases and for taking the steps to reduce malaria incidence during the times of year when high incidence is reported in the Marodijeh region.

Globally, wind energy if properly harnessed, could serve as a source of energy generation in Africa. This study compared the performance of two Machine Learning (ML) algorithms (Linear regression and Random Forest) in predicting wind speed in five major cities in Africa (Yaoundé, Pretoria, Nairobi, Cairo and Abuja). Wind data were collected between January 1, 2000, and December 31, 2022, using the Solar Radiation Data Archive. The data preprocessing was carried out with 80% of the data used for training and 20% for validation. The performance of these ML algorithms was evaluated using Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and coefficient of determination (R2). The result shows that Nairobi (3.814795 m/s) closely followed by Cairo (3.606453 m/s) has the highest mean wind speed while Yaoundé (1.090512 m/s) has the lowest. Based on the performance metrics used, the two Machine Learning algorithms were competitive. Still, the Linear Regression (LR) algorithm outperformed the Random Forest Algorithm in predicting wind speed in all the selected major African cities. In Yaoundé (RMSE = 0.3892, MAE= 0.3001, MAPE =0.5030), Pretoria (RMSE=1.2339, MAE=0.9480, MAPE=0.7450) Nairobi (RMSE= 0.4223, MAE =0.6499, MAPE =0.1872), Nairobi (RMSE=0.6499, MAE=0.5171, MAPE =0.1872), Cairo (RMSE =1.0909, MAE =0.8544, MAPE =0.3541) and Abuja (RMSE = 0.70245, MAE =0.5441, MAPE= 0.4515) the Linear regression algorithms was found to outperformed Random Forest Regression. Therefore, the Linear regression algorithm is more reliable in predicting wind speed compared with the Random Forest regression.

Magnesium Phosphate Cement (MPC) is recognized as an effective rapid repair material, with compressive strength serving as a key mechanical property indicator for its mortar formulations. Nevertheless, due to MPC's complex composition and formulation, predicting its compressive strength remains a significant challenge. In this study, a comprehensive database was developed, incorporating four key input variables: the magnesium-to-phosphate (M/P) molar ratio, water-to-cement (W/C) mass ratio, sand-to-binder (S/B) weight ratio, and the borax-to-magnesia(B/M) weight ratio. This dataset was used to train and validate eight machine learning models, including the Lightweight Gradient Boosting (LGB) algorithm, Support Vector Machine (SVM), Decision Tree (DT), Extreme Gradient Boosting (XGB), Ridge Regression (RR), Random Forest (RF), Backpropagation Neural Network (BP), and Gradient Boosting (GB) models. The eight machine learning models were evaluated using performance metrics, including Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), Correlation Coefficient, and Root Mean Square Error (RMSE), to identify the optimal model, which was then optimized via the Gray Wolf Optimizer (GWO). The most accurate prediction of MPC compressive strength was attained using the XGB model, with the GWO-optimized XGB model showing enhancement in MAPE, MAE, R2, and RMSE by 21.8%, 60.6%, 43.9%, and 55.3% respectively, relative to the unoptimized XGB model. Employing Shapley Additive exPlanations (SHAP) values and Partial Dependence Plots (PDP), this study facilitates the identification of the most influential input variables and quantifies their effects on MPC compressive strength. The optimized model was validated against experimental data, demonstrating robust and conservative prediction behavior. While the model is trained solely to predict compressive strength, its interpretability enables rational insights into how formulation variables influence strength, thereby supporting informed mix design decisions. This framework offers a reliable and transparent computational tool for preemptive strength assessment of MPC and guides the optimization of mechanical performance in structurally demanding applications.

Eliminating canine-mediated human rabies deaths by 2030 is a global priority, necessitating a data-driven approach to understand rabies dynamics and implement effective prevention strategies. This study provides epidemiological insights into canine rabies in Chennai, analyzing nine years of surveillance data (n=428, March 2010 - February 2019) to assess trends, seasonality and predictive patterns. Change point and time series analyses were conducted and forecasting models were evaluated using Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Scaled Error (MASE) metrics. No significant seasonality was detected, but change point analysis identified two key shifts, segmenting the data into three phases and revealing an overall declining trend. Among the models tested, the Prophet model demonstrated the best predictive performance (RMSE: 1.88, MAE: 1.55, MAPE: 45.44%, MASE: 3.52), outperforming the Generalized Additive Model (GAM), Bayesian Structural Time Series (BSTS) and Seasonal Trend decomposition using Loess combined with ARIMA (STL+ARIMA (0,0,2)). This study offers critical epidemiological insights for strengthening One Health-based rabies control strategies, particularly in urban settings where canine rabies plays a major role in human exposure risk. By providing longitudinal data and predictive modelling, these findings guide targeted preventive interventions, inform evidence-based policy decisions and support global efforts to eliminate dog-mediated human rabies deaths by 2030.

Proper sales prediction is essential in retail businesses such as BigMart in order to maximize inventory, pricing policies, and business decisions. This research paper presents a superior forecasting model that integrates Recurrent Neural Networks (RNNs) and Explainable Artificial Intelligence (XAI) methods to predict BigMart sales. The framework learns both the short- and long-run temporal dynamics in the sales data by training an RNN model on past transactional history, product attributes, and store-level features. To make the model more transparent, we combine XAI techniques, i.e., SHAP (Shapley Additive explanations) and LIME (Local Interpretable Model-Agnostic Explanations), and identify the most essential features that drive sales predictions. The following performance measures are used to test the proposed model: Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and R2. Findings indicate that the RNN-XAI model outperforms traditional models, such as ARIMA and XGBoost. In particular, the RNN-XAI model yields the following results: RMSE = 93.14, MAE = 72.45, MAPE = 8.11, and R2 = 0.94, indicating strong predictive power and strong explanatory features. This underscores the fact that variables such as Item MRP, Outlet Type, and Seasonal Indicators have a significant effect on sales. Not only does the XAI integration enhance the model's accuracy, but it also provides insights that non-technical stakeholders can easily interpret and have confidence in the forecast. The given approach demonstrates the potential of combining deep learning and XAI to enhance retail industry decision-making.

The permeability coefficient of soils is an essential measure for designing geotechnical construction. The aim of this paper was to select a highest performance and reliable machine learning (ML) model to predict the permeability coefficient of soil and quantify the feature importance on the predicted value of the soil permeability coefficient with aided machine learning‐based SHapley Additive exPlanations (SHAP) and Partial Dependence Plot 1D (PDP 1D). To acquire this purpose, five single ML algorithms including K‐nearest neighbors (KNN), support vector machine (SVM), light gradient boosting machine (LightGBM), random forest (RF), and gradient boosting (GB) are used to build ML models for predicting the permeability coefficient of soils. Performance criteria for ML models include the coefficient of correlation R 2 , root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE). The best performance and reliable single ML model for predicting the permeability coefficient of soil for the testing dataset is the gradient boosting (GB) model, which has R 2 = 0.971, RMSE = 0.199 × 10 −11 m/s, MAE = 0.161 × 10 −11 m/s, and MAPE = 0.185%. To identify and quantify the feature importance on the permeability coefficient of soil, sensitivity studies using permutation importance, SHapley Additive exPlanations (SHAP), and Partial Dependence Plot 1D (PDP 1D) are performed with the aided best performance and reliable ML model GB. Plasticity index, density > water content, liquid limit, and plastic limit > clay content > void ratio are the order effects on the predicted value of the permeability coefficient. The plasticity index and density of soil are the first priority soil properties to measure when assessing the permeability coefficient of soil.

Accurate estimation of the ultimate bearing capacity (UBC) of shallow foundations is critical for safe and economical geotechnical design. Traditional approaches depend heavily on extensive and costly field and laboratory investigations, while numerical simulations, though effective, are computationally intensive and time-consuming. To address these limitations, this study investigates the application of machine learning (ML) models for efficient and reliable prediction of the ultimate bearing capacity of shallow foundations. Although numerous studies have explored individual ML techniques for this purpose, a comprehensive and consistent comparison of widely used models under identical conditions remains limited. This research evaluates six ML algorithms; k-Nearest Neighbors (kNN), Artificial Neural Network (NN), Random Forest (RF), Extreme Gradient Boosting (xGBoost), Adaptive Boosting (AdaBoost), and Stochastic Gradient Descent (SGD), using a dataset of 169 experimental results collected from literature. The input features include foundation width (B), depth (D), length-to-width ratio (L/B), soil unit weight (γ), and angle of internal friction (φ). Model performance was assessed using multiple evaluation metrics: coefficient of determination (R²), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), Mean Squared Error (MSE), and objective function (OBJ). To enhance model interpretability, SHapley Additive Explanations (SHAP) and Partial Dependence Plots (PDPs) were employed to analyze feature importance and input-output relationships, highlighting the influence of both soil properties and foundation geometry on predicted bearing capacity. Among the evaluated models, AdaBoost demonstrated the best overall performance, achieving R² values of 0.939 and 0.881 on the training and testing sets, respectively. Based on the cumulative ranking of the models across all evaluation metrics, the models were ranked in the following order of performance: AdaBoost > kNN > RF > xGBoost > NN > SGD. While the results are promising, a key limitation is the use of single-layer soil data, which restricts applicability to more complex, multilayered soil profiles. Future studies should incorporate multilayer datasets and account for spatial variability to enhance the generalizability and robustness of predictive models.

Blast-induced rock fragmentation plays a critical role in mining and civil engineering. One of the primary objectives of blasting operations is to achieve the desired rock fragmentation size, which is a key indicator of the quality of the blasting process. Predicting the mean fragmentation size (MFS) is crucial to avoid increased production costs, material loss, and ore dilution. This study integrates three tree-based regression techniques—gradient boosting regression (GBR), histogram-based gradient boosting machine (HGB), and extra trees (ET)—with two optimization algorithms, namely, grey wolf optimization (GWO) and particle swarm optimization (PSO), to predict the MFS. The performance of the resulting models was evaluated using four statistical measures: coefficient of determination (R2), root mean squared error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The results indicate that the GWO-HGB model outperformed all other models, achieving R2, RMSE, MAE, and MAPE values of 0.9402, 0.0251, 0.0185, and 0.0560, respectively, in the testing phase. Additionally, the Shapley additive explanations (SHAP), local interpretable model-agnostic explanations (LIME), and neural network-based sensitivity analyses were applied to examine how input parameters influence model predictions. The analysis revealed that unconfined compressive strength (UCS) emerged as the most influential parameter affecting MFS prediction in the developed model. This study provides a novel hybrid intelligent model to predict MFS for optimized blasting operations in open-pit mines.

BackgroundWhile time-series models have been applied to forecast brucellosis incidence in China, systematic comparisons of multiple models remain relatively limited. This study aimed to elucidate the epidemic characteristics of human brucellosis and to provide a comparative assessment of several time-series prediction models, in order to identify a suitable predictive framework for future incidence forecasting.MethodsMonthly and annual incidence rates (per 100,000 population) of brucellosis in China from January 2011 to December 2020 were used as raw data. Seven time-series models were developed and compared using R software (version 4.3.1): Seasonal Autoregressive Integrated Moving Average (SARIMA), Holt-Winters additive model, Holt-Winters multiplicative model, Neural Network Autoregressive (NNAR) model, Exponential Smoothing State Space (ETS) model, TBATS model, and Prophet model. A rolling-window cross-validation was applied to assess model stability. Model performance was evaluated using root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and mean absolute scaled error (MASE).ResultsAmong the seven models evaluated, the Holt-Winters multiplicative model demonstrated the most stable and superior predictive performance on the test set (MAE = 0.034, RMSE = 0.040, MAPE = 14.881%, MASE = 0.891), which serves as strong evidence for its best generalization capability among the compared models.ConclusionsGiven its stable and superior performance in the test set, the Holt-Winters multiplicative model is recommended for short-term brucellosis forecasting in China. It captures the characteristic spring-summer peak, and its integration into surveillance systems could enhance early warning and targeted interventions.

Predicting egg production rate and egg weight of broiler breeders based on machine learning and Shapley additive explanations

This study presents an innovative approach to predicting the compressive strength (CS) of recycled rubberized concrete (RC) using advanced hybrid machine learning (ML) algorithms. The integration of recycled rubber in concrete offers significant environmental and sustainability benefits by reducing waste and promoting circular construction practices. Its heterogeneous nature introduces complexity in accurately estimating mechanical properties through traditional empirical models. To address this challenge, five ML models, XGB, RF, GBR, and two hybrid ensembles, XGB–RF and XGB–GBR, were developed and evaluated using a data set comprising 369 experimental samples with seven key mix-design parameters. The innovation of this work lies in the development and comparison of hybrid learning frameworks, which effectively capture nonlinear relationships among input parameters and enhance model generalization beyond conventional ML techniques. Model performance was rigorously validated using statistical metrics, such as the coefficient of determination (R2), mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE). The XGB model achieved the highest predictive accuracy R2 = 0.904, RMSE = 3.835 MPa, and MAE = 2.697, outperforming other individual and hybrid models. The XGB–GBR model achieved a high predictive accuracy of R2 = 0.879, RMSE = 4.012 MPa, further validating the strength of hybrid ensemble approaches. To further interpret model behavior, SHAP (SHapley Additive exPlanations) and partial dependence plot (PDP) analyses were conducted, revealing that rubberized aggregate (RA) content exerts the most significant negative influence on CS, followed by notable effects from fine aggregate, superplasticizer, and water content. The study not only highlights the effectiveness of AI-driven methods in forecasting concrete strength but also identifies optimal material proportions for mix design improvement. This research demonstrates that hybrid ML techniques provide a cost-effective, rapid, and highly accurate alternative to conventional testing for RC, offering valuable insights for sustainable material optimization and decision-making in modern civil engineering.

Predicting the fundamental fluxes of an eddy-covariance station using machine learning methods

BackgroundLength of postoperative stay (LOPS) is an important indicator for resource allocation and clinical management in elderly patients with hip fractures. However, previous studies have mostly dichotomized this continuous variable to determine whether it is prolonged, a practice that inherently reduces information and introduces limitations. This study aimed to develop and validate a machine learning (ML) model to accurately predict the specific LOPS in elderly patients with hip fractures.MethodsThis retrospective cohort study included electronic health records (EHRs) of elderly patients with hip fractures admitted to Yichang Central People’s Hospital from January 2016 to December 2022, with a total of 734 patients. Variables commonly measured preoperatively were extracted based on a review of previous studies, and features were selected using Pearson correlation coefficients combined with LASSO regression to construct a backpropagation neural network (BP-NN) model. For comparative evaluation, support vector machine (SVM) and random forest (RF) regression models were developed under the same dataset split (8:2), feature set, and hyperparameter optimization strategy. Model performance was assessed by comparing predicted values versus actual LOPS and calculating root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and error thresholds (20%, 30%). The feature importance of the BP-NN model was analyzed via SHapley Additive exPlanations (SHAP) values.ResultsAmong 734 elderly patients with hip fractures, 503 (68.53%) were female, with an average LOPS of 17.42± 3.77 days. Femoral neck fracture (59.26%) and hemiarthroplasty (41.96%) were the most common fracture type and surgical type, respectively. Pearson correlation analysis and LASSO regression showed that age, age-adjusted Charlson comorbidity index (ACCI), and surgical type were the predictors of LOPS. Further sensitivity analysis adjusting for confounding factors revealed that the very old elderly group (aged or above 90 years) had the longest LOPS (15.84± 0.15 days vs. 17.85± 0.14 days vs. 21.99 ± 0.66 days), with no statistically significant difference in LOPS between different surgical type subgroup (P > 0.05). The predicted values of the BP-NN were consistent with the trend of actual LOPS (R2 = 0.83), with the vast majority of prediction results falling within 30% clinically acceptable error threshold. Its RMSE, MAE and MAPE of 1.23 days, 1.57 days and 7.69% respectively. SHAP analysis revealed that ACCI and age were the main factors influencing LOPS.ConclusionThe BP-NN model, enhanced by multimethod feature selection, rigorous parameter tuning, and SHAP based interpretability, provides early and accurate LOPS prediction for elderly hip fracture patients. It can be used as a tool to assist in clinical decision-making, resource planning, and discharge preparation, without increasing the clinical burden. Future external validation across multiple centers is needed to confirm generalizability.

Predicting future PM2.5 concentrations based on knowledge obtained from past observational data is very useful for predicting air pollution. This paper aims to develop a hybrid forecasting model using an Artificial Neural Network (ANN) and Triple Exponential Smoothing (TES) on clustered PM2.5 data from a HPR (High Pollution Region), MPR (Medium Pollution Region), and LPR (Low Pollution Region) in Malaysia. Historical PM2.5 concentrations in Malaysia from January 2018 to December 2019 were used to develop a hybrid model. The proposed hybrid model was then evaluated in terms of Mean Absolute Percentage Error (MAPE) values by comparing them with real PM2.5 data from the year 2020 in the HPR, MPR and LPR. The results showed that the hybrid model of ANN and TES presented the lowest RMSE (Root Mean Squared Error) (4.25–8.56 µg m−3), MAE (Mean Absolute Error) (2.51–4.95 µg m−3), MAPE (0.13–0.2%), and MASE (Mean Absolute Scaled Error) (1.45–2.01) in different areas of pollution compared with other models. The comparison between the ANN and TES hybrid models and the real PM2.5 data in 2020 showed that the models gave sufficient accuracy in the HPR and MPR with MAPE values of between 20% and 50%, while the LPR showed less accuracy due to the high value of MAPE of more than 50%. Overall, the hybrid model developed in this study opens up a new prediction method for air quality forecasting and is sufficiently accurate to be used as a tool for air quality management.