Search Results (5,446)

Resistance spot-welded joints are crucial parts in contemporary manufacturing technology due to their ubiquitous use in the automobile industry. The necessity of improving manufacturing efficiency and quality at an affordable cost requires deep knowledge of the resistance spot welding (RSW) process and the development of artificial neural network (ANN)- and machine learning (ML)-based modelling techniques, apt for providing essential tools for design, planning, and incorporation in the welding process. Tensile shear force and nugget diameter are the most crucial outputs for evaluating the quality of a resistance spot-welded specimen. This study uses ML and ANN models to predict shear force and nugget diameter responses to RSW parameters. The RSW analysis was executed on similar and dissimilar AISI 304 and grade 2 titanium alloy joints with equal and unequal thicknesses. The input parameters included welding current, pressure, welding duration, squeezing time, holding time, pulse welding, and sheet thickness. Linear regression, Decision tree, Support vector machine (SVM), Random forest (RF), Gradient-boosting, CatBoost, K-Nearest Neighbour (KNN), Ridge, Lasso, and ElasticNet machine learning algorithms, along with two different structures of Multilayer Perceptron, were utilized for studying the impact of the RSW parameters on the shear force and nugget diameter. Different validation metrics were applied to assess each model’s quality. Two equations were developed to determine the shear force and nugget diameter based on the investigation parameters. The current research also presents a prediction of the Relative Importance (RI) of RSW factors. Shear force and nugget diameter predictions were examined using SHapley (SHAP) Additive Explanations for the first time in the RSW field. Trainbr as the training function and Logsig as the transfer function delivered the best ANN model for predicting shear force in a one-output structure. Trainrp with Tansig made the most accurate predictions for nugget diameter in a one-output structure and for shear force and diameter in a two-output structure. Depending on validation metrics, the Random forest model outperformed the other ML algorithms in predicting shear force or nugget diameter in a one-output model, while the Decision tree model gave the best prediction using a two-output structure. Linear regression made the worst ML predictions for shear force, while ElasticNet made the worst nugget diameter forecasts in a one-output model. However, in two-output models, Lasso made the worst predictions. Full article

Hyperspectral compressed imaging is a novel imaging detection technology based on compressed sensing theory that can quickly acquire spectral information of terrestrial objects in a single exposure. It combines reconstruction algorithms to recover hyperspectral data from low-dimensional measurement images. However, hyperspectral images from different scenes often exhibit high-frequency data sparsity and existing deep reconstruction algorithms struggle to establish accurate mapping models, leading to issues with detail loss in the reconstruction results. To address this issue, we propose a hyperspectral reconstruction method based on global gradient information and local low-rank priors. First, to improve the prior model’s efficiency in utilizing information of different frequencies, we design a gradient sampling strategy and training framework based on decision trees, leveraging changes in the loss function gradient information to enhance the model’s predictive capability for data of varying frequencies. Second, utilizing the local low-rank prior characteristics of the representative coefficient matrix, we develop a sparse sensing denoising module to effectively improve the local smoothness of point predictions. Finally, by establishing a regularization term for the reconstruction process based on the semantic similarity between the denoised results and prior spectral data, we ensure spatial consistency and spectral fidelity in the reconstruction results. Experimental results indicate that the proposed method achieves better detail recovery across different scenes, demonstrates improved generalization performance for reconstructing information of various frequencies, and yields higher reconstruction quality. Full article

The Artificial Tree project, developed by the authors, presents an innovative approach to urban sustainability by integrating microalgae cultivation systems for CO₂ capture, biomass production, and urban cooling. This study evaluates the project’s feasibility and effectiveness in transforming urban furniture into functional photobioreactors that enhance environmental quality. Inspired by natural aesthetics, the Artificial Tree functions as both a CO₂ sink and a biofertilizer producer. Using Scenedesmus microalgae, the system captures 50 kg of CO₂ annually per unit and generates 28 kg of biomass, which further reduces emissions when utilized as a biofertilizer. To assess its impact, a multi-criteria decision analysis (MCDA) method was employed, considering factors such as CO₂ capture, biomass production, social engagement, visual appeal, and scalability. This methodology incorporated a three-level qualitative scale and criteria tailored to compare similar projects with at least three months of operation and available data on microalgae productivity. Results highlight that the Artificial Tree achieves up to 2.5 times more CO₂ fixation than a mature tree while combining environmental benefits with public engagement. Its modular and aesthetic design supports educational outreach and inspires larger-scale implementation. This project demonstrates significant potential to redefine urban spaces sustainably by seamlessly integrating functionality, artistic expression, and public interaction. Full article

This article devises the Artificial Intelligence (AI) methods of designing models of short-term forecasting (in 12 h and 24 h horizons) of electricity production in a selected Small Hydropower Plant (SHP). Renewable Energy Sources (RESs) are difficult to predict due to weather variability. Electricity production by a run-of-river SHP is marked by the variability related to the access to instantaneous flow in the river and weather conditions. In order to develop predictive models of an SHP facility (installed capacity 760 kW), which is located in Southern Poland on the Skawa River, hourly data from nearby meteorological stations and a water gauge station were collected as explanatory variables. Data on the water management of the retention reservoir above the SHP were also included. The variable to be explained was the hourly electricity production, which was obtained from the tested SHP over a period of 3 years and 10 months. Obtaining these data to build models required contact with state institutions and private entrepreneurs of the SHP. Four AI methods were chosen to create predictive models: two types of Artificial Neural Networks (ANNs), Multilayer Perceptron (MLP) and Radial Base Functions (RBFs), and two types of decision trees methods, Random Forest (RF) and Gradient-Boosted Decision Trees (GBDTs). Finally, after applying forecast quality measures of Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R²), the most effective model was indicated. The decision trees method proved to be more accurate than ANN models. The best GBDT models’ errors were MAPE 3.17% and MAE 9.97 kWh (for 12 h horizon), and MAPE 3.41% and MAE 10.96 kWh (for 24 h horizon). MLPs had worse results: MAPE from 5.41% to 5.55% and MAE from 18.02 kWh to 18.40 kWh (for 12 h horizon), and MAPE from 7.30% to 7.50% and MAE from 24.12 kWh to 24.83 kWh (for 24 h horizon). Forecasts using RBF were not made due to the very low quality of training and testing (the correlation coefficient was approximately 0.3). Full article

Linear programming models have been used in forest management planning since the 1960s. These models have been formulated in three basic ways: Models I, II, and III, which are defined by the sequences of management unit states represented by the variables. In Model I, variables represent sequences of states from the beginning of the planning horizon to the end. In Model II, variables represent sequences of states from one intervention to the next. Finally, in Model III, variables represent a single arc in a management unit’s decision tree, i.e., two states. The objectives of this paper are to clarify the definitions of these model variations and evaluate the advantages and disadvantages of each model. This second objective is to test the hypothesis that the relative performance of these models varies with the increasing number of ecosystem services (ES) incorporated into the models. This objective was achieved by formulating a case study problem using each model type. The case study includes three increasingly complex scenarios, each incorporating additional ecosystem services. Results show that despite having more variables and constraints, Model III requires the least time to formulate due to its less dense parameter matrix. Model II has the shortest solution times, followed closely by Model III, while Model I requires the longest times for both formulation and solution. These results are increasingly apparent in more complex scenarios. Full article

Background. Sepsis presents significant diagnostic and prognostic challenges, and traditional scoring systems, such as SOFA and APACHE, show limitations in predictive accuracy. Machine learning (ML)-based predictive survival models can support risk assessment and treatment decision-making in the intensive care unit (ICU) by accounting for the numerous and complex factors that influence the outcome in the septic patient. Methods. A systematic literature review of studies published from 2014 to 2024 was conducted using the PubMed database. Eligible studies investigated the development of ML models incorporating commonly available laboratory and clinical data for predicting survival outcomes in adult ICU patients with sepsis. Study selection followed the PRISMA guidelines and relied on predefined inclusion criteria. All records were independently assessed by two reviewers, with conflicts resolved by a third senior reviewer. Data related to study design, methodology, results, and interpretation of the results were extracted in a predefined grid. Results. Overall, 19 studies were identified, encompassing primarily logistic regression, random forests, and neural networks. Most used datasets were US-based (MIMIC-III, MIMIC-IV, and eICU-CRD). The most common variables used in model development were age, albumin levels, lactate levels, and ventilator. ML models demonstrated superior performance metrics compared to conventional methods and traditional scoring systems. The best-performing model was a gradient boosting decision tree, with an area under curve of 0.992, an accuracy of 0.954, and a sensitivity of 0.917. However, several critical limitations should be carefully considered when interpreting the results, such as population selection bias (i.e., single center studies), small sample sizes, limited external validation, and model interpretability. Conclusions. Through real-time integration of routine laboratory and clinical data, ML-based tools can assist clinical decision-making and enhance the consistency and quality of sepsis management across various healthcare contexts, including ICUs with limited resources. Full article

Rapid population growth accelerates changes in land use and land cover (LULC), straining natural resource availability. Monitoring LULC changes is essential for managing resources and assessing climate change impacts. This study focused on extracting LULC data from 1993 to 2024 using the classification and regression tree (CART) method on the Google Earth Engine (GEE) platform in Qena Governorate, Egypt. Moreover, the cellular automata (CA) Markov model was used to anticipate the future changes in LULC for the research area in 2040 and 2050. Three multispectral satellite images—Landsat thematic mapper (TM), enhanced thematic mapper (ETM+), and operational land imager (OLI)—were analyzed and verified using the GEE code editor. The CART classifier, integrated into GEE, identified four major LULC categories: urban areas, water bodies, cultivated soils, and bare areas. From 1993 to 2008, urban areas expanded by 57 km², while bare and cultivated soils decreased by 12.4 km² and 42.7 km², respectively. Between 2008 and 2024, water bodies increased by 24.4 km², urban areas gained 24.2 km², and cultivated and bare soils declined by 22.2 km² and 26.4 km², respectively. The CA-Markov model’s thematic maps highlighted the spatial distribution of forecasted LULC changes for 2040 and 2050. The results indicated that the urban areas, agricultural land, and water bodies will all increase. However, as anticipated, the areas of bare lands shrank during the years under study. These findings provide valuable insights for decision makers, aiding in improved land-use management, strategic planning for land reclamation, and sustainable agricultural production programs. Full article

The relationship between coronary heart disease (CHD) and complex urban built environments remains a subject of considerable uncertainty. The development of predictive models via machine learning to explore the underlying mechanisms of this association, as well as the formulation of intervention policies and planning strategies, has emerged as a pivotal area of research. A cross-sectional dataset of hospital admissions for CHD over the course of a year from a hospital in Dalian City, China, was assembled and matched with multi-source built environment data via residential addresses. This study evaluates five machine learning models, including decision tree (DT), random forest (RF), eXtreme gradient boosting (XGBoost), multi-layer perceptron (MLP), and support vector machine (SVM), and compares them with multiple linear regression models. The results show that DT, RF, and XGBoost exhibit superior predictive capabilities, with all R² values exceeding 0.70. The DT model performed the best, with an R² value of 0.818, and the best performance was based on metrics such as MAE and MSE. Additionally, using explainable AI techniques, this study reveals the contribution of different built environment factors to CHD and identifies the significant factors influencing CHD in cold regions, ranked as age, Digital Elevation Model (DEM), house price (HP), sky view factor (SVF), and interaction factors. Stratified analyses by age and gender show variations in the influencing factors for different groups: for those under 60 years old, Road Density is the most influential factor; for the 61–70 age group, house price is the top factor; for the 71–80 age group, age is the most significant factor; for those over 81 years old, building height is the leading factor; in males, GDP is the most influential factor; and in females, age is the most influential factor. This study explores the feasibility and performance of machine learning in predicting CHD risk in the built environment of cold regions and provides a comprehensive methodology and workflow for predicting cardiovascular disease risk based on refined neighborhood-level built environment factors, offering scientific support for the construction of sustainable healthy cities. Full article

Surface texturing plays a vital role in enhancing tribological performance, reducing friction and wear, and improving durability in industrial applications. This study introduces an innovative approach by employing machine learning models—specifically, decision trees, support vector machines, and artificial neural networks—to predict optimal femtosecond laser surface texturing parameters for tungsten carbide tested with WS₂ and TiCN coatings. Traditionally, the selection of laser parameters has relied heavily on a trial-and-error method, which is both time-consuming and inefficient. By integrating machine learning, this study advances beyond conventional methods to accurately predict the depth and quality of textured features. The ANN demonstrated superior predictive accuracy among the models tested, outperforming SVM and Decision Trees. This machine learning-based approach not only optimizes the surface texturing process by reducing experimental effort but also enhances the resultant surface performance, making it well-suited for applications in sectors such as automotive and oil and gas. Full article

Accurate and reliable knowledge about grassland distribution is essential for farmers, stakeholders, and government to effectively manage grassland resources from agro-economical and ecological perspectives. This study developed a novel pixel-based grassland classification approach using three supervised machine learning (ML) algorithms, which were assessed in the province of Manitoba, Canada. The grassland classification process involved three stages: (1) to distinguish between vegetation and non-vegetation covers, (2) to differentiate grassland from non-grassland landscapes, and (3) to identify three specific grassland classes (tame, native, and mixed grasses). Initially, this study investigated different satellite data, such as Sentinel-1 (S1), Sentinel-2 (S2), and Landsat 8 and 9, individually and combined, using the random forest (RF) method, with the best performance at the first two steps achieved using a combination of S1 and S2. The combination was then utilized to conduct the first two steps of classification using support vector machine (SVM) and gradient tree boosting (GTB). In step 3, after filtering out non-grassland pixels, the performance of RF, SVM, and GTB classifiers was evaluated with combined S1 and S2 data to distinguish different grassland types. Eighty-nine multitemporal raster-based variables, including spectral bands, SAR backscatters, and digital elevation models (DEM), were input for ML models. RF had the highest classification accuracy at 69.96% overall accuracy (OA) and a Kappa value of 0.55. After feature selection, the variables were reduced to 61, increasing OA to 72.62% with a Kappa value of 0.58. GTB ranked second, with its OA and Kappa values improving from 67.69% and 0.50 to 72.18% and 0.58 after feature selection. The impact of raster data quality on grassland classification accuracy was assessed through multisensor image fusion. Grassland classification using the Hue, Saturation, and Value (HSV) fused images showed higher OA (59.18%) and Kappa values (0.36) than the Brovey Transform (BT) and non-fused images. Finally, a web map was created to show grassland results within the Soil Landscapes of Canada (SLC) polygons, relating soil landscapes to grassland distribution and providing valuable information for decision-makers and researchers. Future work may include extending the current methodology by considering other influential variables, like meteorological parameters or soil properties, to create a comprehensive grassland inventory across the whole Prairie ecozone of Canada. Full article

To improve radar-based quantitative precipitation estimation (QPE) methods, this study investigated the relationship between radar reflectivity (Z) and hourly rainfall intensity (R) using data from 289 precipitation events in Shanghai between September 2020 and March 2024. Two Z-R relationship models were compared in terms of their fitting performance: Z = 270.81 R^1.09 (empirically fitted relationship) and Z = 300 R^1.4 (standard relationship). The results show that the Z = 270.81 R^1.09 model outperforms the Z = 300 R^1.4 model in terms of fitting accuracy. Specifically, the Z = 270.81 R^1.09 model more effectively captures the nonlinear relationship between radar reflectivity and rainfall intensity, with a higher degree of agreement between the fitted curve and the observed data points. This model demonstrated superior performance across all 289 precipitation events. This study evaluated the performance of four machine learning approaches while incorporating five meteorological features: specific differential phase shift (KDP), echo-top height (ET), vertical liquid water content (VIL), differential reflectivity (ZDR), and correlation coefficient (CC). Nine QPE models were constructed using these inputs. The key findings are as follows: (1) For models with a single-variable input, the KAN deep learning model outperformed Random Forest, Gradient Boosting Decision Trees, Support Vector Machines, and the traditional Z-R relationship. (2) When six features were used as inputs, the accuracy of the machine learning models improved significantly, with the KAN deep learning model outperforming other machine learning methods. Compared to using only radar reflectivity, the KAN deep learning model reduced the MRE by 20.78%, MAE by 4.07%, and RMSE by 12.74%, while increasing the coefficient of determination (R²) by 18.74%. (3) The integration of multiple meteorological features and machine learning optimization significantly enhanced QPE accuracy, with the KAN deep learning model performing best under varying meteorological conditions. This approach offers a promising method for improving radar-based QPE, particularly considering seasonal, weather system, and precipitation stage differentiation. Full article

Amidst the globalization of markets, there has been a continuous intensification of competitiveness between enterprises. The modern business environment has caused a shift in how business is conducted. Opportunities and challenges arise, which put a tremendous pressure on enterprises regardless of size and industry. Entrepreneurship in enterprises plays an important role in obtaining a competitive edge in the market. Thus, entrepreneurial intentions in enterprises can often shape the future and survival of the enterprise. In this paper, the prediction of entrepreneurial intentions in enterprises through Internet marketing predictors is addressed. For this, several statistical methods in data mining were used. First, simpler approaches such as linear regression, logistic regression were used. Afterward, classifier decision trees QUEST (quick, unbiased, efficient, statistical tree), and CHAID (chi-squared automatic interaction detection) were used. The sample for analysis was 137 enterprises from Serbia. Furthermore, a supervised machine learning algorithm, support vector machine (SVM) was used. Finally, a feed-forward neural network (FNN) was applied. The results varied across the applied approach, thus providing significant insights into the dynamics of data mining for prediction outcomes in an enterprise setting. Full article

For tropical rainforest regions with dense vegetation cover, the development of effective large-scale soil mapping methods is crucial to improve soil management practices to replace the time-consuming and laborious conventional approaches. While machine learning (ML) algorithms demonstrate superior predictability of soil properties over linear models, their practical and automated application for predicting soil properties using remote sensing data requires further assessment. Therefore, this study aims to integrate Unmanned Aerial Vehicles (UAVs)-based hyperspectral images and Light Detection and Ranging (LiDAR) points to predict the soil properties indirectly in two tropical rainforest mountains (Diaoluo and Limu) in Hainan Province, China. A total of 175 features, including texture features, vegetation indices, and forest parameters, were extracted from two study sites. Six ML models, Partial Least Squares Regression (PLSR), Random Forest (RF), Adaptive Boosting (AdaBoost), Gradient Boosting Decision Trees (GBDT), Extreme Gradient Boosting (XGBoost), and Multilayer Perceptron (MLP), were constructed to predict soil properties, including soil acidity (pH), total nitrogen (TN), soil organic carbon (SOC), and total phosphorus (TP). To enhance model performance, a Bayesian optimization algorithm (BOA) was introduced to obtain optimal model hyperparameters. The results showed that compared with the default parameter tuning method, BOA always improved models’ performances in predicting soil properties, achieving average R² improvements of 202.93%, 121.48%, 8.90%, and 38.41% for soil pH, SOC, TN, and TP, respectively. In general, BOA effectively determined the complex interactions between hyperparameters and prediction features, leading to an improved model performance of ML methods compared to default parameter tuning models. The GBDT model generally outperformed other ML methods in predicting the soil pH and TN, while the XGBoost model achieved the highest prediction accuracy for SOC and TP. The fusion of hyperspectral images and LiDAR data resulted in better prediction of soil properties compared to using each single data source. The models utilizing the integration of features derived from hyperspectral images and LiDAR data outperformed those relying on one single data source. In summary, this study highlights the promising combination of UAV-based hyperspectral images with LiDAR data points to advance digital soil property mapping in forested areas, achieving large-scale soil management and monitoring. Full article

Global warming and extreme climate conditions caused by unsuitable temperature and humidity lead to coffee leaf rust (Hemileia vastatrix) diseases in coffee plantations. Coffee leaf rust is a severe problem that reduces productivity. Currently, pesticide spraying is considered the most effective solution for mitigating coffee leaf rust. However, the application of pesticide spray is still not efficient for most farmers worldwide. In these cases, pruning the most infected leaves with leaf rust at coffee plantations is important to help pesticide spraying to be more efficient by creating a more targeted, accessible treatment. Therefore, detecting coffee leaf rust is important to support the decision on pruning infected leaves. The dataset was acquired from a coffee farm in Majalengka Regency, Indonesia. Only images with clearly visible spots of coffee leaf rust were selected. Data collection was performed via two devices, a digital mirrorless camera and a phone camera, to diversify the dataset and test it with different datasets. The dataset, comprising a total of 2024 images, was divided into three sets with a ratio of 70% for training (1417 images), 20% for validation (405 images), and 10% for testing (202 images). Images with leaves infected by coffee leaf rust were labeled via LabelImg^® with the label “CLR”. All labeled images were used to train the YOLOv5 and YOLOv8 algorithms through the convolutional neural network (CNN). The trained model was tested with a test dataset, a digital mirrorless camera image dataset (100 images), a phone camera dataset (100 images), and real-time detection with a coffee leaf rust image dataset. After the model was trained, coffee leaf rust was detected in each frame. The mean average precision (mAP) and recall for the trained YOLOv5 model were 69% and 63.4%, respectively. For YOLOv8, the mAP and recall were approximately 70.2% and 65.9%, respectively. To evaluate the performance of the two trained models in detecting coffee leaf rust on trees, 202 original images were used for testing with the best-trained weight from each model. Compared to YOLOv5, YOLOv8 demonstrated superior accuracy in detecting coffee leaf rust. With a mAP of 73.2%, YOLOv8 outperformed YOLOv5, which achieved a mAP of 70.5%. An edge device was utilized to deploy real-time detection of CLR with the best-trained model. The detection was successfully executed with high confidence in detecting CLR. The system was further integrated into pruning solutions for Arabica coffee farms. A pruning device was designed using Autodesk Fusion 360^® and fabricated for testing on a coffee plantation in Indonesia. Full article

This study explores a method to improve the site selection for elderly care facilities in an aging region, using Hefei City, China, as the study area. It combines topographic conditions, population distribution, economic development status, and other multi-source spatial big data at a 500 m grid scale; constructs a prediction model for the suitability of sites for elderly care facilities based on integrated learning; and carries out a comprehensive evaluation and feature importance analysis. Finally, it uses trained random forest (RF) and gradient boosting decision tree (GBDT) models to predict preliminary site selection results for elderly care facilities. A second screening that compares three degrees of population aging is conducted to obtain the final site selection results. The results show the following: (1) The comprehensive evaluation indexes of the two integrated learning models, RF and GBDT, are above or below 80% as needed, which is better than the four single learning models. (2) The prediction results of the RF and GBDT models have 87.9% and 78.4% fit to existing elderly facilities, respectively, which indicates that the methods are reasonable and reliable. (3) The results of both the RF and GBDT models indicate that the closest distance to healthcare facilities and the size of the population distribution are the two most important factors affecting the location of elderly care facilities. (4) The results of the preliminary site selection show an overall spatial distribution of higher suitability in the main urban area and lower suitability in the suburban counties. The secondary screening finds that priority needs to be given to the periphery of the main urban area and to Lujiang County and other surrounding townships that have a more serious degree of aging as soon as possible in the site selection of new elderly care facilities. Full article