Search Results (14,691)

With the advancement of the “dual carbon” goals, a high proportion of renewable energy sources are being widely integrated into the power grid, resulting in a power system characterized by numerous uncertainties, rapid changes in supply and demand, and strong multi-dimensional randomness. These characteristics pose new challenges to the safe and stable operation of the power grid. However, traditional power system reliability assessment methods are constrained by computational complexity, making it difficult to meet the demands for rapid assessment. To address this issue, this paper designs a data-assisted intelligent model to achieve rapid and accurate reliability assessment of power systems under the context of high-penetration renewable energy integration. Firstly, based on the coupling relationship between the unavailability rate of transmission lines and their operating conditions as well as aging effects, this paper establishes a model for the unavailability rate of transmission lines and proposes a method for selecting key components in the power grid. Subsequently, an analytical model for power grid reliability indicators concerning the reliability parameters of key components is constructed. By utilizing this analytical model to generate a large number of data samples, a Physics-Informed Neural Network (PINN) model is constructed and trained to enable rapid calculation of reliability indicators. Finally, the effectiveness and feasibility of the proposed method are validated through the IEEE standard test system. After analysis, the single-evaluation time of the proposed method is approximately 10 ms, representing a computational efficiency improvement of up to 63.2% compared to existing artificial intelligence models such as MGAT, TCN-BiGRU, etc. Full article

Background: Gastric cancer remains one of the leading causes of cancer-related mortality worldwide, underscoring the need for more effective diagnostic strategies. This study aims to use annotated digitized histological slides of gastric cancer and precancerous lesions to develop artificial intelligence algorithms for the diagnosis of gastric lesions. Materials and Methods: We developed a deep learning tool using a training cohort of 970 digitized gastric biopsy slides. Convolutional neural networks (CNNs) were trained for histological recognition and ICD-10 code assignment. The model was validated on an independent test cohort of 250 cases, with expert consensus as the reference standard. Performance was assessed using sensitivity, specificity, and Cohen’s kappa. Survival analysis used Kaplan–Meier, log-rank tests (SPSS 16.0; p < 0.05 significant). Results: Analysis of the training cohort led to a scoring system predicting fatal outcomes based on age and morphology (high-grade component > 70%, ulceration, absence of metaplasia/dysplasia). High-risk patients (4–5 points) had significantly worse survival than low-risk patients (0–3 points) (Log Rank = 14,754; p < 0.0001). One-year survival was 71% (low-risk) vs. 40% (high-risk); mean survival was 19.2 vs. 11.3 months. In the test cohort, the AI algorithm demonstrated 79.6% sensitivity and 86.7% specificity (p < 0.0001) for differentiating malignant from benign gastric lesions. Conclusions: A system combining AI-based analysis with a prognostic scoring model has been developed to reduce diagnostic errors and improve risk stratification in gastric cancer pathology. Full article

Predicting the concrete breakout strength of an expansion anchor embedded in short carbon fiber-reinforced concrete (SCFRC) is challenging due to the nonlinear and heterogeneous nature of fiber–matrix interaction. This study develops an Artificial Neural Network (ANN) model to estimate the breakout capacity of a single expansion anchor installed in SCFRC. Experimental data from 48 cases covering variations in compressive strength, tensile strength, fiber volume fraction, and fiber length were used to train and validate multiple ANN architectures in MATLAB’s Regression Learner. A 4-4-1 trilayered ANN with Rectified Linear Unit (ReLU) activation and 5-fold cross-validation achieved the most reliable performance, yielding R² values of 0.6726 (validation) and 0.9376 (test), with correspondingly low RMSE, MAE, and scatter index (SI < 0.1). SHAP-based sensitivity analysis identified tensile strength as the dominant predictor, contributing 70.78% to model output influence. ANN predictions were compared with the Concrete Capacity Design (CCD) model adopted by ACI and the National Structural Code of the Philippines (NSCP) and a multiple linear regression (MLR) model, showing that while the ANN is not the most precise model, it provides acceptable accuracy and captures nonlinear concrete breakout behavior more effectively than linear approaches. Results demonstrate that the ANN framework offers a viable data-driven tool for estimating concrete breakout strength in SCFRC anchorage systems. Full article

Cruise ships and superyachts have experienced significant global expansion throughout the 21st century. Although the growth in cruise passenger numbers was temporarily disrupted by the COVID-19 pandemic, occupancy rates have since rebounded and even exceeded pre-pandemic levels. This study highlights the significant environmental impact of cruise ships and luxury yachts, particularly in terms of air emissions and marine pollution. Emission levels associated with different fuel types and marine engines are analysed, including the average emissions generated by the Norwegian Cruise Line fleet while docked in ports, as well as the estimated emission reductions achievable through the implementation of onshore power supply systems. To identify environmentally preferable fuel options, a hybrid ANN/MCDM framework is applied. The weighting coefficients of eight evaluation criteria are determined using the Artificial Neural Network/Extreme Learning Machine (ANN/ELM) model, ensuring an objective and data-driven assessment of their relative importance. The ANN/ELM model was trained using emission and fuel-related data collected from the literature and industry reports, and its performance was validated using standard validation procedures, achieving satisfactory predictive accuracy for determining the weighting coefficients. The final ranking of eight fuel alternatives is subsequently performed using the Ranking Alternatives by Weighting of Evaluated Criteria (RAWEC) method. The considered alternatives include conventional and emerging marine fuels currently used in practice or under technological development (A₁–A₈), while the optimization criteria (C₁–C₈) encompass major air pollutants (CO₂, NOx, SOx, CO, PM, CH₄), the fuel cost-to-consumption ratio, and the potential impact on water pollution. The water pollution criterion is assessed qualitatively using the Saaty scale. The integrated ANN/ELM–RAWEC approach enables a systematic comparison of marine fuels and supports the identification of options with the lowest overall environmental impact. Full article

Framed within data-centric artificial intelligence, this study integrates statistics, geotechnologies and AI to improve water quality prediction. The primary objective was to identify the minimum sample size required to train robust and accurate machine learning models. Based on 30 sampling points in a tropical wetland in northern Colombia, ammonium concentration was selected as the target variable, and total dissolved solids, suspended solids, phosphate, dissolved oxygen, nitrate and chemical oxygen demand were chosen as predictors. Because 30 observations are insufficient to train robust models, data augmentation was performed using ordinary kriging (OK) and empirical Bayesian kriging (EBK). From the kriging-interpolated surfaces, 1000 synthetic points (randomly and spatially distributed while preserving the estimated spatial structure) were sampled; from this expanded dataset, subsamples of varying sizes were drawn to train six algorithms: multiple linear regression (MLR), random forest (RF), k-nearest neighbours (k-NN), gradient boosting machines (GBM), multilayer perceptron (MLP) and radial basis function neural network (RBF-NN). The RF, k-NN, MLP, RBF-NN and GBM models trained on the interpolated data exhibited excellent performance: in the testing phase, they achieved adjusted coefficients of determination > 0.95 and symmetric mean absolute percentage errors (SMAPEs) < 10%, and the resulting predictive surfaces showed comparable performance under external validation. According to the criteria of stability, goodness of fit, and external validation, the optimal minimum sample size for most algorithms was 104 observations. These results represent a significant advance in mitigating data scarcity in water quality modelling. The identification of effective data augmentation methods and the determination of appropriate sample sizes, as demonstrated here, support the robust application of AI techniques in water quality prediction. The proposed strategy is transferable to other quantitative, spatially continuous environmental variables and thus contributes to the development of the emerging subdiscipline of geospatial artificial intelligence (GeoAI). Full article

Pig weighing is an essential procedure for monitoring growth and animal health; however, conventional methods are often labor-intensive, costly, and potentially stressful. In this context, this study proposes a non-invasive approach for estimating the body weight of pigs during the growing stage based on computer vision and the YOLOv11 algorithm, enabling automatic segmentation and individual identification in multi-animal environments. The study used RGB images of 10 group-housed pigs captured throughout the growing phase, in which automatic dorsal segmentation was combined with individual identification through numerical markings. From the generated binary masks, the segmented dorsal area was extracted and used as a predictor variable in Linear Regression and a Multilayer Perceptron (MLP) Artificial Neural Network. The YOLOv11 model showed consistent performance in the segmentation task, achieving test-set metrics of Precision = 0.849, Recall = 0.886, mAP@0.50 = 0.936, and mAP@0.50–0.95 = 0.819, demonstrating good generalization capability in scenarios with intense animal interaction. In the weight prediction stage, Linear Regression and the MLP achieved high coefficients of determination (R² = 0.96 and 0.95, respectively) with low errors (RMSE = 1.52 kg and 1.63 kg; MAE = 1.20 kg and 1.25 kg), indicating a strong correlation between segmented dorsal area and actual body weight. Class-wise analysis revealed superior performance for classes 7 and 9, with R² values up to 0.98 and RMSE below 1.1 kg, whereas class 8 showed greater error dispersion, associated with higher morphological variability and a smaller number of available samples. These results demonstrate that the direct use of morphometric information extracted from segmented masks in 2D images constitutes a robust, accurate, and low-cost approach for automatic pig body-weight estimation. Moreover, this study is among the few addressing this task specifically during the growing stage, highlighting its potential for future deployment in embedded systems and intelligent monitoring platforms for precision pig farming, although further evaluation of computational efficiency and real-time performance is still required. Full article

Land Use and Land Cover (LULC) changes significantly influence flood hazard, especially in rapidly urbanizing areas like the Wadi Ibrahim watershed in Makkah, Saudi Arabia. This study analyzed the impacts of historical (2001–2025) and projected (2037) LULC changes on floods using remote sensing, GIS, and hydrological modeling with 30 m DEM and Landsat data. Urban growth was assessed from 2001, 2013, and 2025 maps, and future scenarios were simulated with the MOLUSCE plugin in QGIS using Cellular Automata–Artificial Neural Network (CA-ANN) techniques. Hydrological simulations were used to examine changes in flood discharge and response to LULC transitions. The results revealed substantial urban expansion, with built-up areas increasing from 12 km² (11%) in 2001 to 28.7 km² (26%) in 2025 and projected to reach 31.9 km² (28.3%) by 2037. The corresponding impervious surface fraction rose from 11% to 28% over the same period. Hydrological modeling for 50-, 100-, and 200-year return periods reveals a significant escalation in flood response, with peak discharge (Q_p) increasing by up to 12% and runoff volume (V) by approximately 9% between 2001 and 2037. The LULC classification using the Random Forest algorithm demonstrated strong and reliable performance, achieving an average Kappa (κ) value of 0.86, indicating almost perfect agreement. Overall, the findings underscore the need for sustainable land management to reduce flood risk in rapidly growing arid regions. Full article

This work introduces an approach to evolutionary analysis in which information encoded in amino-acid sequences is converted into a specific type of image, termed a genetic image. Genetic images derived from the amino-acid sequences of cytochrome b and cytochrome c oxidase subunit I are shown to be suitable for identifying evolutionary similarities between organisms. Furthermore, artificial neural networks are demonstrated to recognize these genetic images, enabling identification of species evolution. The results indicate the similarity of the genetic images of organisms belonging to species that emerged earlier during Earth’s evolutionary history to the genetic images of organisms belonging to species that emerged later. This finding indicates that genetic images are inherited and undergo gradual modification during evolutionary processes. The phenomenon of inheritance and modification of genetic images suggests that evolution tends to change the already existing functionalities of organisms, which allows for the ordering of organisms belonging to different species from ancient forms, through species that appeared successively during evolution, to those belonging to species that have developed more recently, up to Homo sapiens. Moreover, unlike analyses based on phylogenetic trees, the method presented in this article does not require computing hypothetical taxonomic units to study evolution. Combined with analyses of the inheritance of genetic images, it can support the interpretations of phylogenetic trees and evolutionary research. Full article

E-commerce web content is dynamic and diverse, necessitating continuous monitoring and adaptation. This presents researchers with the challenge of discovering methods to improve delivered services. Hence, integrating natural language processing (NLP), Machine Learning (ML), Deep Learning (DL), and sentiment analysis (SA) provides businesses with robust frameworks to utilize customer feedback and enhance decision-making. Therefore, we introduce a novel dataset collection methodology that captures the dynamic relationships between e-commerce web content and consumer sentiment. Additionally, we introduce a novel, real-consumer-based quality metric on product content through FG-CSrP, extending SA into a new Fine-Grained Consumer Sentiment related to the Product. We evaluated our dataset using baseline models: Deep Neural Network (DNN), Long Short-Term Memory (LSTM), DistilBERT, and twelve automatically optimized models created by AutoGluon-Tabular across three scenarios, each with varying feature inputs (numerical, textual, and both). We then applied Explainable Artificial Intelligence (XAI) to the DNN model to explain feature importance in prediction. Our findings showed that LightGBMXT outperformed the other models in two out of three scenarios, and XAI interpretations highlighted the significant role of vendor-provided web content details in consumer sentiment. Overall, our approach provides actionable insights that can help vendors improve e-commerce strategies and strengthen customer engagement. Full article

Over the past three decades, artificial intelligence (AI) has substantially reshaped marketing research and practice, yet the discipline has not established a systematic understanding of its evolutionary trajectory and intellectual structure. A bibliometric analysis of 1923 Scopus publications (1992–2025) was conducted using CiteSpace to explore collaboration patterns, conceptual development, and thematic organization. It identified six evolutionary stages with accelerating innovation cycles, starting with neural networks (1992–2000) and ending with generative AI (2024–2025), with research attention per stage compressing from approximately 9 years to just 2 years. The analysis of the collaboration network shows that the key contributors are India, China, the USA, and the UK. Co-citation analysis indicates that there are three thematic dimensions with seven clusters, namely: (i) AI technological foundations and capabilities, (ii) AI marketing applications and transformation, and (iii) responsible AI governance and ethics. It suggests a Three-Force Evolutionary Framework, which combines technology-push, market-pull, and governance-moderator forces to describe the dynamics of the field. This framework shows that the Regulatory Awakening of 2018 (e.g., GDPR and the Cambridge Analytica incident) guided, not limited, innovation, and highlighted the critical personalization–privacy paradox on which modern developments are based. It identifies three priority research directions: generative AI in creative marketing, consumer trust in the personalization–privacy paradox, and organizational adaptation to fast innovation cycles. This study provides scholars with a comprehensive knowledge map, practitioners with strategic imperatives for responsible AI adoption, and policymakers with evidence that well-designed regulation accelerates innovation by balancing commercial value with societal concerns. Full article

The activated sludge process, along with its modifications, is currently the most widely used wastewater treatment method to achieve desired environmental outcomes. However, it is also characterized by operational instability resulting from changing conditions, a wide range of quantitative and qualitative wastewater parameters, and technical and technological factors. Multi-parameter analysis of biological processes enables more comprehensive control through the use of chemometric techniques, modeling, artificial neural networks, and AI in the decision-making process. This article presents the results of a multivariate data analysis of parameters of activated sludge suspension held under anaerobic conditions. Several correlations were identified between parameters characterizing activated sludge and sludge liquid. PCA and HCA analyses enabled the extraction of three sets of parametric clusters. They reflect specific stages of sludge transformation under anaerobic conditions: initial high biological activity (cluster I), degradation and nutrient release (cluster II), and stabilization with minimal sludge activity (cluster III). These clusters indicate characteristic qualitative changes in sludge and sludge liquid, which can serve as effective control and optimization tools for biological wastewater treatment processes. Statistical and chemometric analyses demonstrate the potential to rapidly assess the condition of activated sludge or the stage of anaerobic transformation by correlating individual parameters. This is an example of how these tools can be used to control wastewater treatment processes more effectively, including in anaerobic conditions. Such control may improve treatment quality and the energy efficiency of the process. It will also help reduce the impact of treatment plants on the aquatic environment and enable the reuse of wastewater that is more effectively treated, which is undoubtedly an important element of sustainable development. Full article

The effects of different ultrasound parameters on some physicochemical properties and secoiridoid compositions of olive extracts were investigated. For this purpose, pH, acidity, photometric color index (PCI), total phenolic content, and secoiridoid phenolic compound composition analyses were carried out in olive extracts obtained by ultrasonic extraction at different operating parameters such as temperature, ultrasonic power, and extraction time. The data obtained were modeled and optimized by using the Box–Behnken design of RSM. Then, the comparison of experimental data versus mathematical estimations was performed by using both ANN and RSM. The results revealed that the pH values of the samples ranged between 4.94 and 5.23, and the average acidity value was 0.551 (% oleic acid). PCI values varied between 20.46 and 83.70. Total phenolic content ranged between 0.13 and 0.42 mg GAE (gallic acid equivalent)/g extract. Regarding secoiridoid phenolics, the ranges for oleuropein, oleacein, and oleocanthal were 5.33–34.39 ng/μL, 0.76–6.03 ng/μL, and 3.77–14.16 ng/μL, respectively. The optimized temperature, time, and ultrasonic power were 43.13 °C, 15 min, and 100% (of the maximum ultrasonic power of 90 W), respectively. The overall desirability of the process was obtained as 95.51%. RSM and ANN were both favorable in the estimation of experimental data with slight differences. Full article

With the development of geological data analysis and big data technology, intelligent mineral prospectivity mapping (MPM) has become a key direction in the integration of geoscience and artificial intelligence, showing promising applications in the identification and evaluation of strategic mineral resources such as gold. To address the limitations of conventional methods—including insufficient training samples, complex model structures, and weak capability in recognizing anomalous zones—this study proposes an improved convolutional neural network (CNN) approach for mineral prediction. A lightweight, modular CNN structure with repeatable stacking is designed to reduce computational cost while enhancing model robustness and generalization. In addition, a dynamic learning rate scheduling strategy is adopted to optimize the training process, significantly improving convergence speed and training stability. Furthermore, high-probability prediction samples and low-probability background samples are combined to form a new training dataset for regional prospectivity evaluation, yielding a high area under the curve (AUC) score. The method is applied and validated in the Xiong’ershan region, and the predicted high-potential zones account for 30% of the study area and contain 81.4% of the known gold deposits. These results demonstrate the method’s effectiveness in mineral information extraction and blind-area targeting, offering a new approach for mineral prospectivity mapping. Full article

The paper presents a study regarding the tool-life of uncoated and DLC-coated cutting inserts used for machining aluminum–lithium components used in the structure of the Airbus A350 aircraft. The experiment was conducted in an industrial environment that produced aircraft parts, using industrial equipment, under serial processing conditions during 5874 machining hours, resulting in 1440 samples. The experimental results were used as the input data for obtaining predictive models for the estimation of the tool-life machining supervised learning from MATLAB 2025b based on four machine-learning algorithms: trainlm and trainbr (artificial neural networks), fitrtree (decision trees), and fitrensemble (ensemble methods) respectively. The models were evaluated and compared in terms of their performance, which determined the best option. Also, a sensitive analysis of the five predictors was performed. The validation of the four learning algorithms was performed based on a separate set of experimental data, which was not used in learning. The analysis between the experimental results and those predicted by the learning models confirmed their robustness. The analysis between the experimental results and those predicted concluded the best model. Full article

Vehicle trajectories are time series, and entropy is a powerful tool for testing or quantifying the complexity of a given series. Entropy tools are often applied to variables such as velocity, acceleration, space headway, and time headway, but the local position data have not been addressed previously. The novelty of this study is that it uses the Improved Permutation Entropy (IPE) for the first time to analyze vehicle position data and convert those data into a limited range (0–0.3317), aiming to understand individual vehicle behavior during car-following and introduce a new prediction method for developing artificial intelligence-based car-following models. The study uses the IPE analysis results as a new input variable, in addition to existing input variables, to improve the prediction accuracy of these models. Three types of neural networks were adopted according to the development of artificial intelligence models: artificial neural networks (ANNs), long short-term memory networks (LSTMs), and Transformer models. The results indicate that all models using the proposed prediction method, which includes the IPE analysis result, outperformed those using the traditional prediction method. The Transformer & IPE model shows the best performance in prediction accuracy of the follower acceleration output; the statistically significant percentage improvements were 2.04%, 1.42%, 1.22%, and 2.62% for RMSE, MAE, MASE, and R², in that order. Furthermore, the results indicate that all models using the proposed prediction method outperformed the benchmarking Intelligent Driver Model (IDM) for the follower acceleration output. Full article