Search Results (4,886)

Breast cancer detection through non-invasive and accurate techniques remains a critical challenge in medical diagnostics. This study introduces a deep learning-based framework that leverages a microwave radar system equipped with an arc-shaped array of six antennas to estimate key tumor parameters, including position, size, and depth. This research begins with the evolutionary design of an ultra-wideband octagram ring patch antenna optimized for enhanced tumor detection sensitivity in directional near-field coupling scenarios. The antenna is fabricated and experimentally evaluated, with its performance validated through S-parameter measurements, far-field radiation characterization, and efficiency analysis to ensure effective signal propagation and interaction with breast tissue. Specific Absorption Rate (SAR) distributions within breast tissues are comprehensively assessed, and power adjustment strategies are implemented to comply with electromagnetic exposure safety limits. The dataset for the deep learning model comprises simulated self and mutual S-parameters capturing tumor-induced variations over a broad frequency spectrum. A core innovation of this work is the development of the Attention-Based Feature Separation (ABFS) model, which dynamically identifies optimal frequency sub-bands and disentangles discriminative features tailored to each tumor parameter. A multi-branch neural network processes these features to achieve precise tumor localization and size estimation. Compared to conventional attention mechanisms, the proposed ABFS architecture demonstrates superior prediction accuracy and interpretability. The proposed approach achieves high estimation accuracy and computational efficiency in simulation studies, underscoring the promise of integrating deep learning with conformal microwave imaging for safe, effective, and non-invasive breast cancer detection. Full article

This study applies Gradient Boosting Machines (GBMs) and principal component regression (PCR) to forecast the closing price of the Johannesburg Stock Exchange (JSE) All-Share Index (ALSI), using daily data from 2009 to 2024, sourced from the Wall Street Journal. The models are evaluated under three training–testing split ratios to assess short-term forecasting performance. Forecast accuracy is assessed using standard error metrics: mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute scaled error (MASE). Across all test splits, the GBM consistently achieves lower forecast errors than PCR, demonstrating superior predictive accuracy. To validate the significance of this performance difference, the Diebold–Mariano (DM) test is applied, confirming that the forecast errors from the GBM are statistically significantly lower than those of PCR at conventional significance levels. These findings highlight the GBM’s strength in capturing nonlinear relationships and complex interactions in financial time series, particularly when using features such as the USD/ZAR exchange rate, oil, platinum, and gold prices, the S&P 500 index, and calendar-based variables like month and day. Future research should consider integrating additional macroeconomic indicators and exploring alternative or hybrid forecasting models to improve robustness and generalisability across different market conditions. Full article

This research focuses on medium-term load forecasting in a tropical region post-pandemic. This study presents one of the first attempts to analyze medium-term forecasting using half-hourly resolution in the Java-Bali power system post-COVID-19 period. The dataset comprises load measurements recorded every 30 min (48 data points per day) from 2014 to 2022. Three distinct methods, namely polynomial regression, split polynomial regression, and Long Short-Term Memory (LSTM) networks, were employed and compared to predict the electricity load demand. The analysis found that LSTM outperformed the other methods, exhibiting the lowest error rates with Mean Absolute Percentage Error (MAPE) at 3.86% and Root Mean Squared Error (RMSE) at 1247.93. Additionally, a consistent observation emerged, showing that all methods performed better in predicting load demand during nighttime hours (6 p.m. to 6 a.m.). The hypothesis is that data stability during nighttime, with fewer significant fluctuations, contributed to the improved prediction accuracy. These findings provide valuable insights for improving load forecasting in the post-pandemic tropical region and offer opportunities for enhancing power grid efficiency and reliability. Full article

Football performance results from the dynamic interaction between physical, tactical, technical, and psychological dimensions—each of which also influences player well-being, recovery, and readiness. However, integrated monitoring approaches remain scarce, particularly in youth and sub-elite contexts. This systematic review screened 341 records from PubMed, Scopus, and Web of Science, with 46 studies meeting the inclusion criteria (n = 1763 players; age range: 13.2–28.7 years). Physical external load was reported in 44 studies using GPS-derived metrics such as total distance and high-speed running, while internal load was examined in 36 studies through session-RPE (rate of perceived exertion × duration), heart rate zones, training impulse (TRIMP), and Player Load (PL). A total of 22 studies included well-being indicators capturing fatigue, sleep quality, stress levels, and muscle soreness, through tools such as the Hooper Index (HI), the Total Quality Recovery (TQR) scale, and various Likert-type or composite wellness scores. Tactical behaviours (n = 15) were derived from positional tracking systems, while technical performance (n = 7) was assessed using metrics like pass accuracy and expected goals, typically obtained from Wyscout^® or TRACAB^® (a multi-camera optical tracking system). Only five studies employed multivariate models to examine interactions between performance domains or to predict well-being outcomes. Most remained observational, relying on descriptive analyses and examining each domain in isolation. These findings reveal a fragmented approach to player monitoring and a lack of conceptual integration between physical, psychological, tactical, and technical indicators. Future research should prioritise multidimensional, standardised monitoring frameworks that combine contextual, psychophysiological, and performance data to improve applied decision-making and support player health, particularly in sub-elite and youth populations. Full article

Ethanol upgrading via catalytic C–C coupling, commonly known as the Guerbet reaction, offers a sustainable route to produce 1-butanol, a high-performance biofuel. To address gaps in the mechanistic understanding of the catalytic reaction, we investigated the process involving a fixed-bed reactor, operated at 275–325 °C, 21 bar, and weight hourly space velocities of 0.25–2.5 g_EtOH/(g_cat·h), using helium as a carrier gas, with a 5:1 He/EtOH molar ratio. The catalyst was a MgO–Al₂O₃ mixed oxide (Mg/Al = 2:1), derived from a hydrotalcite precursor. A detailed kinetic model was developed, encompassing 15 species and 27 reversible steps (10 sorption and 17 reaction steps), within a 1+1D sorption–reaction–transport framework. Four C₄-forming pathways were included: aldol condensation to form crotonaldehyde, semi-direct coupling to form butyraldehyde and crotyl alcohol, and direct coupling to form 1-butanol. To avoid overfitting, Arrhenius parameters were grouped by reaction type, resulting in sixty rate parameters and one active site-specific density parameter. The optimized model achieved high accuracy, with an average prediction error of 1.44 times the experimental standard deviation. The mechanistic analysis revealed aldol condensation as the dominant pathway below 335 °C, with semi-direct coupling to crotyl alcohol prevailing above 340 °C. The resulting model provides a robust framework for understanding and predicting complex reaction networks in ethanol upgrading systems. Full article

Artificial intelligence (AI) has already played a significant role in the healthcare sector, particularly in image-based medical diagnosis. Deep learning models have produced satisfactory and useful results for accurate decision-making. Among the various types of medical images, magnetic resonance imaging (MRI) is frequently utilized in deep learning applications to analyze detailed structures and organs in the body, using advanced intelligent software. However, challenges related to performance and data privacy often arise when using medical data from patients and healthcare institutions. To address these issues, new approaches have emerged, such as federated learning. This technique ensures the secure exchange of sensitive patient and institutional data. It enables machine learning or deep learning algorithms to establish a client–server relationship, whereby specific parameters are securely shared between models while maintaining the integrity of the learning tasks being executed. Federated learning has been successfully applied in medical settings, including diagnostic applications involving medical images such as MRI data. This research introduces an analytical intelligence system based on an Internet of Medical Things (IoMT) framework that employs federated learning to provide a safe and effective diagnostic solution for brain tumor identification. By utilizing specific brain MRI datasets, the model enables multiple local capsule networks (CapsNet) to achieve improved classification results. The average accuracy rate of the CapsNet model exceeds 97%. The precision rate indicates that the CapsNet model performs well in accurately predicting true classes. Additionally, the recall findings suggest that this model is effective in detecting the target classes of meningiomas, pituitary tumors, and gliomas. The integration of these components into an analytical intelligence system that supports the work of healthcare personnel is the main contribution of this work. Evaluations have shown that this approach is effective for diagnosing brain tumors while ensuring data privacy and security. Moreover, it represents a valuable tool for enhancing the efficiency of the medical diagnostic process. Full article

This paper presents the flow field reconstruction and prediction of powder fuel transport systems based on representative feature extraction from scattering images using deep learning techniques. A laboratory-built powder fuel supply system was used to conduct scattering spectroscopy experiments on boron-based fuel under various flow rate conditions. Based on the acquired scattering images, a prediction and reconstruction method was developed using a deep network framework composed of a Stacked Autoencoder (SAE), a Backpropagation Neural Network (BP), and a Long Short-Term Memory (LSTM) model. The proposed framework enables accurate classification and prediction of the dynamic evolution of flow structures based on learned representations from scattering images. Experimental results show that the feature vectors extracted by the SAE form clearly separable clusters in the latent space, leading to high classification accuracy under varying flow conditions. In the prediction task, the feature vectors predicted by the LSTM exhibit strong agreement with ground truth, with average mean square error, mean absolute error, and r-square values of 0.0027, 0.0398, and 0.9897, respectively. Furthermore, the reconstructed images offer a visual representation of the changing flow field, validating the model’s effectiveness in structure-level recovery. These results suggest that the proposed method provides reliable support for future real-time prediction of powder fuel mass flow rates based on optical sensing and imaging techniques. Full article

The integration of computational intelligence techniques into pharmaceutical wastewater treatment offers promising opportunities to improve process efficiency and minimize operational costs. This study compares the predictive capabilities of Response Surface Methodology (RSM) and Artificial Neural Network (ANN) models in forecasting the rejection efficiencies of caffeine and paracetamol using AFC 40 and AFC 80 nanofiltration (NF) membranes. Experiments were conducted under varying operating conditions, including transmembrane pressure, feed concentration, and flow rate. The predictive performance of both models was evaluated using statistical metrics such as the Coefficient of Determination (R²), Root Mean Square Error (RMSE), Marquardt’s Percentage Squared Error Deviation (MPSED), Hybrid fractional error function (HYBRID), and Average Absolute Deviation (AAD). Both models demonstrated strong predictive accuracy, with R² values of 0.9867 and 0.9832 for RSM and ANN, respectively, in AFC 40 membranes, and 0.9769 and 0.9922 in AFC 80 membranes. While both approaches closely matched the experimental results, the ANN model consistently yielded lower error values and higher R² values, indicating superior predictive performance. These findings support the application of ANNs as a robust modelling tool in optimizing NF membrane processes for pharmaceutical removal. Full article

This study explores virtual sensing techniques for the Eolink floating offshore wind turbine (FOWT), which features a pyramidal platform and a single-point mooring system that enables weathervaning to maximize power production and reduce structural loads. To address the challenges and costs associated with monitoring submerged components, virtual sensors are investigated as an alternative to physical instrumentation. The main objective is to design a virtual sensor of mooring hawser loads using a reduced set of input features from GPS, anemometer, and inertial measurement unit (IMU) data. A virtual sensor is also proposed to estimate the bending moment at the joint of the pyramid masts. The FOWT is modeled in OrcaFlex, and a range of load cases is simulated for training and testing. Under defined sensor sampling conditions, both supervised and physics-informed machine learning algorithms are evaluated. The models are tested under aligned and misaligned environmental conditions, as well as across operating regimes below- and above-rated conditions. Results show that mooring tensions can be estimated with high accuracy, while bending moment predictions also perform well, though with lower precision. These findings support the use of virtual sensing to reduce instrumentation requirements in critical areas of the floating wind platform. Full article

Respiratory diseases represent a persistent global health challenge, underscoring the need for intelligent, accurate, and personalized diagnostic and therapeutic systems. Existing methods frequently suffer from limitations in diagnostic precision, lack of individualized treatment, and constrained adaptability to complex clinical scenarios. To address these challenges, our study introduces a modular AI-powered framework that integrates an audio-based disease classification model with simulated molecular biomarker profiles to evaluate the feasibility of future multimodal diagnostic extensions, alongside a synthetic-data-driven prescription recommendation engine. The disease classification model analyzes respiratory sound recordings and accurately distinguishes among eight clinical classes: bronchiectasis, pneumonia, upper respiratory tract infection (URTI), lower respiratory tract infection (LRTI), asthma, chronic obstructive pulmonary disease (COPD), bronchiolitis, and healthy respiratory state. The proposed model achieved a classification accuracy of 99.99% on a holdout test set, including 94.2% accuracy on pediatric samples. In parallel, the prescription module provides individualized treatment recommendations comprising drug, dosage, and frequency trained on a carefully constructed synthetic dataset designed to emulate real-world prescribing logic.The model achieved over 99% accuracy in medication prediction tasks, outperforming baseline models such as those discussed in research. Minimal misclassification in the confusion matrix and strong clinician agreement on 200 prescriptions (Cohen’s $\kappa$ = 0.91 [0.87–0.94] for drug selection, 0.78 [0.74–0.81] for dosage, 0.96 [0.93–0.98] for frequency) further affirm the system’s reliability. Adjusted clinician disagreement rates were 2.7% (drug), 6.4% (dosage), and 1.5% (frequency). SHAP analysis identified age and smoking as key predictors, enhancing model explainability. Dosage accuracy was 91.3%, and most disagreements occurred in renal-impaired and pediatric cases. However, our study is presented strictly as a proof-of-concept. The use of synthetic data and the absence of access to real patient records constitute key limitations. A trialed clinical deployment was conducted under a controlled environment with a positive rate of satisfaction from experts and users, but the proposed system must undergo extensive validation with de-identified electronic medical records (EMRs) and regulatory scrutiny before it can be considered for practical application. Nonetheless, the findings offer a promising foundation for the future development of clinically viable AI-assisted respiratory care tools. Full article

Accurate and rapid prediction of structural responses to seismic loading is critical for ensuring structural safety. Recently, there has been active research focusing on the application of deep learning techniques, including Physics-Informed Neural Networks (PINNs) and Long Short-Term Memory (LSTM) networks, to predict the dynamic behavior of structures. While these methods have shown promise, each comes with distinct limitations. PINNs offer physical consistency but struggle with capturing long-term temporal dependencies in nonlinear systems, while LSTMs excel in learning sequential data but lack physical interpretability. To address these complementary limitations, this study proposes a hybrid LSTM-PINN model, combining the temporal learning ability of LSTMs with the physics-based constraints of PINNs. This hybrid approach allows the model to capture both nonlinear, time-dependent behaviors and maintain physical consistency. The proposed model is evaluated on both single-degree-of-freedom (SDOF) and multi-degree-of-freedom (MDOF) structural systems subjected to the El-Centro ground motion. For validation, the 1940 El-Centro NS earthquake record was used, and the ground acceleration data were normalized and discretized for numerical simulation. The proposed LSTM-PINN is trained under the same conditions as the conventional PINN models (e.g., same optimizer, learning rate, and loss structure), but with fewer training epochs, to evaluate learning efficiency. Prediction accuracy is quantitatively assessed using mean error and mean squared error (MSE) for displacement, velocity, and acceleration, and results are compared with PINN-only models (PINN-1, PINN-2). The results show that LSTM-PINN consistently achieves the most stable and precise predictions across the entire time domain. Notably, it outperforms the baseline PINNs even with fewer training epochs. Specifically, it achieved up to 50% lower MSE with only 10,000 epochs, compared to the PINN’s 50,000 epochs, demonstrating improved generalization through temporal sequence learning. This study empirically validates the potential of physics-guided time-series AI models for dynamic structural response prediction. The proposed approach is expected to contribute to future applications such as real-time response estimation, structural health monitoring, and seismic performance evaluation. Full article

This study presents an AI-enhanced pedestrian simulation model for subway stations, combining the Social Force Model (SFM) with LiDAR trajectory data from Samseong Station in Seoul. To reflect time-dependent behavioral differences, RMSProp-based optimization is performed separately for the morning peak, leisure hours, and evening peak, yielding time-specific parameter sets. Compared to baseline models with static parameters, the proposed method reduces prediction errors (MSE) by 50.1% to 84.7%. The model integrates adaptive learning rates, mini-batch training, and L2 regularization, enabling robust convergence and generalization across varied pedestrian densities. Its accuracy and modular design support real-world applications such as pre-construction design testing, post-opening monitoring, and capacity planning. The framework also contributes to Sustainable Urban Mobility Plans (SUMPs) by enabling predictive, data-driven evaluation of pedestrian flow dynamics in complex station environments. Full article

High rates of childhood vaccination defaulting remain a significant barrier to achieving full vaccination coverage in sub-Saharan Africa, contributing to preventable morbidity and mortality. This study evaluated the utility of machine learning algorithms for predicting childhood vaccination defaulters in Ghana, addressing the limitations of traditional statistical methods when handling complex, high-dimensional health data. Using a merged dataset from two malaria vaccine pilot surveys, we engineered novel temporal features, including vaccination timing windows and birth seasonality. Six algorithms, namely logistic regression, support vector machine, random forest, gradient boosting machine, extreme gradient boosting, and artificial neural networks, were compared. Models were trained and validated on both original and synthetically balanced and augmented data. The results showed higher performance across the ensemble tree classifiers. The random forest and extreme gradient boosting models reported the highest F1 scores (0.92) and AUCs (0.95) on augmented unseen data. The key predictors identified include timely receipt of birth and week six vaccines, the child’s age, household wealth index, and maternal education. The findings demonstrate that robust machine learning frameworks, combined with temporal and contextual feature engineering, can improve defaulter risk prediction accuracy. Integrating such models into routine immunization programs could enable data-driven targeting of high-risk groups, supporting policymakers in strategies to close vaccination coverage gaps. Full article

Earthquakes are sudden and highly destructive events that severely disrupt infrastructure and logistics systems, making accurate and timely emergency material demand forecasting a critical challenge in disaster response. However, the scarcity of reliable data during the early stages of an earthquake limits the effectiveness of traditional forecasting methods. To address this issue, this study proposes a hybrid forecasting framework that integrates the Grey Model (GM(1,1)) with Bayesian Dynamic Linear Models (BDLMs), aiming to improve both the accuracy and adaptability of demand predictions. The approach operates in two phases: first, GM(1,1) generates preliminary forecasts using limited initial observations; second, BDLMs dynamically update these forecasts in real time as new data become available. The model is validated through a case study of the 2010 M7.1 Yushu earthquake in Qinghai Province, China. The results indicate that the hybrid method produces reliable forecasts even at the earliest stages of the disaster, with increasing accuracy as more observational data are incorporated. Our case study demonstrates that the integrated GM(1,1)-BDLM framework substantially reduces prediction errors compared to standalone GM(1,1). Using the first five days’ data to forecast fatalities and emergency material demand for days 6–10, the hybrid model achieves a 4.01% error rate—a 19.62 percentage point improvement over GM(1,1)’s 23.63% error rate. This adaptive forecasting mechanism offers robust support for evidence-based decision-making in emergency material allocation, enhancing the efficiency and responsiveness of post-disaster relief operations. Full article

The acquisition of plant phenotypic traits is essential for selecting superior varieties, improving crop yield, and supporting precision agriculture and agricultural decision-making. Therefore, it plays a significant role in modern agriculture and plant science research. Traditional manual measurements of phenotypic traits are labor-intensive and inefficient. In contrast, combining 3D reconstruction technologies with autonomous vehicles enables more intuitive and efficient trait acquisition. This study proposes a 3D semantic reconstruction system based on an improved ORB-SLAM3 framework, which is mounted on an unmanned vehicle to acquire phenotypic traits in tomato cultivation scenarios. The vehicle is also equipped with the A * algorithm for autonomous navigation. To enhance the semantic representation of the point cloud map, we integrate the BiSeNetV2 network into the ORB-SLAM3 system as a semantic segmentation module. Furthermore, a two-stage filtering strategy is employed to remove outliers and improve the map accuracy, and OctoMap is adopted to store the point cloud data, significantly reducing the memory consumption. A spherical fitting method is applied to estimate the number of tomato fruits. The experimental results demonstrate that BiSeNetV2 achieves a mean intersection over union (mIoU) of 95.37% and a frame rate of 61.98 FPS on the tomato dataset, enabling real-time segmentation. The use of OctoMap reduces the memory consumption by an average of 96.70%. The relative errors when predicting the plant height, canopy width, and volume are 3.86%, 14.34%, and 27.14%, respectively, while the errors concerning the fruit count and fruit volume are 14.36% and 14.25%. Localization experiments on a field dataset show that the proposed system achieves a mean absolute trajectory error (mATE) of 0.16 m and a root mean square error (RMSE) of 0.21 m, indicating high localization accuracy. Therefore, the proposed system can accurately acquire the phenotypic traits of tomato plants, providing data support for precision agriculture and agricultural decision-making. Full article