Search Results (884)

Ethnicity recognition has become increasingly important for a wide range of applications, highlighting the need for accurate and robust predictive models. Despite advances in machine learning, ethnicity classification remains a challenging research problem due to variations in facial features, class imbalance, and generalization issues. This study provides a concise synthesis of prior work to motivate the problem and then introduces a novel experimental framework for ethnicity recognition rather than a survey review. It proposes an improved approach that leverages transfer learning to enhance classification performance. The inclusion of various imaging sensors in the proposed methodology allows for an examination of how these imaging sensors impact the performance of facial recognition systems when a variety of images are captured under a number of real-world conditions, using professional and consumer-grade devices to create a range of conditions; from this dataset, the UTKFace dataset will be used to train and validate our method; an additional balanced dataset of Test Celebrities Faces was also created, representing five different ethnic groups (Black, Asian, White, Indian, and Other); the “Other” classification was specifically excluded for final evaluations to eliminate ambiguity and enhance stability. Rigorous preprocessing of both datasets was performed for optimal extraction of features from the sensors’ acquired images; the performance of several pre-trained CNN (Convolutional Neural Network) models (VGG16, DenseNet169, VGG19, ResNet50, MobileNetV2, InceptionV3 and EfficientNetB4) was used to identify an Ideal Hyperparameter Configuration for Optimal Performance. The resulting experimental results indicate that the VGG19 model achieved an 87% validation accuracy and a Maximum test accuracy of 75% on the Primary Dataset of Celebrity Faces; subsequently, the VGG19 model demonstrated a Range of Per-Class Accuracies, in addition to an overall accuracy of 87% across all five ethnic groups (51–90%+). This work demonstrates that leveraging transfer learning on imaging-sensor-captured images enables robust ethnicity classification with high accuracy and improved training efficiency relative to full model retraining. Furthermore, systematic hyperparameter optimization enhances model generalization and mitigates overfitting. Comparative experiments with recent state-of-the-art methods (2023–2025) further confirm that our optimized VGG19 model achieves competitive performance, reinforcing the effectiveness of the proposed reproducible and fairness-aware evaluation framework. Full article

In complex decision-making scenarios, such as smart city renewable energy project selection, decision-makers must contend with multi-dimensional uncertainty, conflicting expert opinions, and evolving temporal dynamics. This study introduces a novel Fractional q-Rung Orthopair Fuzzy Tensor (Fq-ROFT)-based group decision-making methodology that integrates the flexibility of q-rung orthopair fuzzy sets with tensorial representation and fractional-order dynamics. The proposed framework allows for the modeling of positive and negative membership degrees in a multi-dimensional, time-dependent structure while capturing memory effects inherent in expert evaluations. A detailed case study involving six renewable energy alternatives and six criteria demonstrates the method’s ability to aggregate expert opinions, compute fractional dynamic scores, and provide robust, reliable rankings. Comparative analysis with existing approaches, including classical q-ROFSs, intuitionistic fuzzy sets, and weighted sum methods, highlights the superior discriminative power, consistency, and dynamic sensitivity of the Fq-ROFT approach. Sensitivity analysis confirms the robustness of the top-ranked alternatives under variations in expert weights and fractional orders and membership perturbations. The study concludes by discussing the advantages, limitations, and future research directions of the proposed methodology, establishing Fq-ROFT as a powerful tool for dynamic, high-dimensional, and uncertain group decision-making applications. Full article

Estrogen (E2, 17β estradiol) is recognized for its regulatory role in numerous genes associated with energy metabolism and for its ability to disrupt mitochondrial function in various cancer types. However, the influence of E2 on the metabolism of colorectal cancer (CRC) cells remains largely unexplored. In this study, we examined how E2 affects mitochondrial function and energy production in CRC cells, utilizing two distinct CRC cell lines, HCT-116 and SW480. Cell viability, mitochondrial function, and the expression of several genes involved in oxidative phosphorylation (OXPHOS) were assessed in estrogen receptor α (ERα)-expressing and ERα-silenced cells treated with increasing concentrations of E2 for 48 h. Our results indicated that the cytotoxicity of E2 against CRC cells is mediated by the E2/ERα complex, which induces disturbances in mitochondrial function and the OXPHOS pathway. Furthermore, we identified two novel targets, RPS2 and TMEM177, which displayed overexpression, hypomethylation, and a negative association with ERα expression in CRC tissue. E2 treatment in CRC cells reduced the expression of both targets through promoter hypermethylation. Treatment with 5-Aza-2-deoxycytidine increased the expression of RPS2 and TMEM177. This epigenetic effect disrupts the mitochondrial membrane potential (MMP), resulting in decreased activity of the OXPHOS pathway and inhibition of CRC cell growth. Knockdown of RPS2 or TMEM177 in CRC cells resulted in anti-cancer effects and disruption of MMP and OXPHOS. These findings suggest that E2 exerts ERα-dependent epigenetic reprogramming that leads to significant mitochondria-related anti-growth effects in CRC. Full article

Accurate and quantitative pain assessment remains a major challenge in clinical medicine, especially for patients unable to verbalize discomfort. Conventional methods based on self-reports or clinician observation are subjective and inconsistent. This study introduces a novel automated facial pain assessment framework built on a dual-attention convolutional neural network (CNN) that achieves clinically calibrated, high-reliability performance and interpretability. The architecture combines multi-head spatial attention to localize pain-relevant facial regions with an enhanced channel attention block employing triple-pooling (average, max, and standard deviation) to capture discriminative intensity features. Regularization through label smoothing (α = 0.1) and AdamW optimization ensures calibrated, stable convergence. Evaluated on a clinically annotated dataset using subject-wise stratified sampling, the proposed model achieved a test accuracy of 90.19% ± 0.94%, with an average 5-fold cross-validation accuracy of 83.60% ± 1.55%. The model further attained an F1-score of 0.90 and Cohen’s κ = 0.876, with macro- and micro-AUCs of 0.991 and 0.992, respectively. The evaluation covers five pain classes (No Pain, Mid Pain, Moderate Pain, Severe Pain, and Very Pain) using subject-wise splits comprising 5840 total images and 1160 test samples. Comparative benchmarking and ablation experiments confirm each module’s contribution, while Grad-CAM visualizations highlight physiologically relevant facial regions. The results demonstrate a robust, explainable, and reproducible framework suitable for integration into real-world automated pain-monitoring systems. Inspired by biological pain perception mechanisms and human facial muscle responses, the proposed framework aligns with biomimetic sensing principles by emulating how localized facial cues contribute to pain interpretation. Full article

Early and reliable detection of bearing faults is essential for ensuring the safe and efficient operation of rotating electrical machines, especially under varying loads and non-stationary operating conditions. However, traditional diagnostic approaches struggle to maintain accuracy when signals are noisy, high-dimensional, or affected by multiple fault patterns. To address these issues, this work presents RNN-XBoostNet, a lightweight hybrid framework that combines the temporal-feature extraction capability of Recurrent Neural Networks (RNNs) with the robust classification strength of XGBoost. A new feature-selection strategy, CoLaR-FS (integrating correlation analysis, Lasso regularization, and recursive feature elimination), is introduced to reduce redundancy and retain only the most discriminative fault features. The proposed framework is evaluated using the widely known CWRU dataset and a newly developed induction-machine dataset containing ten fault categories, including six newly introduced real-world conditions. Experimental results show significant performance improvements: accuracy increased from 87.01% to 99.35% on the CWRU dataset and from 79.98% to 99.57% on the laboratory dataset. The combination of high accuracy, reduced complexity, and strong generalization demonstrates that RNN-XBoostNet, supported by CoLaR-FS, is a practical and effective solution for modern condition-based monitoring systems. Full article

Background/Objectives: Hypertension (HTN) remains a major global concern despite the availability of many antihypertensive medications, each with its own side effects. Lifestyle interventions, such as aerobic exercise and antioxidant-rich foods, represent promising non-pharmacological strategies for hypertension management. This study investigated the combined effects of exercise and vitamin C on anthropometric parameters, blood pressure, gut histology, biochemical markers, hematological profile, inflammatory gene expression, redox status, and stress hormones in L-nitroarginine methyl ester (L-NAME)-induced hypertensive rats. Methods: Male Wistar rats (n = 30) were randomly divided into five groups (n = 6/group): control, hypertensive (HTN), hypertensive + exercise (HTN + EX), hypertensive + vitamin C (HTN + VC), and hypertensive + exercise + vitamin C (HTN + EX + VC). Exercise consisted of treadmill training at a low intensity (50 ft/min) for 60 min daily, while vitamin C was administered orally (200 mg/kg/day) for four weeks. Blood pressure, anthropometric parameters, gut histology, inflammatory gene expression, hematological indices, serum biochemistry, oxidative stress markers, and hormonal assays were measured. Results: Both exercise and vitamin C individually reduced blood pressure (p < 0.05) and increased villi length (p < 0.05), upregulated anti-inflammatory cytokine expression in the gut, lowered oxidative stress (assessed through CRP, MDA, and catalase), and reduced stress hormones (cortisol and norepinephrine). The combined intervention (HTN + EX + VC) showed the most pronounced effects, resulting in a greater reduction in blood pressure and reversal of the changes induced by hypertension when compared to the HTN group. Conclusions: Exercise and vitamin C were beneficial in lowering blood pressure and improving the adverse changes associated with hypertension. Full article

The temperature fluctuations due to the mixing of two streams in a T-junction induce thermal stresses in the piping material, resulting in a pipe failure in Nuclear Power Plants. The numerical modeling of the thermal mixing in T-junctions is a challenging task in computational fluid dynamics (CFD) as it requires advanced turbulence modeling with scale-resolving capabilities for accurate prediction of the temperature fluctuations near the wall. One approach to address this challenge is using Partially Averaged Navier–Stokes modeling (PANS), which can capture the unresolved turbulent scales more accurately than traditional Reynolds-Averaged Navier–Stokes models. PANS modeling with k-ε closure gives encouraging results in the case of the Vattenfall T-junction benchmark case. In this study, PANS k-ω closure modeling is implemented for the WATLON T-junction Benchmark case. The momentum ratio (M_R) for two inlet streams is 8.14, which is a wall jet case. The time-averaged and root mean square velocity and temperature profiles are compared with the PANS k-ε and LES results and with experimental data. The velocity and temperature field results for PANS k-ω are close to the experimental data as compared to the PANS k-ε for a given filter control parameter f_k. Full article

Modern smart cities face increasing pressure to invest in sustainable and reliable energy systems while navigating uncertainties arising from fluctuating market conditions, evolving technology landscapes, and diverse expert opinions. Traditional multi-criteria decision-making (MCDM) approaches often fail to fully represent these uncertainties as they typically rely on crisp inputs, lack temporal memory, and do not explicitly account for stochastic variability. To address these limitations, this study introduces a novel Stochastic Fractional Fuzzy Tensor (SFFT)-based Group Decision-Making framework. The proposed approach integrates three dimensions of uncertainty within a unified mathematical structure: fuzzy representation of subjective expert assessments, fractional temporal operators (Caputo derivative, $\alpha =0.85$) to model the influence of historical evaluations, and stochastic diffusion terms ($\sigma =0.05$) to capture real-world volatility. A complete decision algorithm is developed and applied to a realistic smart city renewable energy selection problem involving six alternatives and six criteria evaluated by three experts. The SFFT-based evaluation identified Geothermal Energy as the optimal choice with a score of 0.798, followed by Offshore Wind (0.722) and Waste-to-Hydrogen (0.713). Comparative evaluation against benchmark MCDM methods—TOPSIS (Technique for Order Preference by Similarity to Ideal Solution), VIKOR (VIšekriterijumsko KOmpromisno Rangiranje), and WSM (Weighted Sum Model)—demonstrates that the SFFT approach yields more robust and stable rankings, particularly under uncertainty and model perturbations. Extensive sensitivity analysis confirms high resilience of the top-ranked alternative, with Geothermal retaining the first position in 82.4% of 5000 Monte Carlo simulations under simultaneous variations in weights, memory parameter ($\alpha \in [0.25,0.95]$), and noise intensity ($\sigma \in [0.01,0.10]$). This research provides a realistic, mathematically grounded, and decision-maker-friendly tool for strategic planning in uncertain, dynamic urban environments, with strong potential for deployment in wider engineering, management, and policy applications. Full article

Rice production experiences significant losses due to fungal diseases, particularly rice sheath blight caused by Rhizoctonia solani. Despite the intensive and continuous use of synthetic fungicides, diseases severity has not reduced and control has become increasingly challenging; therefore, the search for environmentally friendly and sustainable products has intensified. Here, we conducted a chemical characterization of Xylopia frutescens and using in silico analysis evaluated the interaction of their two major compounds with lectin protein site of R. solani. In vitro tests using increasing concentrations of essential oil against R. solani were performed. Subsequently, in four varieties of rice, five concentrations of X. frutescens essential oils were applied and evaluated the phytotoxicity effect as well the potential of Xylopia frutescens essential oil for controlling, both preventively and curatively, rice sheath blight. We further investigate the selectivity of this essential oil towards the non-target organism, Trichoderma asperellum. Our analysis revealed that trans-pinocarveol and myrtenal are the main compounds of X. frutescens essential oil and interact with the lectin of R. solani, supporting the antifungal properties of X. frutescens essential oil. In in vitro conditions, the highest tested concentrations of X. frutescens essential oil inhibited the pathogen’s sclerotia and mycelial growth. Under greenhouse conditions, the treatments caused low phytotoxicity and effectively reduced disease severity when applied, both preventively and curatively. Furthermore, the biocontrol agent T. asperellum exhibited tolerance to X. frutescens essential oil. Collectively, our findings demonstrate the potential of X. frutescens essential oil for the development of botanical fungicides capable of controlling R. solani without harming beneficial non-target organisms such as T. asperellum. Full article

In response to the growing complexity and uncertainty in real-world decision-making, this study introduces a novel framework based on the polytopic fuzzy tensor (PFT) model, which unifies the geometric structure of polytopes with the representational power of fuzzy tensors. The PFT framework is specifically designed to handle high-dimensional, imprecise, and ambiguous information commonly encountered in multi-criteria group decision-making scenarios. To support this framework, we define a suite of algebraic operations, aggregation mechanisms, and theoretical properties tailored to the PFT environment, with comprehensive mathematical formulations and illustrative validations. The effectiveness of the proposed method is demonstrated through a real-world application involving the evaluation of six pancreatic cancer treatment strategies. These alternatives are assessed against five key criteria: quality of life, side effects, treatment accessibility, cost, and duration. Our results reveal that the PFT-based approach outperforms traditional fuzzy decision-making techniques by delivering more consistent, interpretable, and reliable outcomes under uncertainty. Moreover, comparative analysis confirms the model’s superior ability to handle multidimensional expert evaluations and integrate conflicting information. This research contributes a significant advancement in the field of fuzzy decision science by offering a flexible, theoretically sound, and practically applicable tool for complex decision problems. Future work will focus on improving computational performance, adapting the model for real-time data, and exploring broader interdisciplinary applications. Full article

Background/Objectives: Acute respiratory distress syndrome (ARDS) represents a critical complication in polytrauma patients, characterized by diffuse lung inflammation and bilateral pulmonary infiltrates with mortality rates reaching 45% in intensive care units (ICU). The heterogeneous nature of ARDS and complex clinical presentation in severely injured patients poses substantial diagnostic challenges, necessitating early prediction tools to guide timely interventions. Machine learning (ML) algorithms have emerged as promising approaches for clinical decision support, demonstrating superior performance compared to traditional scoring systems in capturing complex patterns within high-dimensional medical data. Based on the identified research gaps in early ARDS prediction for polytrauma populations, our study aimed to: (i) develop a balanced random forest (BRF) ML model for early ARDS prediction in critically ill polytrauma patients, (ii) identify the most predictive clinical features using ANOVA-based feature selection, and (iii) evaluate model performance using comprehensive metrics addressing class imbalance challenges. Methods: This retrospective cohort study analyzed 407 polytrauma patients admitted to the ICU of the Center of Traumatology and Major Burns of Ben Arous, Tunisia, between 2017 and 2021. We implemented a comprehensive ML pipeline that incorporates Tomek Links undersampling, ANOVA F-test feature selection for the top 10 predictive variables, and SMOTE oversampling with a conservative sampling rate of 0.3. The BRF classifier was trained with class weighting and evaluated using stratified 5-fold cross-validation. Performance metrics included AUROC, PR-AUC, sensitivity, specificity, F1-score, and Matthews correlation coefficient. Results: Among 407 patients, 43 developed ARDS according to the Berlin definition, representing a 10.57% incidence. The BRF model demonstrated exceptional predictive performance with an AUROC of 0.98, a sensitivity of 0.91, a specificity of 0.80, an F1-score of 0.84, and an MCC of 0.70. Precision–recall AUC reached 0.86, demonstrating robust performance despite class imbalance. During stratified cross-validation, AUROC values ranged from 0.93 to 0.99 across folds, indicating consistent model stability. The top 10 selected features included procalcitonin, PaO₂ at ICU admission, 24-h pH, massive transfusion, total fluid resuscitation, presence of pneumothorax, alveolar hemorrhage, pulmonary contusion, hemothorax, and flail chest injury. Conclusions: Our BRF model provides a robust, clinically applicable tool for early prediction of ARDS in polytrauma patients using readily available clinical parameters. The comprehensive two-step resampling approach, combined with ANOVA-based feature selection, successfully addressed class imbalance while maintaining high predictive accuracy. These findings support integrating ML approaches into critical care decision-making to improve patient outcomes and resource allocation. External validation in diverse populations remains essential for confirming generalizability and clinical implementation. Full article

This study evaluates the spatial equity of community parks in Al-Khobar City, Saudi Arabia, by examining their proximity, availability, distribution, accessibility, and user satisfaction. Ensuring equitable access to public open spaces is vital for promoting urban liveability and achieving the sustainability objectives of Saudi Vision 2030. A mixed-methods approach integrating Geographic Information System (GIS)-based spatial analysis with a structured user survey was applied. GIS was used to map park locations, calculate per capita green space, and assess accessibility within a 500 m walking radius, while survey data from 300 respondents captured user satisfaction and perceptions of community park dimensions and indicators. The results reveal pronounced spatial disparities across neighbourhoods, with more than twenty areas lacking any park access and several others falling below the 5 m² per capita standard. In contrast, centrally located neighbourhoods demonstrate adequate provision and higher satisfaction levels. These findings indicate a fragmented and inequitable park distribution that limits community well-being and social inclusion. The study concludes that integrating GIS-based evidence with community feedback can inform data-driven planning policies and promote equitable, accessible, and sustainable community parks. The proposed framework offers a replicable model for assessing urban green space equity in other Saudi and Middle Eastern cities. Full article

Antibiotic discovery occurs at a snail’s pace, coercing researchers to find novel and promising alternatives to tackle antimicrobial resistance (AMR). Marine microbial exopolysaccharides (EPSs) have emerged as one, considering the recent recognition of these substances as a significant bioactive compound. This manuscript is intended to relate the identified molecular features of marine-driven EPS and applications in the field of biomedical sciences. The current review pointed out the ecological merits of such polymers in agriculture sector. Biochemical structure and the controlling mechanisms of EPS production in marine microbes are considered key features as well. Climate-induced factors impacting the production, composition, and functionality of EPSs are scrutinized. Last but not least, it draws biological insights from medical, industrial, and biotechnology sectors, thereby highlighting their linkage between antimicrobial innovation, industrial biotechnology, and environmental sustainability, while also describing the concerns that need to be resolved, like translation of laboratory results into marketable products. Full article

Time-fractional interface problems arise in systems where interacting materials exhibit memory effects or anomalous diffusion. These models provide a more realistic description of physical processes than classical formulations and appear in heat conduction, fluid flow, porous media diffusion, and electromagnetic wave propagation. However, the presence of complex interfaces and the nonlocal nature of fractional derivatives makes their numerical treatment challenging. This article presents a numerical scheme that combines radial basis functions (RBFs) with the finite difference method (FDM) to solve time-fractional partial differential equations involving interfaces. The proposed approach applies to both linear and nonlinear models with constant or variable coefficients. Spatial derivatives are approximated using RBFs, while the Caputo definition is employed for the time-fractional term. First-order time derivatives are discretized using the FDM. Linear systems are solved via Gaussian elimination, and for nonlinear problems, two linearization strategies, a quasi-Newton method and a splitting technique, are implemented to improve efficiency and accuracy. The method’s performance is assessed using maximum absolute and root mean square errors across various grid resolutions. Numerical experiments demonstrate that the scheme effectively resolves sharp gradients and discontinuities while maintaining stability. Overall, the results confirm the robustness, accuracy, and broad applicability of the proposed technique. Full article

Urban Flooding is one of the most prevalent natural hazards worldwide, leading to substantial human and economic losses. Therefore, the assessment and mapping of flood hazard levels are essential for reducing the impact of future flood disasters. This study develops and integrates a methodology to evaluate urban flood susceptibility in Nangarhar Province, Afghanistan, a semi-arid region with limited prior research. Landsat imagery from 2004 to 2024 was used to analyze land use land cover change (LULCC), indicating that built-up areas increased from 124 to 180 km² in 2004 to 2024, respectively, while agricultural land decreased from 1978 km² to 1883 km² during the same period. Climate data exhibit increases in temperatures and intensifying rainfall, exacerbating flood hazards. Geospatial analysis of elevation, slope, drainage density, and proximity to water bodies highlights the high susceptibility of low-lying areas. The Analytical Hierarchy Process (AHP) was employed to integrate diverse flood risk factors and produce accurate flood hazard maps. The findings show that very-high flood susceptibility zones expanded from 1537 to 1699 km² in 2004 to 2024, whereas low-susceptibility zones declined from 131 km² to 110 km². Socioeconomic indicators such as population density, built-up density, and education accessibility were also incorporated into the assessment. This study underscores the need for adaptive land use planning, resilient drainage systems, and community-based flood risk reduction strategies. The findings provide actionable insights for sustainable flood management and demonstrate the value of combining GIS, remote sensing, and multi-criteria analysis in data-scarce, conflict-affected regions. Full article