Search Results (12,386)

With the rapid penetration of renewable energy, grid-connected microgrids have become a cornerstone of low-carbon power systems, while also posing major challenges for coordinated scheduling under coupled economic and environmental goals. The resulting dispatch problem is highly nonlinear and high-dimensional, featuring tight operational constraints and conflicting cost–emission trade-offs that often undermine the efficiency and reliability of conventional optimization methods, thereby limiting overall economic productivity. This paper presents an adaptive economic–environmental dispatch framework for grid-connected microgrids formulated as a multi-objective optimization problem that simultaneously minimizes operating cost and environmental protection cost. To navigate the rugged and constrained search landscape, we develop an enhanced metaheuristic termed the Lévy–Triangular Walk Dung Beetle Optimizer (LTWDBO). The LTWDBO integrates (i) chaotic population initialization to improve diversity and feasibility coverage, (ii) a geometry-inspired triangular walk operator to strengthen local exploitation, and (iii) an adaptive Lévy-flight strategy to boost global exploration, achieving a robust exploration–exploitation balance over the entire optimization process, representing a process innovation in metaheuristic-driven dispatch optimization. The proposed method is validated on a representative grid-connected microgrid comprising photovoltaic generation, wind turbines, micro gas turbines, and battery energy storage. Comparative experiments against representative baselines (DBO, WOA, TDBO, and NSGA-II) demonstrate that the LTWDBO achieves consistently better solution quality. Our LTWDBO attains the lowest optimal objective value of 255,718.34 Yuan, compared with 357,702.68 Yuan (DBO), 347,369.28 Yuan (TDBO), and 3,854,359.36 Yuan (WOA). The LTWDBO also yields the best average objective value of 673,842.24 Yuan, an improvement of over 1,001,813.10 Yuan (DBO). Full article

Background/Objectives: Periodontitis represents a significant global health burden, yet preventive health literacy remains critically low among emerging adults—a developmental stage where lifelong health behaviors crystallize. This study evaluated the effectiveness of the GUM (an acronym of Gum Understanding Mission) game, an interactive gamified digital tool incorporating AI-informed or manual feedback, for improving periodontitis literacy among tenth-semester Software Engineering students at the University of Guayaquil. Methods: In a controlled pre-test/post-test experiment, 50 participants were randomly assigned to either the GUM game intervention or a traditional lecture. Both groups completed identical knowledge assessments immediately before and after their respective 50-min instructional sessions. The GUM game featured adaptive questioning, immediate elaborated feedback, and comprehensive performance analytics, while the control group received instructor-led didactic instruction with a subsequent question-and-answer session. Results: The GUM group improved from a baseline of 21% to 94% correct responses, while the lecture group increased from 22% to 67% ($p<0.001$). Error reduction was 74% in the GUM group versus 45% in the control group. However, the study’s scope is currently limited to a single, digitally literate cohort, and knowledge retention over time was not assessed. Conclusions: These findings suggest that a self-directed, feedback-driven serious game can substantially outperform traditional methods in fostering periodontitis literacy within this population. Further research is needed across diverse populations with extended follow-up periods to assess knowledge retention and generalizability. Full article

The CALIPSO V4.10 5 km cloud-layer product contains a small yet influential fraction of low-confidence and “unknown” cloud-type labels, which constrains its effectiveness in climatological analyses and limits its utility for downstream Earth system applications. To improve the practical usability and completeness of these observations, this study develops a multilayer perceptron (MLP)-based refinement framework using global summer daytime CALIPSO data from 2006–2021. High-confidence cloud samples (76% of the dataset), defined as cases with high Feature Type QA and high Ice/Water Phase QA, were used as the reliable supervision subset to train the MLP model using 11 geolocation-, optical-, and microphysics-related variables, including cloud optical depth, cloud thickness, depolarization ratio, and color ratio. The trained model was subsequently applied to a separately defined low-confidence cloud subset (~5% of the dataset), consisting of cases with high Feature Type QA but low Ice/Water Phase QA, of which over 60% were originally labeled as “unknown”, to generate probabilistic assignments of three cloud types: ice clouds, water clouds, and oriented ice crystals. Evaluation using withheld high-confidence samples indicates a strong level of agreement with operational CALIPSO classifications (~94.99%). Moreover, the refined low-confidence results exhibit physically coherent vertical structural characteristics consistent with established cloud thermodynamic regimes. It is emphasized that the proposed framework does not establish an independent physical truth beyond CALIOP’s measurement capability; instead, it provides a physically consistent and statistically robust approach to improving the completeness and practical usability of CALIPSO cloud-type products for large-scale scientific and modeling applications. Full article

Soiling in photovoltaic systems is a recurring problem that reduces energy generation and demands efficient operation and maintenance (O&M) strategies. In this context, this paper proposes a machine learning-based approach to identify dirt levels and generate cleaning alerts using operational and weather data. Initially, the models were evaluated with a decision threshold ranging from 0.5 to 0.7, using only operational features. Subsequently, the inclusion of weather features was tested, which improved the models’ performance and enabled the selection of the best models for the exhaustive features search step. The models analyzed in this step were Extra Trees, Histogram-based Gradient Boosting, Extreme Gradient Boosting, and Random Forest. Exhaustive analysis further improved model performance, as indicated by global metrics and ROC curves. The Extra Trees model with a threshold of 0.5 showed the best performance and was selected as the final configuration, achieving an accuracy of 0.9884 and an AUC-ROC of 0.9957. Finally, the selected model was applied to determine daily soiling levels and trigger alerts based on temporal persistence, indicating its potential to support predictive O&M decisions and cleaning actions in PV systems. Full article

Cognitive impairment is a prevalent non-motor manifestation of Parkinson’s disease (PD), yet early detection remains limited by the sensitivity of conventional cognitive assessments. Emerging evidence suggests that motor dysfunction, particularly gait and balance abnormalities, reflects underlying cognitive vulnerability. This study examined motor–cognitive associations and evaluated whether motor-derived features can be used to classify low-MoCA status in PD without direct cognitive testing. Data from 102 individuals with PD were analyzed, incorporating clinical assessments, physical function measures, lifestyle factors, and gait-derived biomarkers. Multiple regression identified Unified Parkinson’s Disease Rating Scale Part III, stride length of the more affected side during 360° turning at preferred speed, and maximum ankle jerk on the less affected side during forward walking as independent predictors of Montreal Cognitive Assessment scores, collectively explaining 34.7% of the variance. Network analysis revealed integrative relationships among global motor severity, gait smoothness, and cognitive performance. Using a compact motor-based feature set, logistic regression achieved a mean accuracy of 65.8% and an AUC of 0.737 in classifying low-MoCA status under cross-validation. These findings demonstrate that motor-derived digital biomarkers capture clinically meaningful information about cognitive status in PD and may serve as adjunctive tools for identifying cognitive vulnerability in clinical settings. Full article

Grasslands globally are threatened by loss and degradation as shifting factors in climate and management put them at risk. These grassland ecosystems support local economies and are a center of biodiversity, which makes understanding the risks that affect them key to effectively protecting them. One major risk to grasslands is woody plant encroachment, and reliable management hinges on understanding its patterns. A major challenge of woody plant encroachment is detecting it at early stages (<20% cover). This study investigated the utility of a combination of environmental features and remotely sensed data for differentiating varying levels of woody plant encroachment in a montane Canadian grassland. The response of woody species to environmental factors including slope and available moisture varied by individual species. As in past studies, it was challenging to separate the early stages of encroachment using base spectral bands or NDVI, even with the use of higher-resolution satellite imagery. Bands in the yellow and red wavelength regions both showed promise for shrub detection, providing more between band separability and key modeling components. The spatial resolution and band combinations used here were able to model woody plant cover levels, helping to facilitate the implementation of effective management in combating woody plant encroachment. Full article

Atmospheric corrosion of carbon and low-alloy steels causes direct economic losses that are estimated at around 3.4% of the global GDP, and its accurate multi-year prediction is essential for protective coating selection, service-life estimation, and infrastructure maintenance scheduling. In this study, machine learning (ML) algorithms, including gradient boosting regressor (GBR), eXtreme gradient boosting (XGBoost), random forest (RF), support vector regression (SVR), and ridge regression, were trained on a 600-sample physics-grounded dataset to predict the cumulative atmospheric corrosion loss (µm) of low-alloy steels over 1–10 years of exposure. The dataset was constructed using the exact ISO 9223:2012 dose–response function (DRF) for a first-year corrosion rate and the ISO 9224:2012 power-law multi-year kinetic model (C(t) = C₁·t0.5), spanning ISO 9223 corrosivity categories C2–CX across 11 environmental and material input features. All models were evaluated on the original (untransformed) corrosion scale under an 80/20 train/test split and five-fold cross-validation. Gradient boosting achieved the best overall performance with test set R² = 0.968, CV-R² = 0.969, RMSE = 10.58 µm, MAE = 5.99 µm, and MAPE = 12.6%. XGBoost was a close second (R² = 0.958, CV-R² = 0.960). RF achieved an R² of 0.944. SHAP (SHapley Additive exPlanations) analysis identified SO₂ deposition rate, exposure time, relative humidity, Cl⁻ deposition rate, and temperature as the five most influential predictors. The dominance of the SO₂ deposition rate (mean |SHAP| = 26.37 µm) and the high second-place ranking of exposure time (13.67 µm) are fully consistent with the ISO 9223:2012 dose–response function and ISO 9224:2012 power-law kinetics, respectively, while among the material features, Cu and Cr contents showed the strongest negative SHAP contributions, confirming their corrosion-inhibiting roles in weathering steels. These results establish a physics-consistent, interpretable ML benchmark exceeding R² = 0.90 for multi-year cumulative corrosion loss prediction and provide a quantitative tool for alloy screening, coating selection in aggressive atmospheric environments, and service-life planning. Full article

Background/Objectives: Cancer remains one of the leading global health burdens, mainly because of the lack of specificity and off-target toxicity associated with conventional therapeutic approaches. To move toward more efficient anticancer drug discovery, we have developed an advanced machine-learning-based architecture that allows for predictive modeling of anticancer small molecules. Methods: A total of 3600 compounds with experimentally validated IC₅₀ values were systematically processed to derive a comprehensive suite of molecular representations comprising 2D physicochemical descriptors, structural fingerprints, and hybrid descriptor sets generated via the Mordred and PaDEL frameworks. A total of six machine learning algorithms—Random Forest (RF), Extreme Gradient Boosting (XGB), Gradient Boosting (GB), Extra-Trees classifier (ET), Adaptive Boosting (AdaBoost), and Light Gradient Boosting Machine (LightGBM)—were trained and benchmarked via a rigorous model evaluation protocol incorporating 10-fold cross-validation along with multiple performance metrics. Ensemble voting strategies were also examined to assess potential performance. Result: Of all configurations, the XGB-Hybrid architecture emerged as the most robust and generalizable classifier with an AUC of 0.88 and accuracy of 79.11% on the independent test set. To ensure interpretability and mechanistic insight, SHAP-based feature analysis was conducted, by which feature contributions could be quantified and the molecular determinants most influential for anticancer activity discrimination were revealed. Altogether, the current study establishes an XGB-Hybrid framework as technically rigorous, interpretable, and high-performance predictive modeling with the ability to accelerate early-stage anticancer small molecule identification. Conclusions: The study has brought into focus the transformational effect of machine learning in modern computational oncology and rational drug design pipelines. Full article

Water surface object detection in shipborne remote sensing is challenged by unstable wave-induced backgrounds, illumination variations, extreme scale changes with tiny objects, and limited annotations. Multimodal RGB–infrared (RGB–IR) sensing leverages complementary visible and infrared cues to enhance robustness. However, most existing RGB–IR methods rely on backbones pretrained on limited-scale data, which constrain their performance for complex water surface scenes. In this work, we propose the WS-R-IR Adapter, a parameter-efficient vision foundation model (VFM)-based framework for shipborne RGB–IR object detection. Instead of full fine-tuning, it adapts frozen VFM representations via lightweight task-specific designs. the WS-R-IR Adapter includes (1) a water scene domain-aware modal adapter that progressively guides frozen backbone features with evolving semantic cues, (2) a parallel multi-scale structural perception module for fine-grained, scale-sensitive modeling, (3) an adaptive RGB–IR feature modulation fusion strategy, and (4) a resolution-aligned context semantic and structural detail fusion module. Moreover, we introduce an object-guided global-to-local registration framework to address dynamic cross-modal misalignment, and construct modality-aligned PoLaRIS-DET and ASV-RI-DET datasets that cover diverse water surface scenes. On the two datasets, the proposed method achieves mAP@0.5:0.95 scores of 74.2% and 50.2%, respectively, significantly outperforming existing methods with only 11.9M additional parameters. These results demonstrate the effectiveness of parameter-efficient VFM adaptation for multimodal water surface remote sensing. Full article

Against the backdrop of global coral reef degradation, benthic resource structure is shifting from coral dominance to turf algae and detritus-dominated epilithic algal matrix (EAM). As a typical detritivorous reef fish, Ctenochaetus striatus (Quoy & Gaimard, 1825) plays an important ecological role in regulating the functioning of degraded coral reef ecosystems. Using stable isotope analysis (δ¹³C and δ¹⁵N), this study systematically compared the trophic niche characteristics of different size classes of C. striatus across four reef habitats in the Xisha Islands, South China Sea, representing a gradient of disturbance (Qilianyu Island > Lingyang Reef > North Reef > Langhua Reef), in order to elucidate habitat-specific ontogenetic shifts and their adaptive features. The results showed that C. striatus from Qilianyu Island and Lingyang Reef exhibited overall higher δ¹⁵N values, suggesting an overall pattern consistent with stronger nitrogen enrichment at the more disturbed reefs, whereas individuals from Langhua Reef had significantly lower δ¹³C values, indicating a stronger reliance on offshore-derived carbon pathways. Across size classes, the trophic niche area (SEAc) and intraspecific trophic heterogeneity, measured as mean nearest neighbor distance and standard deviation of nearest neighbor distance, of populations from Qilianyu Island, Lingyang Reef, and North Reef generally decreased with increasing body size, revealing a pattern of trophic convergence toward core resources. In contrast, the Langhua Reef population exhibited a distinct expansion–contraction pattern, suggesting flexible resource use across developmental stages under conditions of low human disturbance and high resource heterogeneity. Although smaller size classes generally showed high probabilities of niche overlap among reefs, overlap declined markedly in the largest size class, with most values falling below 50%, indicating that resource assimilation strategies increasingly reflected reef-specific resource backgrounds. These findings demonstrate that ontogenetic trophic niche shifts in C. striatus are not fixed, but are highly dependent on local resource context and habitat conditions. In degraded reefs with simplified resource structure, individuals tend to converge on core resource spectra to maintain survival, whereas in healthier reefs with greater habitat heterogeneity, they tend to show greater variation in major food sources and resource use. This study provides a theoretical basis for coral reef ecological restoration. Full article

In insurance portfolios, classifying customers without a prior history at a given company is particularly challenging due to the absence of historical behavior, extreme class imbalance, heavy-tailed loss distributions, and strict operational constraints. Traditional machine learning approaches, including the baseline methodology proposed in previous studies, typically optimize global predictive accuracy and therefore fail to capture business-critical outcomes, especially the identification of high-risk clients. This study extends the existing approach by evaluating two complementary business-aware classification strategies: (i) a balanced bagging ensemble specifically designed to handle class imbalance and maximize expected profit under explicit customer-omission constraints, and (ii) a lightweight Transformer-based architecture capable of learning richer feature representations. Both approaches incorporate the asymmetric financial cost structure of insurance and operate under operational selection limits. The empirical analysis is conducted on a proprietary large-scale auto insurance dataset comprising 51,618 customers and is complemented by validation on nine synthetic datasets to assess robustness. Model performance is evaluated using statistical tests (ANOVA, Friedman, and pair-wise comparisons) together with business-oriented metrics. The results show that both proposed approaches consistently outperform the baseline methodology (p < 0.001) in terms of profit, with the ensemble offering a better balance of performance and efficiency, while the Transformer shows stronger robustness and generalization under data perturbations. The balanced ensemble provides the most favourable trade-off between predictive performance, robustness, interpretability, and computational efficiency, making it suitable for deployment in regulated insurance environments, while the Transformer achieves competitive results and exhibits stronger generalization under data perturbations. The proposed approach aligns machine learning with actuarial portfolio optimization by explicitly integrating profit-driven objectives and operational constraints, offering two practical and scalable solutions for risk-based decision-making in real-world insurance settings. Full article

This study proposes a robust hybrid framework for iris segmentation in covert biometric systems, specifically addressing the challenge of non-ideal images featuring fully or nearly closed eyes. To overcome the limitations of traditional geometric methods, this study implements a SqueezeNet-based Deep Convolutional Neural Network (DCNN) for rapid eye-state classification. Comparative analysis with various pretrained DCNN models indicates that SqueezeNet provides an optimal balance of accuracy and efficiency, requiring only 1.24 million parameters and a minimal memory footprint of 5.2 MB. For iris contour demarcation, the proposed algorithm combines the Circular Hough Transform (CHT) with global gray-level statistics and anatomical constraints to facilitate reliable iris localization. Utilizing image decimation, percentile-based thresholding, and Canny edge detection, it systematically delineates the limbic and pupillary boundaries. This improved search methodology ensures precise contour delineation, even under sub-optimal imaging circumstances. The proposed algorithm was validated on a novel dataset encompassing challenging conditions such as specular reflections, blur, non-uniform illumination, and varying degrees of occlusion, including nearly or fully closed eyes. Experimental results demonstrate superior segmentation accuracy and significant computational efficiency, underscoring the model’s potential for real-time biometric applications in unconstrained environments. Full article

Timely and accurate monitoring of surface water dynamics via remote sensing is critical, given water resources’ importance. However, accurate water body delineation based on high-resolution remotely sensed imagery is still challenging due to the complexity of water bodies’ boundaries and the diversity of their shapes and sizes, which can lead to boundary ambiguity and varying degrees of confusion with near-water vegetation in water body maps. To address this challenge, we introduce an uncertainty-aware hybrid CNN–Transformer model for delineating water bodies using remotely sensed imagery. In our designed network, a multi-scale transformer (MST) module is first designed to effectively model and refine the multi-scale global semantic dependencies of water bodies. Subsequently, an uncertainty-guided multi-scale information fusion (MSIF) module is constructed to extract water body mapping information from these multi-scale features output from the MST module and fuse them adaptively. Across different scales, the extracted features differ in their ability to distinguish water bodies from non-water bodies and in their levels of uncertainty. Consequently, during the adaptive fusion of multi-scale water body information in the MSIF module, the mapping uncertainty is quantified and suppressed to minimize its impact, thus yielding enhanced precision in water body delineation. Ultimately, a comprehensive loss function is designed for model optimization to generate the final water body map. Furthermore, to promote water body segmentation models’ development, this study also presents the HBD_Water water body sample dataset, which contains 44 multispectral, 5000 × 5000-pixel images at 2 m spatial resolution, and will be released on the LuojiaSET platform soon. Finally, to verify the proposed model and its constituent MST and MSIF modules, extensive water mapping experiments were performed on three datasets. The experimental results substantiate their effectiveness. Furthermore, comparative experiment results demonstrate that the proposed model performs better at water body extraction than advanced networks including TransUNet, DeeplabV3+, and ADCNN. Full article

Electroencephalogram (EEG) signals serve as the core information carrier for brain–computer interfaces (BCIs); however, their highly non-stationary nature, extremely low signal-to-noise ratio, and significant inter-individual variability pose considerable challenges for signal decoding. Existing deep learning methods struggle to strike a balance between multi-scale, fine-grained feature extraction and efficient long-range temporal modeling. To overcome this limitation, this study proposes a novel deep cascaded architecture, MSResBiMamba, which deeply integrates multi-scale spatiotemporal feature learning with cutting-edge long-sequence modeling techniques. The model first utilizes an enhanced multi-scale spatiotemporal convolutional network (MS-CNN) combined with a SE-channel attention mechanism to adaptively extract local multi-band features and dynamically suppress redundant artefacts. Subsequently, it innovatively introduces an enhanced bidirectional Mamba (Bi-Mamba) module to efficiently capture non-causal long-range temporal dependencies with linear computational complexity, whilst cascading multi-head self-attention mechanisms to establish global higher-order feature interactions. Extensive experiments on the BCI Competition IV-2a dataset demonstrate that MSResBiMamba achieves outstanding classification performance in multi-class motor imagery tasks, significantly outperforming traditional methods and existing state-of-the-art neural networks. Ablation studies and t-SNE visualisations further confirm the model’s robustness in feature decoupling and cross-subject applications, providing a high-precision, high-efficiency decoding solution for BCI systems. Full article

Background/Objectives: Alzheimer’s disease (AD) is an irreversible neurodegenerative disorder that imposes a profound burden on global public health. While resting-state functional magnetic resonance imaging (rs-fMRI)-based dynamic functional connectivity (dFC) analysis has demonstrated promise in capturing time-varying brain network abnormalities, existing deep learning methods suffer from three fundamental limitations: (1) an inability to model temporal dependencies across dynamic connectivity windows, (2) reliance on post hoc black-box explainability tools, and (3) misalignment between feature learning and classification objectives. Methods: To address these challenges, we propose MambaKAN, an end-to-end interpretable framework integrating a Variational Autoencoder (VAE), a Selective State Space Model (Mamba), and a Kolmogorov–Arnold Network (KAN). The VAE encodes each dFC snapshot into a compact latent representation, preserving nonlinear connectivity patterns. The Mamba encoder captures long-range temporal dynamics across the sequence of latent representations via input-selective state transitions. The KAN classifier provides intrinsic interpretability through learnable B-spline activation functions, enabling direct visualization of how latent features influence diagnostic decisions without post-hoc approximation. The entire pipeline is trained end-to-end with a joint loss function that aligns feature learning with classification. Results: Evaluated on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset across five classification tasks (CN vs. AD, CN vs. EMCI, EMCI vs. LMCI, LMCI vs. AD, and four-class), MambaKAN achieves accuracies of 95.1%, 89.8%, 84.0%, 86.7%, and 70.5%, respectively, outperforming strong baselines including LSTM, Transformer, and MLP-based variants. Conclusions: Comprehensive ablation studies confirm the indispensable contribution of each module, and the three-layer interpretability analysis reveals key temporal patterns and brain regions associated with AD progression. Full article