Search Results (600)

Accurate demand forecasting and adaptive load balancing are critical for maintaining stability and efficiency in modern smart power grids. This study proposes a hybrid deep learning (DL) framework, termed Transformer-Generative Adversarial Network-Gated Recurrent Unit (Transformer-GAN-GRU), which integrates global attention-based temporal modeling, generative data augmentation, and sequential refinement into a unified architecture. The proposed framework captures both long- and short-term dependencies while improving representation of imbalanced demand patterns. The model is evaluated on three heterogeneous benchmark datasets, namely Pecan Street, the reliability test system-grid modernization laboratory consortium (RTS-GMLC), and the reference energy disaggregation dataset (REDD). Experimental results demonstrate that the proposed model consistently outperforms state-of-the-art baselines, achieving a maximum accuracy (Acc) of 99.49%, a recall of 99.67%, and an area under the curve (AUC) of 99.83%. In addition to high predictive performance, the framework exhibits strong stability, fast convergence, and low inference latency, confirming its suitability for real-time deployment in smart grid environments. Full article

The aim of this study was to develop an effective and fast tool to support the automatic segmentation of skin lesions, with particular emphasis on the precise differentiation between malignant and benign lesions. In response to the problem of high false positive rates in existing CAD systems, modern neural network architectures from the YOLO family (YOLOv8, YOLOv9, YOLOv11, YOLOv12, and YOLOv26) were used in this research. The models were trained and evaluated on a new, balanced dataset (7000 images) based on the ISIC archive, where the key innovation was the introduction of a dedicated background class representing healthy skin. Through a multi-stage, rigorous optimization process, it was demonstrated that the yolov11s-seg model is highly effective for this task. It achieved a strong balance between effectiveness and processing speed, obtaining an mAP@50 score of 0.840 and an overall precision of 0.852. From a clinical perspective, the model’s high sensitivity (85.9%) in detecting the most aggressive lesion, invasive melanoma (MI), is particularly noteworthy. Thanks to its extremely short inference time (only 4.8 ms), the proposed yolov11s-seg variant overcomes the limitations of heavy hybrid architecture, providing a stable and highly efficient solution showing significant potential for deployment in real-time medical mobile applications. Full article

Millimeter-wave radar has gradually gained popularity as a sensor mode for Human Activity Recognition (HAR) in recent years because it preserves the privacy of individuals and is resistant to environmental conditions. Nevertheless, the fast inference of high-dimensional and sparse 4D radar data is still difficult to perform on low-resource edge devices. Current models, including 3D Convolutional Neural Networks and Transformer-based models, are frequently plagued by extensive parameter overhead or quadratic computational complexity, which restricts their applicability to edge applications. The present paper attempts to resolve these issues by introducing RadarSSM as a lightweight spatiotemporal hybrid network in the context of radar-based HAR. The explicit separation of spatial feature extraction and temporal dependency modeling helps RadarSSM decrease the overall complexity of computation significantly. Specifically, a spatial encoder based on depthwise separable 3D convolutions is designed to efficiently capture fine-grained geometric and motion features from voxelized radar data. For temporal modeling, a bidirectional State Space Model is introduced to capture long-range temporal dependencies with linear time complexity $O\left(T\right)$, thereby avoiding the quadratic cost associated with self-attention mechanisms. Extensive experiments conducted on public radar HAR datasets demonstrate that RadarSSM achieves accuracy competitive with state-of-the-art methods while substantially reducing parameter count and computational cost relative to representative convolutional baselines. These results validate the effectiveness of RadarSSM and highlight its suitability for efficient radar sensing on edge hardware. Full article

Grid-forming (GFM) battery energy storage system (BESS) inverters are becoming a cornerstone of resilient microgrids, where severe voltage sags and abrupt operating shifts can challenge both voltage regulation and controller stability. Finite-set model predictive control (FS-MPC) offers fast transient response and multi-objective coordination, yet conventional designs rely on static cost-function weights that are typically tuned offline and may become suboptimal under disturbance-driven regime changes. This paper proposes a forecast-guided KAN-adaptive FS-MPC framework that (i) formulates the inner-loop predictive control in the stationary αβ frame, thereby avoiding PLL dependency and mitigating loss-of-lock risk under extreme sags, and (ii) introduces an Operating Stress Index (OSI) that fuses load forecasts with reserve-margin or percent-operating-reserve signals to quantify grid vulnerability and trigger resilience-oriented control adaptation. A lightweight Kolmogorov–Arnold Network (KAN), parameterized by learnable B-spline edge functions, is embedded as an online weight governor to update key FS-MPC weighting factors in real time, dynamically balancing voltage tracking and switching effort. Experimental validation under high-frequency microgrid scenarios shows that, under a 50% symmetrical voltage sag, the proposed controller reduces the worst-case voltage deviation from 0.45 p.u. to 0.16 p.u. (64.4%) and shortens the recovery time from 35 ms to 8 ms (77.1%) compared with static-weight FS-MPC. In the islanding-like transition case, the proposed method restores the PCC voltage within 18 ms, whereas the static baseline fails to recover within 100 ms. Moreover, the deployed KAN governor requires only 6.2 μs per inference on a 200 MHz DSP, supporting real-time embedded implementation. These results demonstrate that forecast-guided adaptive weighting improves transient resilience and power quality while maintaining DSP-feasible computational complexity. Full article

Data acquired from a processing system using industrial-scale electrical resistance tomography (ERT) could provide valuable information on the operational performance of hydrocyclones. Tomography images of hydrocyclones, in general, are used to analyze operational parameters, but their analysis may not be fast enough to capture transient changes or provide clear phase boundaries between the object of interest and the medium. In such cases, one of the alternative approaches is to utilize least-squares modeling of the raw data to interpret transient changes, which is relatively faster and more efficient. In hindsight, this method may not be able to identify the location of the object of interest. In this paper, a new data analysis approach to estimate transient changes in the disturbance and a simplified conductivity matrix to estimate the location of the disturbance are considered. The conductivities measured across a cross-section were used to calculate the size of the disturbance. The disturbance’s position with respect to the cross-section was estimated using a simplified reconstruction of the conductivity matrix. In both cases, the same conductivity matrix was used. Several fundamental ERT experiments with different disturbance sizes were carried out to establish a suitable algorithm that could identify the disturbance. The analysis method presented in this paper can provide a basis to further explore an additional approach to analyze the performance of the hydrocyclone. The estimated radius of the disturbance was overlaid on an actual cross-section to infer the position with respect to the cross-section of the system. An attempt was also made to develop an empirical relationship that can estimate the effective size of the disturbance. The paper also discusses some implementation and practical challenges that need to be addressed for us to gain confidence in the proposed analysis method. Full article

Background/Objective: Women with a history of gestational diabetes mellitus (GDM) are at increased risk of type 2 diabetes mellitus (T2DM), dysglycemia, and dyslipidemia. However, the role of postpartum weight change in long-term metabolic outcomes remains unclear. Here, we determined the long-term incidence of dysglycemia and dyslipidemia after GDM and evaluated whether postpartum changes in body mass index (BMI) independently predicted these outcomes. Methods: This single-center prospective cohort study included 205 Japanese women diagnosed with GDM. All participants underwent a 75 g oral glucose tolerance test at 6–12 weeks postpartum. The incidence of impaired fasting glucose (IFG), impaired glucose tolerance (IGT), T2DM, and dyslipidemia was evaluated over a median follow-up of 3.6 years. Cumulative incidence was estimated using the Kaplan–Meier method, and Cox proportional hazards models identified independent risk factors, particularly postpartum BMI change. Results: During follow-up, 42.4%, 6.3%, and 35.6% of women developed IFG or IGT (prediabetes), T2DM, and dyslipidemia, respectively. The estimated cumulative incidence rates at 6 years postpartum were 57.1% and 50% for IFG/IGT and dyslipidemia, respectively, whereas the 5-year incidence of T2DM was 10.3%. Postpartum BMI increase was independently associated with new-onset dysglycemia. No independent predictor of T2DM progression was identified. Dyslipidemia was independently associated with higher pre-pregnancy BMI and multiparity, whereas postpartum BMI change was not independently associated after multivariable adjustment. Conclusions: Postpartum BMI change was independently associated with dysglycemia in women with a history of GDM. These findings suggest that postpartum weight change may help identify women at higher risk of subsequent metabolic abnormalities, particularly dysglycemia, in this high-risk population, although causal relationships cannot be inferred from this observational study. Full article

Cross-view geo-localization tries to find the matching place in large satellite or aerial pictures from photos taken at ground level, which is useful for applications like self-driving cars, flying drones, and adding virtual objects to real city scenes. However, the traditional deep learning hybrid CNN-Transformer architecture and complex geometric submodules result in a large computational overhead, making it difficult to apply in real-time on resource-constrained devices. To make it light, fast, and accurate, this paper suggests an effective way to make a state-space model for cross-view geo-localization tasks. The model replaces the traditional self-attention structure with a state-space vision backbone, lowering the sequence modeling complexity from quadratic to linear and greatly accelerating the inference process; it devises a channel-group aggregation strategy without any learnable parameters, producing a comprehensive yet lightweight representation, and introduces a dynamic difficulty-aware loss function that assigns varying weights to all negative samples within a batch according to their similarities, greatly improving the efficiency of hard-negative sample mining and the quality of convergence. The results on the authoritative public datasets CVUSA and CVACT indicate that our method has high accuracy and low computational complexity, providing a feasible approach for the lightweight design of more powerful cross-view geolocation models in the future. Full article

Lightweight day-ahead photovoltaic (PV) forecasting models encounter a significant technical challenge: under resource-constrained deployment conditions, it is difficult to simultaneously address weather-regime heterogeneity, maintain model interpretability, and preserve adaptability as operating conditions evolve. To address this issue, we propose a multimodal short-term photovoltaic (PV) forecasting method that integrates weather-mode partitioning using the Clustering Using Representatives (CURE) algorithm with a self-updating Batch-Lasso model. First, the meteorological-PV dataset is partitioned along two dimensions by combining seasonal grouping with CURE clustering within each season, producing representative weather modes and enhancing the fidelity of weather pattern classification. Second, to extract informative predictors from high-dimensional meteorological inputs while maintaining interpretability, we formulate per-mode Lasso regression and adopt the Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) to efficiently solve for the sparse regression coefficients. Third, we introduce a batch-based self-update and correction mechanism with rollback verification, enabling the mode-specific models to be refreshed as new historical data become available while preventing performance degradation. Compared with representative machine learning baselines, the proposed method maintains competitive accuracy with substantially lower computational and storage overhead, enabling high-frequency and energy-efficient inference on resource-constrained terminals, thereby reducing operational burdens and computational energy costs and better meeting the deployment needs of sustainable energy systems under heterogeneous weather conditions. Full article

Accurate crop classification provides fundamental data for agricultural resource management and ecological research. Hyperspectral image (HSI) classification is the core technique for achieving precise crop mapping. However, existing models often suffer from excessive parameters, limited robustness under few-shot conditions, and a trade-off between efficiency and robustness. To address these issues, this paper proposes a Multi-Scale Wavelet Kolmogorov–Arnold Network (MSWKN). The model employs a Two-Branch Feature Extractor (TBFE) to capture both spectral correlations and spatial textures. a Channel Cross-Spatial (CCS) module to suppress background clutter and highlight discriminative regions. A group convolution-based Fixed Wavelet Multi-Scale Convolutional Layer (FW-MSCL) that leverages the time–frequency localization of wavelets and learnable linear combinations to enhance robustness against spectral distortion while reducing parameters. And a Fourier-based Transformer encoder to enable global frequency–space modeling. Experiments on the WHU-Hi-HanChuan and WHU-Hi-HongHu hyperspectral crop datasets show that MSWKN achieves high overall accuracy and performs favorably on few-shot categories. Under lower parameter counts and fast inference conditions, the model demonstrates a reasonable trade-off between accuracy and computational efficiency. Ablation studies and wavelet kernel comparisons further confirm the contribution of each module and the advantage of the wavelet. The proposed framework provides an efficient and robust solution for fine-grained hyperspectral crop classification. Full article

Background: Dietary calcium and dairy products are hypothesized protective factors against metabolic syndrome (MetS), yet epidemiological evidence remains inconsistent. This systematic review and meta-analysis evaluated the association between total dietary calcium intake or dairy consumption and MetS prevalence in adults. Methods: Following PRISMA 2020 guidelines, PubMed, Cochrane Library, ClinicalTrials.gov, and SCOPUS were searched through to October 2025 for eligible cross-sectional studies assessing dietary calcium or dairy intake and MetS (NCEP ATP III, IDF, or JIS criteria). Longitudinal studies, non-English articles, and pediatric populations were excluded. Quality was assessed via an adapted Newcastle–Ottawa Scale. Random-effects meta-analyses pooled fully adjusted odds ratios (ORs) and 95% confidence intervals (CIs) comparing the highest versus lowest intake categories. Results: Twenty-four studies were included (12 for dietary calcium intake, 12 for dairy products). Higher dietary calcium intake was significantly associated with lower MetS odds (pooled OR: 0.85; 95% CI: 0.80–0.91), despite substantial heterogeneity (I² = 70.1%). Higher dairy consumption was also inversely associated with MetS (pooled OR: 0.78; 95% CI: 0.72–0.85; I² = 64.6%). While small-study effects were observed for dairy, trim-and-fill analysis confirmed the robustness of the findings. Higher calcium intake further correlated with favorable profiles in individual MetS components, including blood pressure, HDL cholesterol, waist circumference, triglycerides, and fasting glucose. Conclusions: Higher total dietary calcium intake and dairy product consumption are associated with a lower prevalence of MetS in adults. However, the cross-sectional nature of the included studies precludes any inference of causality between calcium intake and MetS. Therefore, although these findings suggest a protective role of calcium-rich diets, well-designed prospective and interventional studies are warranted to clarify whether this relationship is causal. Full article

Floating offshore wind turbines (FOWTs) exhibit complex motions under marine environmental loads and frequently undergo coupled oscillations across multiple degrees of freedom (DOFs). Accurate short-term motion prediction of these responses is crucial for operational safety and maintenance. To overcome the limitations of traditional “black-box” models under complex aero-hydrodynamic loads, this study proposes STL–TimesNet–NLinear, a novel physics-informed deep learning framework. The framework utilizes STL decomposition to explicitly decouple motion signals: NLinear captures non-stationary low-frequency slow drifts, while TimesNet extracts multi-periodic wave-frequency responses. The model was evaluated across different platform typologies—a 5 MW semi-submersible and a larger-scale 15 MW Spar-type platform—under various typical operational and extreme environmental conditions. Model performance was evaluated using comparative and ablation experiments. At a prediction-ahead time (PAT) of 5 s, the proposed model achieves coefficients of determination (R²) exceeding 0.95. Even at longer PATs, the R² remains above 0.90, consistently outperforming multiple benchmark models. Compared to traditional recurrent neural networks (e.g., LSTM), it decreases the Mean Absolute Error (MAE) for pitch motion under extreme sea states by 54.7% and increases the R² to 0.9573. Furthermore, the inference latency is only 2.4 ms per step. These findings confirm that the proposed STL–TimesNet–NLinear model provides fast and accurate solutions for the short-term motion response prediction of FOWTs, demonstrating valuable potential applications for enhancing the safety planning of offshore wind turbine operation and maintenance. Full article

Background: The need for autonomous aerial surveillance originates from weaknesses in manual monitoring, such as late response, low scalability and rigid patrol plans. AI and GPS-driven smart aerial monitoring present an attractive solution for continuous adaptive wide-area surveillance. Objective: In this paper, we aim at designing and validating experimentally a low-cost drone-based unmanned autonomous mission patrolling system with waypoint navigation, real-time video backhauling, AI-based human/object detection and GPS path re-planning when an event occurs to ensure the safety of patrol missions under battery constraints. Methods: The proposed architecture combines autonomous navigation and embedded flight-control with online analog video streaming and ground-station-based computer vision processing. Object detection based on deep learning for live aerial video is used, and the proposed system’s performance is tested at different altitudes, lighting states and GPS patrol plans. Results: Experimental results show that the proposed method can obtain stable waypoint tracking with a clear real-time video downlink in patrol missions. The system is able to adaptively modify paths as a reaction to detected events and commence safe return-to-home functionality during low-battery conditions. The proposed detection model obtains a mean average precision of 87.4%, with an F1-score of 0.89 and real-time inference latency (20–25 ms per frame) that enables fast service without any interruption in practice during surveillance deployment. Conclusions: Experimental results show that the proposed method can obtain stable waypoint tracking with a clear real-time video downlink in patrol missions. The system can adaptively modify paths as a reaction to detected events and commence safe return-to-home functionality during low-battery conditions. The proposed detection model obtains a mean average precision of 87.4%, with an F1-score of 0.89 and real-time inference latency (20–25 ms per frame) that enables fast service without any interruption in practice during surveillance deployment. Full article

Energy management systems operating under dynamic electricity pricing require fast and cost-optimal control strategies for flexible loads. Mixed-integer linear programming (MILP) can compute theoretically optimal control trajectories but is computationally expensive and typically relies on accurate load forecasts, limiting its practical real-time applicability. This paper proposes a supervised imitation learning (IL) framework that learns optimal setpoint trajectories for a conventional proportional (P) controller directly from electricity price signals and temporal features, thereby eliminating the need for explicit load forecasting. The learned model predicts setpoint trajectories in an open-loop manner, while a lower-level P controller ensures stable closed-loop operation within a two-stage control architecture. The approach is validated in an industrial case study involving load shifting of a refrigeration system under dynamic electricity pricing and benchmarked against MILP optimization, reinforcement learning (RL), heuristic strategies, and various machine learning models. The MILP solution achieves a cost reduction of 21.07% and represents a theoretical upper bound under perfect information. The proposed Transformer model closely approximates this optimum, achieving 19.33% cost reduction while enabling real-time inference. Overall, the results demonstrate that the proposed supervised IL approach can achieve near-optimal control performance with substantially reduced computational effort for real-time energy management applications. Full article

The fast growth of electric vehicles (EVs) and renewable energy motivates reliable charging infrastructure with balanced energy management and good power quality. However, conventional converter controllers like proportional and integral (PI) and fuzzy logic controllers (FLCs) exhibit slow dynamic response, poor adaptability to varying solar conditions, unbalanced energy management, low power quality, and higher total harmonic distortion (THD). To overcome these limitations, this work proposes an adaptive neuro-fuzzy inference system (ANFIS) controller for balanced energy management and improved power quality in EV charging stations. The ANFIS controller is a combination of a fuzzy inference system (FIS) and a neural network (NN). The FIS provides the best maximum power point tracking and robust control during changing solar PV conditions. The NN optimally controls the flow of power between the solar PV system, energy storage battery (ESB), EV, and utility grid. The entire system is simulated in MATLAB/Simulink. It consists of a PV system with a capacity of 2 kW, an ESB with a capacity of 10 kWh and an EV battery with a capacity of 4 kWh, which are linked by bidirectional DC/DC converters. A 30 kVA bidirectional inverter, along with an LCL filter, is connected between the 500 V DC bus and 440 V utility grid, allowing for both directions. The results validate the effectiveness of the proposed ANFIS controller in terms of DC bus voltage stability, faster dynamic response, enhanced renewable energy utilization, improved efficiency to 98.86%, reduced voltage and current THD to 4.65% and 2.15% respectively, reduced utility grid stress, and enhanced energy management compared to conventional PI and FLCs. Full article

4D millimeter-wave radar provides a promising solution for robust perception in adverse weather. Existing detectors still struggle with sparse and noisy point clouds, and maintaining real-time inference while achieving competitive accuracy remains challenging. We propose SGE-Flow, a streamlined PointPillars-based 4D radar 3D detector that embeds lightweight spatiotemporal geometric enhancements into the voxelization front-end. Velocity Displacement Compensation (VDC) leverages compensated radial velocity to align accumulated points in physical space and improve geometric consistency. Distribution-Aware Density (DAD) enables fast density feature extraction by estimating per-pillar density from simple statistical moments, which also restores vertical distribution cues lost during pillarization. To compensate for the absence of tangential velocity measurements, a Transformer-based Inter-frame Flow (IFF) module infers latent motion from frame-to-frame pillar occupancy changes. Evaluations on the View-of-Delft (VoD) dataset show that SGE-Flow achieves 53.23% 3D mean Average Precision (mAP) while running at 72 frames per second (FPS) on an NVIDIA RTX 3090. The proposed modules are plug-and-play and can also improve strong baselines such as MAFF-Net. Full article