Search Results (79)

With the increasing integration of wind and solar energy, power systems face growing challenges in supply–demand balancing, renewable energy accommodation, and reserve regulation, especially in future power systems with evolving generation mixes. To this end, a system adaptability evaluation method particularly considering planned future wind farms and photovoltaic (PV) stations is proposed. Available historical meteorological data are converted into wind and PV power output sequences through renewable power conversion models. Then, a generative adversarial network (GAN)-based model is built to learn the temporal fluctuation characteristics and inter-station correlations of renewable generation, thereby generating multiple representative wind and PV output scenarios. Finally, these scenarios are embedded into a security-constrained unit commitment (SCUC)-based model to evaluate system adaptability in terms of load shedding, renewable energy curtailment, accommodation rate, and reserve margin. The proposed method provides a forward-looking framework for assessing the operational adaptability of power systems under high renewable energy penetration. Full article

This paper presents the design, structural optimization, and two-dimensional (2D) technology computer-aided design (TCAD) simulation of a gallium nitride (GaN) vertical Merged P-i-N/Schottky (MPS) diode incorporating a multi-drift-layer doping profile, composite SiO₂/Si₃N₄ passivation, and field-plate (FP) termination. The proposed device is constructed on an n⁺-GaN substrate with a three-sub-layer n-type drift region and a p-GaN/p⁺-GaN anode region. Systematic TCAD simulations are performed to investigate the dependences of key performance metrics—including knee voltage (V_knee), specific on-resistance (R_on), breakdown voltage (BV), reverse leakage current (J_leak), and Baliga’s figure of merit (BFOM)—on the Schottky metal work function, multi-drift-layer doping concentration, drift-layer thickness, Schottky-to-PN contact length ratio (γ_w), operating temperature, and reverse recovery switching transients. Results demonstrate that the MPS architecture effectively decouples forward conduction loss from reverse blocking capability, overcoming the conventional R_on–BV trade-off. The optimal doping profile (n_mm = 2 × 10¹⁵, n_m = 2 × 10¹⁵, n = 1 × 10¹⁶ cm⁻³) achieves a BFOM of ~31.97 GW·cm⁻² with BV ≈ 5.98 kV and R_on ≈ 1.12 mΩ·cm². Joint doping–thickness optimization further identifies a graded doping profile (n_mm = 2 × 10¹⁵, n_m = 5 × 10¹⁵, n = 1 × 10¹⁶ cm⁻³) combined with layer thicknesses (T_nmm, T_nm, T_n) = (4.49, 5, 20) μm as the overall optimum, achieving BFOM = 55.36 GW·cm⁻² (BV = 6.61 kV, R_on = 0.79 mΩ·cm²)—a +73% improvement, governed by the punch-through/field-stop design principle. The optimal contact ratio of γ_w = 1.33 yields a BFOM of 38.71 GW·cm⁻². Temperature analysis confirms a positive BV temperature coefficient due to drift-region-limited avalanche breakdown, and the BFOM improves monotonically from 33.31 to 37.82 GW·cm⁻² between 200 K and 450 K. Mixed-mode switching simulations show that increasing γ_w substantially reduces reverse recovery charge (Q_rr), demonstrating the strong potential of the proposed MPS diode for high-voltage, high-frequency, and high-temperature power electronic applications. Full article

The large-scale integration of variable renewable energy sources introduces critical challenges of intermittency and uncertainty, yet consumption forecasting, generation forecasting, and anomaly detection are typically addressed in isolation, neglecting the bidirectional feedback between consumption patterns, generation mix, and public decision-making. This PRISMA 2020-compliant systematic review compared statistical, machine learning, and deep learning models for energy forecasting and machine learning and deep learning models for anomaly detection. Searches in Google Scholar and Scopus used seven targeted strings, restricted to peer-reviewed empirical studies (2022–2026; 2023–2026 for anomaly detection), indexed in Q1–Q3 JCR journals, excluding theoretical and non-benchmarked works. A six-item risk of bias questionnaire—with a threshold of four points—guided inclusion, yielding 60 articles. Addressing the first research question (RQ1) on comparative model performance, hybrid deep learning architectures optimized with bio-inspired metaheuristics achieved the highest forecasting accuracy ($R^2$ up to 0.9984), with metaheuristic optimization acting as a cost-reducing factor; statistical models remained competitive for long-horizon forecasting, while large-language-model-based approaches addressed data scarcity through few-shot learning. Addressing the second research question (RQ2) on smart grid optimization, predictive techniques reduce forecasting errors enabling real-time load adjustment and Demand Response, though a systematic asymmetry constrains their potential: consumption studies integrate socio-economic variables, whereas generation studies rely on meteorological inputs. Addressing the third research question (RQ3) on infrastructure security, supervised and unsupervised approaches detect anomalous operational states and support fault diagnosis, yet remain constrained by scarce labeled fault data and limited cross-regional validation; generative models such as GANs and diffusion models partially address this limitation by enabling Sim2Real strategies and realistic digital twin construction. Evidence is strongest for hybrid forecasting; certainty is lower for anomaly detection given reliance on experimental surrogates. No single paradigm achieves universal superiority. The primary finding is the consistent absence of integrated frameworks jointly modeling consumption, generation, anomaly detection, and public decision-making across the reviewed literature. This result reflects a structural limitation of the current state of the art, rather than a forward-looking research agenda. This study was funded by the ENIA International Chair on Trustworthy Artificial Intelligence European Recovery Plan; the protocol was not pre-registered. Full article

This narrative critical review addresses class imbalance in medical imaging, particularly within the context of multi-sensor and multi-modal environments, poses a critical challenge to developing reliable AI diagnostic systems. The integration of heterogeneous data from sources like CT, MRI, and PET presents a unique opportunity to address data scarcity for rare conditions through fusion techniques. This review provides a structured analysis of strategies to tackle class imbalance, categorizing them into data-centric (e.g., advanced resampling like SMOTE-ENC for mixed data types, GAN-based synthesis) and model-centric (e.g., loss function engineering, transfer learning, and ensemble methods) approaches. Crucially, we highlight how multi-sensor feature fusion and decision-level fusion paradigms can inherently enrich representations for minority classes, offering a powerful frontier beyond single-modality learning. We evaluate each method’s merits, clinical viability, and compliance considerations (e.g., FDA). Finally, we identify emerging trends where imbalance-aware learning synergizes with multi-sensor fusion frameworks, federated learning, and explainable AI, charting a roadmap toward robust, equitable, and clinically deployable diagnostic tools. Our quantitative synthesis shows that data-centric strategies can improve minority class recall by 12–35% in datasets with imbalance ratios (majority:minority) ≥10:1, while model-centric strategies achieve an average AUC improvement of 0.08–0.21 in multi-sensor medical imaging tasks with sample sizes ranging from 50 to 50,000. Full article

Background/Objectives: Contrast-enhanced CT (CECT) is essential for mediastinal and lymph node assessment but is often limited in patients with renal dysfunction, prior severe contrast reactions, or pediatric populations. Deep learning approaches, such as generative adversarial networks (GANs), allow the generation of synthetic CECT (sCECT) from non-contrast CT (NCCT) without contrast injection. Materials and Methods: A GAN-based model was trained using 400 CECT scans acquired between March and July 2024. The model was tested in 20 patients with lymphoma or metastatic lymphadenopathy diagnosed between January and July 2025, using only NCCT scans. Quantitative evaluation compared sCECT with CECT using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Pearson Correlation Coefficient (PCC). Two radiologists performed qualitative assessment, and Signal-to-Noise Ratio (SNR)/Contrast-to-Noise Ratio (CNR) values were measured for thoracic structures. Results: Compared with NCCT, sCECT demonstrated slightly lower MAE (20.87 ± 8.84 vs. 21.26 ± 9.26) and RMSE (45.22 ± 14.22 vs. 45.94 ± 15.07), and marginally higher PSNR (15.44 ± 2.70 vs. 15.38 ± 3.02), indicating modest improvements in pixel-wise similarity. SSIM values were comparable (0.610 ± 0.09 vs. 0.63 ± 0.10), while PCC decreased (0.61 ± 0.09 vs. 0.77 ± 0.15). All differences were statistically significant (p < 0.001). Despite these mixed quantitative results, sCECT was qualitatively rated significantly higher by radiologists, with improved visualization of mediastinal structures. SNR and CNR analyses further supported enhanced contrast depiction in sCECT compared with NCCT. Conclusions: The GAN-based model successfully generated sCECT from NCCT with modest quantitative similarity gains but clear qualitative improvement, particularly for mediastinal lymph node evaluation. Although synthetic enhancement represents a learned intensity transformation rather than true iodine-based attenuation, sCECT may serve as a valuable adjunct in patients with contraindications to iodinated contrast. Full article

Dislocation reduction in gallium nitride (GaN) epitaxial layers remains a critical challenge for high-performance GaN-based electronic devices. In this study, GaN epitaxial growth on newly-developed 4H-Silicon Carbide (SiC) meta-substrates was systematically investigated to elucidate the role of surface pattern geometry in modulating dislocation propagation. A series of truncated-hexagonal-pyramid meta-structures with a fixed array period and varying pattern ratios (R) were designed and fabricated to enable controlled tuning of the effective surface morphology. Atomic force microscopy confirmed comparable surface flatness for all samples after epitaxial growth. Cathodoluminescence analysis revealed a non-monotonic dependence of defect density on R, indicating the existence of an optimal pattern geometry. Among all configurations, the outstanding sample exhibited the lowest defect density, achieving a 54.96% reduction in threading dislocations (edge + mixed) compared with a planar reference. Cross-sectional transmission electron microscopy further confirmed a substantially reduced dislocation density and clear evidence of dislocation bending and termination near the meta-structured regions. These results demonstrate that geometry-engineered 4H-SiC meta-substrates provide an effective and scalable strategy for dislocation modulation in GaN epitaxy on SiC meta-substrates, offering a promising pathway toward advanced GaN power and RF devices. Full article

In mixed traffic scenarios involving both motorized and non-motorized participants, accurately predicting future trajectories of surrounding vehicles remains a major challenge for autonomous driving. Predicting the motion of powered two-wheelers (PTWs) is particularly difficult due to their abrupt behavioral changes and stochastic interaction patterns. To address this issue, this paper proposes an enhanced Social-GAT model with a multi-module architecture for PTW trajectory prediction. The model consists of a dual-channel LSTM encoder that separately processes position and motion features; a temporal attention mechanism to weight key historical states; and a residual-connected two-layer GAT structure to model social relationships within the interaction range, capturing interactive features between PTWs and surrounding vehicles through dynamic adjacency matrices. Finally, an LSTM decoder integrates spatiotemporal features and outputs the predicted trajectory. Experimental results on the rounD dataset demonstrate that our model achieves an outstanding ADE of 0.28, surpassing Trajectron++ by 9.68% and Social-GAN by 69.2%. It also attains the lowest RMSE values across 0.4–2.0s prediction horizons, confirming its superior accuracy and stability for PTW trajectory prediction in mixed traffic environments. Full article

The rapid advancement of generative models, such as GAN and diffusion architectures, has enabled the creation of highly realistic forged images, raising critical challenges in key domains. Detecting such forgeries is essential to prevent potential misuse in sensitive areas, including healthcare, financial documentation, and identity verification. This study addresses the problem by deploying a vision transformer (ViT)-based multiclass classification framework to identify image forgeries across three distinct domains: invoices, human faces, and medical images. The dataset comprises both authentic and AI-generated samples, creating a total of six classification categories. To ensure uniform feature representation across heterogeneous data and to effectively utilize pretrained weights, all images were resized to 224 × 224 pixels and converted to three channels. Model training was conducted using stratified K-fold cross-validation to maintain balanced class distribution in each fold. Experimental results of this study demonstrate consistently high performance across three folds, with an average training accuracy of 0.9983 (99.83%), validation accuracy of 0.9620 (96.20%), and test accuracy of 0.9608 (96.08%), along with a weighted F1 score of 0.9608 and exceeding 0.96 (96%) for all classes. These findings highlight the effectiveness of ViT architectures for cross-domain forgery detection and emphasize the importance of preprocessing standardization when working with mixed datasets. Full article

Accurate diagnosis of melanoma using hematoxylin and eosin (H&E)-stained histological images is often challenged by the scarcity and imbalance of biomedical datasets, limiting the performance of deep learning models. This study investigates the impact of synthetic image generation, via generative adversarial networks (GAN), on training automatic classifiers based on the ResNet-18 architecture. Two experimental setups were designed: one using only real images and another combining real images with synthetic ones of the melanocytic nevus class to balance the dataset. Models were trained and evaluated at resolutions up to 1024 × 1024 pixels, employing standard classification metrics and the Fréchet Inception Distance (FID) to assess the quality of the generated images. The results suggest that although mixed models do not consistently outperform those trained exclusively on real data, they achieve competitive performance, particularly in terms of specificity and reduction in false negatives. This study supports the use of synthetic data as a complementary tool in scenarios where the acquisition of new samples is limited and lays the groundwork for future research in conditional generation and synthesis of malignant samples. In our best-performing model (1024 × 1024 px, 50 epochs, mixed dataset), we achieved an accuracy of 96.00%, a specificity of 97.00%, and a reduction in false negatives from 80 to 75 cases compared with real-only training. These results highlight the potential of synthetic augmentation to improve clinically relevant outcomes, particularly in reducing missed melanoma diagnoses. Full article

This exploratory study investigates the usability of performance metrics for generative adversarial network (GAN)-based models for speech-driven facial animation. These models focus on the transfer of speech information from an audio file to a still image to generate talking-head videos in a small-scale “everyday usage” setting. Two models, LipGAN and a custom implementation of a Wasserstein GAN with gradient penalty (L1WGAN-GP), are examined for their visual performance and scoring according to commonly used metrics: Quantitative comparisons using FID, SSIM, and PSNR metrics on the GRIDTest dataset show mixed results, and metrics fail to capture local artifacts crucial for lip synchronization, pointing to limitations in their applicability for video animation tasks. The study points towards the inadequacy of current quantitative measures and emphasizes the continued necessity of human qualitative assessment for evaluating talking-head video quality. Full article

To address the small-sample training bottleneck and inadequate convergence efficiency of Deep Reinforcement Learning (DRL)-based communication anti-jamming methods in complex electromagnetic environments, this paper proposes a Generative Adversarial Network-enhanced Deep Q-Network (GA-DQN) anti-jamming method. The method constructs a Generative Adversarial Network (GAN) to learn the time–frequency distribution characteristics of short-period jamming and to generate high-fidelity mixed samples. Furthermore, it screens qualified samples using the Pearson correlation coefficient to form a sample set, which is input into the DQN network model for pre-training to expand the experience replay buffer, effectively improving the convergence speed and decision accuracy of DQN. Our simulation results show that under periodic jamming, compared with the DQN algorithm, this algorithm significantly reduces the number of interference occurrences in the early communication stage and improves the convergence speed, to a certain extent. Under dynamic jamming and intelligent jamming, the algorithm significantly outperforms the DQN, Proximal Policy Optimization (PPO), and Q-learning (QL) algorithms. Full article

Privacy preservation poses significant challenges in third-party data sharing, particularly when handling table data containing personal information such as demographic and behavioral records. Synthetic table data generation has emerged as a promising solution to enable data analysis while mitigating privacy risks. While Generative Adversarial Networks (GANs) are widely used for this purpose, they exhibit limitations in modeling table data due to challenges in handling mixed data types (numerical/categorical), non-Gaussian distributions, and imbalanced variables. To address these limitations, this study proposes a novel adversarial learning framework integrating gradient boosting trees for synthesizing table data, called Adversarial Gradient Boosting Decision Tree (AGBDT). Experimental evaluations on several datasets demonstrate that our method outperforms representative baseline models regarding statistical similarity and machine learning utility. Furthermore, we introduce a privacy-aware adaptation of the framework by incorporating k-anonymization constraints, effectively reducing overfitting to source data while maintaining practical usability. The results validate the balance between data utility and privacy preservation achieved by our approach. Full article

This paper introduces a novel adversarial learning framework for reconstructing hidden layers in historical palimpsests. Recovering text hidden in historical palimpsests is complicated by various artifacts, such as ink diffusion, degradation of the writing substrate, and interference between overlapping layers. To address these challenges, the authors of this paper combine a synthetic data generator grounded in physical modeling with three generative architectures: a baseline VAE, an improved variant with stronger regularization, and a U-Net-based GAN that incorporates residual pathways and a mixed loss strategy. The synthetic data engine aims to emulate key degradation effects—such as ink bleeding, the irregularity of parchment fibers, and multispectral layer interactions—using stochastic approximations of underlying physical processes. The quantitative results suggest that the U-Net-based GAN architecture outperforms the VAE-based models by a notable margin, particularly in scenarios with heavy degradation or overlapping ink layers. By relying on synthetic training data, the proposed method facilitates the non-invasive recovery of lost text in culturally important documents, and does so without requiring costly or specialized imaging setups. Full article

The integration of high-penetration renewable energy sources (RESs) into transmission networks introduces profound uncertainty that challenges traditional infrastructure planning approaches. Existing transmission expansion planning (TEP) models either rely on static scenario sets or over-conservative worst-case assumptions, failing to capture the operational stress triggered by rare but structurally impactful renewable behaviors. This paper proposes a novel bi-level optimization framework for transmission planning under adversarial uncertainty, coupling a distributionally robust upper-level investment model with a lower-level operational response embedded with physics and market constraints. The uncertainty space was not exogenously fixed, but instead dynamically generated through a physics-informed spatiotemporal generative adversarial network (PI-ST-GAN), which synthesizes high-risk renewable and load scenarios designed to maximally challenge the system’s resilience. The generator was co-trained using a composite stress index—combining expected energy not served, loss-of-load probability, and marginal congestion cost—ensuring that each scenario reflects both physical plausibility and operational extremity. The resulting bi-level model was reformulated using strong duality, and it was decomposed into a tractable mixed-integer structure with embedded adversarial learning loops. The proposed framework was validated on a modified IEEE 118-bus system with high wind and solar penetration. Results demonstrate that the GAN-enhanced planner consistently outperforms deterministic and stochastic baselines, reducing renewable curtailment by up to 48.7% and load shedding by 62.4% under worst-case realization. Moreover, the stress investment frontier exhibits clear convexity, enabling planners to identify cost-efficient resilience strategies. Spatial congestion maps and scenario risk-density plots further illustrate the ability of adversarial learning to reveal latent structural bottlenecks not captured by conventional methods. This work offers a new methodological paradigm, in which optimization and generative AI co-evolve to produce robust, data-aware, and stress-responsive transmission infrastructure designs. Full article

Pedestrian safety at crosswalks remains a critical concern as traffic accidents frequently result from drivers’ failure to yield, leading to severe injuries or fatalities. In response, various jurisdictions have enacted pedestrian priority laws to regulate driver behavior. Nevertheless, intersections lacking clear traffic signage and environments with limited visibility continue to present elevated risks. The scarcity and difficulty of collecting data under such complex conditions pose significant challenges to the development of accurate detection systems. This study proposes a CyclicGAN-based loop-learning framework, in which the learning process begins with a set of manually annotated images used to train an initial labeling model. This model is then applied to automatically annotate newly generated synthetic images, which are incorporated into the training dataset for subsequent rounds of model retraining and image generation. Through this iterative process, the model progressively refines its ability to simulate and recognize diverse contextual features, thereby enhancing detection performance under varying environmental conditions. The experimental results show that environmental variations—such as daytime, nighttime, and rainy conditions—substantially affect the model performance in terms of F1-score. Training with a balanced mix of real and synthetic images yields an F1-score comparable to that obtained using real data alone. These results suggest that CycleGAN-generated images can effectively augment limited datasets and enhance model generalization. The proposed system may be integrated with in-vehicle assistance platforms as a supportive tool for pedestrian-crossing detection in data-scarce environments, contributing to improved driver awareness and road safety. Full article