Search Results (326)

Background/Objectives: Sugemalimab demonstrated clinical efficacy in the GEMSTONE-303 trial, but its cost-effectiveness remains unclear. This study aims to evaluate the cost-effectiveness of sugemalimab in combination with chemotherapy (CAPOX) as a first-line treatment for patients with advanced or metastatic gastric or gastroesophageal junction (G/GEJ) adenocarcinoma, compared to chemotherapy alone, from the perspective of Taiwan’s healthcare payer. Methods: A partitioned survival model was developed to simulate outcomes over a 40-year time horizon, and model parameters were derived from GEMSTONE-303 and the wider literature. Health benefits were measured in quality-adjusted life-years (QALYs), and only direct medical costs were included, with both discounted at an annual rate of 3%. The willingness-to-pay threshold was set at three times the 2024 GDP per capita. Deterministic and probabilistic sensitivity analyses were conducted alongside scenario analyses. Results: Compared to capecitabine and oxaliplatin (CAPOX) alone, adding sugemalimab yielded an incremental gain of 0.39 QALYs at an additional cost of USD 47,020, resulting in an incremental net monetary benefit of −USD 7478. Conclusions: Sugemalimab plus CAPOX is not cost-effective for advanced or metastatic G/GEJ adenocarcinoma from the Taiwan payer’s perspective. Achieving cost-effectiveness would require a 20–30% price reduction for sugemalimab (to USD 1204–USD 1376 per 600 mg), assuming first-line therapy is administered for the median treatment duration observed in the GEMSTONE-303 trial. If reimbursement continued until disease progression, a reduction of approximately 68% would be required (USD 550 per 600 mg). Full article

Phorusrhacids correspond to a group of birds considered to be apex predators, which are a common element of the American fossil Cenozoic avifauna, especially in Argentina, where it is not unusual to find at least two species of terror birds. Nevertheless, the presence of more than one species of terror bird outside Argentina is null. Here we report a second terror bird from the middle Miocene of La Venta locality. The new specimen could reach approximately 180 kg, being about 15% larger than the previous report of a terror bird for the locality. Although it is not possible to completely discard the possibility of these two specimens belonging to a dimorphic species, morphological differences may indicate so. Certainly, the presence of two gigantic terror birds coexisting in the La Venta locality represents an interesting scenario for further studies on their ecology and niche partitioning; this could be an argument for the presence of large open areas within the forests and wetlands of La Venta, further supporting the complex and diverse ecosystems in this region during the Middle Miocene period. Full article

In recent years, with the development of micro-satellite clusters and large-scale satellite constellations, the likelihood of multiple spacecraft engaging in orbital pursuit–evasion games has increased. This paper establishes a novel interception domain theory for planar orbital multi-player “encirclement-capture” differential games, and it proves the partitioned structure and classification properties of Nash equilibrium solutions. The main contributions of our study are the following: (1) Proposing the first rigorous definition of interception domains in orbital pursuit–evasion games, proving their convexity, developing computational methods for domain intersections, and establishing a complete classification of equilibrium for planar multi-pursuer interception games, which establishes a theoretical foundation for analyzing multi-spacecraft orbital pursuit–evasion games. (2) Analyzing Nash equilibrium properties for “encirclement-capture” differential games with two, three, or more pursuers, classifying degenerate/non-degenerate scenarios via spatial inclusion relationships. The equilibrium results indicate that as the number of pursuers increases, the game tends toward a degenerate scenario where the likelihood of redundant pursuers (whose actions do not affect the game outcome) rises. Full article

Community Earth System Model-Large Ensemble (CESM-LE) simulations are used to partition the Surface Air Temperature (SAT) trends over East Asia into the contribution of external forcing factors and internal variability. In the historical period (1966–2005), the summer SAT trends display a considerable diversity (≤−2 °C to ≥2 °C) across the 35 member ensembles, while under the RCP8.5 scenario, the region is mostly dominated by a strong warming trend (~1.5–2.5 °C/51 years) and touches the ~4 °C mark by the end of the 21st century. In the historical period, the warming is prominent over the Yangtze River basin of China, while under the RCP8.5 scenario, the warming pattern shifts northward towards Mongolia. In the historical period, the Signal-to-Noise Ratio (SNR) is less than 1, while it is higher than 4 under the RCP8.5 scenario, which indicates that, in the early period, internal variability overrides the forced response and vice versa under the RCP8.5 scenario. In addition, over much of the East Asian region, the chances of cooling are relatively high in the historical period, which partially counteracted the warming trend due to external forcing factors. In contrast, under the RCP8.5 scenario, the chances of warming reach ~100% over East Asia due to contributions from the external forcing factors. The novel aspect of the current study is that, in the negative phase (from the mid-1960s to ~2000), the Atlantic Multidecadal Oscillation (AMO) accounts for ~70–80% of the cooling trend or the SAT variability over East Asia, and thereafter, natural variability exhibits a slow increasing trend in the future. However, the contribution of external forcing factors increases from ~55% in 2000 to 95% in 2075 at a rate much faster than natural variability, which is primarily due to increasing downward solar radiation fluxes and albedo feedback on SAT over East Asia. Full article

In recent years, the remarkable versatility of large language models (LLMs) has spurred considerable interest in leveraging their capabilities for recommendation systems. Critically, we argue that the intrinsic aptitude of LLMs for modeling sequential patterns and temporal dynamics renders them uniquely suited for sequential recommendation tasks—a foundational premise explored in depth later in this work. This potential, however, is tempered by significant hurdles: a discernible gap exists between the general competencies of conventional LLMs and the specialized needs of recommendation tasks, and their capacity to uncover complex, latent data interrelationships often proves inadequate, potentially undermining recommendation efficacy. To bridge this gap, our approach centers on adapting LLMs through fine-tuning on dedicated recommendation datasets, enhancing task-specific alignment. Further, we present the temporal Integration Enhanced Fine-Tuning of Large Language Models for Sequential Recommendation (TisLLM) framework. TisLLM specifically targets the deeper excavation of implicit associations within recommendation data streams. Its core mechanism involves partitioning sequential user interaction data using temporally defined sliding windows. These chronologically segmented slices are then aggregated to form enriched contextual representations, which subsequently drive the LLM fine-tuning process. This methodology explicitly strengthens the model’s compatibility with the inherently sequential nature of recommendation scenarios. Rigorous evaluation on benchmark datasets provides robust empirical validation, confirming the effectiveness of the TisLLM framework. Full article

This study tackles the issue of ensuring secure communications in vehicular ad hoc networks (VANETs) under dynamic eavesdropping threats, where eavesdroppers adaptively reposition to intercept transmissions. We introduce a scheme utilizing a partitioned reconfigurable intelligent surface (RIS) to assist in the joint transmission of confidential signals and artificial noise (AN) from a source station. The RIS is divided into segments: one enhances legitimate signal reflection toward the intended vehicular receiver, while the other directs AN toward eavesdroppers to degrade their reception. To maximize secrecy performance in rapidly changing environments, we introduce a joint optimization framework integrating meta-learning for RIS partitioning and reinforcement learning (RL) for reflection matrix optimization. The meta-learning component rapidly determines the optimal RIS partitioning ratio when encountering new eavesdropping scenarios, leveraging prior experience to adapt with minimal data. Subsequently, RL is employed to dynamically optimize both beamforming vectors as well as RIS reflection coefficients, thereby further improving the security performance. Extensive simulations demonstrate that the suggested approach attain a 28% higher secrecy rate relative to conventional RIS-assisted techniques, along with more rapid convergence compared to traditional deep learning approaches. This framework successfully balances signal enhancement with jamming interference, guaranteeing robust and energy-efficient security in highly dynamic vehicular settings. Full article

Reliable LiDAR point clouds are essential for perception in robotics and autonomous driving. However, adverse weather conditions introduce substantial noise that significantly degrades perception performance. To tackle this challenge, we first introduce a novel, point-wise annotated dataset of over 800 scenes, created by collecting and comparing point clouds from real-world adverse and clear weather conditions. Building upon this comprehensive dataset, we propose the Spatial Context-Aware Point Cloud Encoder Network (SCOPE), a deep learning framework that identifies noise by effectively learning spatial relationships from sparse point clouds. SCOPE partitions the input into voxels and utilizes a Voxel Spatial Feature Extractor with contrastive learning to distinguish weather-induced noise from structural points. Experimental results validate SCOPE’s effectiveness, achieving high Intersection-over-Union (mIoU) scores in snow (88.66%), rain (92.33%), and fog (88.77%), with a mean mIoU of 89.92%. These consistent results across diverse scenarios confirm the robustness and practical effectiveness of our method in challenging environments. Full article

Traffic sign detection is critically important for intelligent transportation systems, yet persistent challenges like multi-scale variation and complex background interference severely degrade detection accuracy and real-time performance. To address these limitations, this study presents CPB-YOLOv8, an advanced multi-scale detection framework based on the YOLOv8 architecture. A Cross-Stage Partial-Partitioned Transformer Block (CSP-PTB) is incorporated into the feature extraction stage to preserve semantic information during downsampling while enhancing global feature representation. For feature fusion, a four-level bidirectional feature pyramid BiFPN integrated with a P2 detection layer significantly improves small-target detection capability. Further enhancement is achieved via an optimized loss function that balances multi-scale objective localization. Comprehensive evaluations were conducted on the TT100K, the CCTSDB, and a custom multi-scenario road image dataset capturing urban and suburban environments at 1920 × 1080 resolution. Results demonstrate compelling performance: On TT100K, CPB-YOLOv8 achieved 90.73% mAP@0.5 with a 12.5 MB model size, exceeding the YOLOv8s baseline by 3.94 percentage points and achieving 6.43% higher small-target recall. On CCTSDB, it attained a near-saturation performance of 99.21% mAP@0.5. Crucially, the model demonstrated exceptional robustness across diverse environmental conditions. Rigorous analysis on partitioned CCTSDB subsets based on weather and illumination, alongside validation using a separate self-collected dataset reserved solely for inference, confirmed strong adaptability to real-world distribution shifts and low-visibility scenarios. Cross-dataset validation and visual comparisons further substantiated the model’s robustness and its effective suppression of background interference. Full article

Monitoring multimode industrial processes presents significant challenges due to varying operating conditions, nonlinear dynamics, and mode-dependent feature distributions. This paper proposes a novel process monitoring framework that integrates an enhanced Gaussian Mixture Model (GMM) for mode identification with Label Consistent K-SVD (LC-KSVD) for sparse dictionary learning. The improved GMM employs a parallelized Expectation–Maximization algorithm to achieve accurate and scalable mode partitioning in high-dimensional environments. Subsequently, the LC-KSVD then learns label-consistent, discriminative sparse representations, enabling effective monitoring across modes. The proposed method is evaluated through a simulation study and the widely used Continuous Stirred Tank Heater (CSTH) benchmark. Comparative results with traditional techniques such as LNS-PCA and FGMM demonstrate that the proposed method achieves superior fault detection rates (FDRs) and significantly lower false alarm rates (FARs), even under complex mode transitions and mild fault scenarios. Furthermore, the method also provides interpretable fault isolation through reconstruction-error-guided variable contribution analysis. These findings confirm that the proposed LC-KSVD-based scheme offers a reliable solution for fault detection and isolation in multimode process systems. Full article

The increasing frequency of climate- and cyber-induced blackouts in modern distribution networks calls for restoration strategies that are both resilient and control-aware. Traditional black-start schemes, based on predefined energization sequences from synchronous machines, are inadequate for inverter-dominated grids characterized by high penetration of distributed energy resources and limited system inertia. This paper proposes a novel multi-layered black-start planning framework that explicitly incorporates the dynamic capabilities and operational constraints of grid-forming energy storage systems (GFESs). The approach formulates a multi-objective optimization problem solved via the Non-Dominated Sorting Genetic Algorithm III (NSGA-III), jointly minimizing total restoration time, voltage–frequency deviations, and maximizing early-stage load recovery. A graph-theoretic partitioning module identifies restoration subgrids based on topological cohesion, critical load density, and GFES proximity, enabling localized energization and autonomous island formation. Restoration path planning is embedded as a mixed-integer constraint layer, enforcing synchronization stability, surge current thresholds, voltage drop limits, and dispatch-dependent GFES constraints such as SoC evolution and droop-based frequency support. The model is evaluated on a modified IEEE 123-bus system with five distributed GFES units under multiple blackout scenarios. Simulation results show that the proposed method achieves up to 31% faster restoration and 46% higher voltage compliance compared to MILP and heuristic baselines, while maintaining strict adherence to dynamic safety constraints. The framework yields a diverse Pareto frontier of feasible restoration strategies and provides actionable insights into the coordination of distributed grid-forming resources for decentralized black-start planning. These results demonstrate that control-aware, partition-driven optimization is essential for scalable, safe, and fast restoration in the next generation of resilient power systems. Full article

Infrared imaging technology demonstrates significant advantages in aviation safety monitoring due to its exceptional all-weather operational capability and anti-interference characteristics, particularly in scenarios requiring real-time detection of aerial objects such as airport airspace management. However, traditional infrared target detection algorithms face critical challenges in complex sky backgrounds, including low signal-to-noise ratio (SNR), small target dimensions, and strong background clutter, leading to insufficient detection accuracy and reliability. To address these issues, this paper proposes the AFK-YOLO model based on the YOLO11 framework: it integrates an ADown downsampling module, which utilizes a dual-branch strategy combining average pooling and max pooling to effectively minimize feature information loss during spatial resolution reduction; introduces the KernelWarehouse dynamic convolution approach, which adopts kernel partitioning and a contrastive attention-based cross-layer shared kernel repository to address the challenge of linear parameter growth in conventional dynamic convolution methods; and establishes a feature decoupling pyramid network (FDPN) that replaces static feature pyramids with a dynamic multi-scale fusion architecture, utilizing parallel multi-granularity convolutions and an EMA attention mechanism to achieve adaptive feature enhancement. Experiments demonstrate that the AFK-YOLO model achieves 78.6% mAP on a self-constructed aerial infrared dataset—a 2.4 percentage point improvement over the baseline YOLO11—while meeting real-time requirements for aviation safety monitoring (416.7 FPS), reducing parameters by 6.9%, and compressing weight size by 21.8%. The results demonstrate the effectiveness of dynamic optimization methods in improving the accuracy and robustness of infrared target detection under complex aerial environments, thereby providing reliable technical support for the prevention of mid-air collisions. Full article

Multi-source topographic point clouds are of great value in applications such as mine monitoring, geological hazard assessment, and high-precision terrain modeling. However, challenges such as heterogeneous data sources, drastic terrain variations, and significant differences in point density severely hinder accurate registration. To address these issues, this study proposes a robust point cloud registration method named Cauchy-AdaV2, which integrates region-adaptive weighting with Cauchy-based residual suppression. The method jointly leverages slope and roughness to partition terrain into regions and constructs a spatially heterogeneous weighting function. Meanwhile, the Cauchy M-estimator is employed to mitigate the impact of outlier correspondences, enhancing registration accuracy while maintaining adequate correspondence coverage. The results indicate that the proposed method significantly outperforms traditional ICP, GICP, and NDT methods in terms of overall error metrics (MAE, RMSE), error control in complex terrain regions, and cross-sectional structural alignment. Specifically, it achieves a mean absolute error (MAE) of 0.0646 m and a root mean square error (RMSE) of 0.0688 m, which are 70.5% and 72.4% lower than those of ICP, respectively. These outcomes demonstrate that the proposed method possesses stronger spatial consistency and terrain adaptability. Ablation studies confirm the complementary benefits of regional and residual weighting, while efficiency analysis shows the method to be practically applicable in large-scale point cloud scenarios. This work provides an effective solution for high-precision registration of heterogeneous point clouds, especially in challenging environments characterized by complex terrain and strong disturbances. Full article

Accurate photovoltaic (PV) power output forecasting is critical for ensuring stable operation of modern power systems, yet it is constrained by high-dimensional redundancy in input weather data and the inherent heterogeneity of output scenarios. To address these challenges, this paper proposes a novel cascaded data-driven forecasting approach that enhances forecasting accuracy through systematically improving and optimizing the feature extraction, scenario clustering, and temporal modeling. Firstly, guided by weather data–PV power output correlations, the Deep Autoencoder (DAE) is enhanced by integrating Pearson Correlation Coefficient loss, reconstruction loss, and Kullback–Leibler divergence sparsity penalty into a multi-objective loss function to extract key weather factors. Secondly, the Fuzzy C-Means (FCM) algorithm is comprehensively refined through Mahalanobis distance-based sample similarity measurement, max–min dissimilarity principle for initial center selection, and Partition Entropy Index-driven optimal cluster determination to effectively cluster complex PV power output scenarios. Thirdly, a Long Short-Term Memory–Temporal Pattern Attention (LSTM–TPA) model is constructed. It utilizes the gating mechanism and TPA to capture time-dependent relationships between key weather factors and PV power output within each scenario, thereby heightening the sensitivity to key weather dynamics. Validation using actual data from distributed PV power plants demonstrates that: (1) The enhanced DAE eliminates redundant data while strengthening feature representation, thereby enabling extraction of key weather factors. (2) The enhanced FCM achieves marked improvements in both the Silhouette Coefficient and Calinski–Harabasz Index, consequently generating distinct typical output scenarios. (3) The constructed LSTM–TPA model adaptively adjusts the forecasting weights and obtains superior capability in capturing fine-grained temporal features. The proposed approach significantly outperforms conventional approaches (CNN–LSTM, ARIMA–LSTM), exhibiting the highest forecasting accuracy (97.986%), optimal evaluation metrics (such as Mean Absolute Error, etc.), and exceptional generalization capability. This novel cascaded data-driven model has achieved a comprehensive improvement in the accuracy and robustness of PV power output forecasting through step-by-step collaborative optimization. Full article

Road extraction from remote sensing imagery plays a critical role in applications such as autonomous driving, urban planning, and infrastructure development. Although deep learning methods have achieved notable progress, current approaches still struggle with complex backgrounds, varying road widths, and strong texture interference, often leading to fragmented road predictions or the misclassification of background regions. Given that roads typically exhibit smooth low-frequency characteristics while background clutter tends to manifest in mid- and high-frequency ranges, incorporating frequency-domain information can enhance the model’s structural perception and discrimination capabilities. To address these challenges, we propose a novel frequency-aware road extraction network, termed PWFNet, which combines frequency-domain modeling with multi-scale feature enhancement. PWFNet comprises two key modules. First, the Pyramidal Wavelet Convolution (PWC) module employs multi-scale wavelet decomposition fused with localized convolution to accurately capture road structures across various spatial resolutions. Second, the Frequency-aware Adjustment Module (FAM) partitions the Fourier spectrum into multiple frequency bands and incorporates a spatial attention mechanism to strengthen low-frequency road responses while suppressing mid- and high-frequency background noise. By integrating complementary modeling from both spatial and frequency domains, PWFNet significantly improves road continuity, edge clarity, and robustness under complex conditions. Experiments on the DeepGlobe and CHN6-CUG road datasets demonstrate that PWFNet achieves IoU improvements of 3.8% and 1.25% over the best-performing baseline methods, respectively. In addition, we conducted cross-region transfer experiments by directly applying the trained model to remote sensing images from different geographic regions and at varying resolutions to assess its generalization capability. The results demonstrate that PWFNet maintains the continuity of main and branch roads and preserves edge details in these transfer scenarios, effectively reducing false positives and missed detections. This further validates its practicality and robustness in diverse real-world environments. Full article

To ensure sustainable marine resource utilization, advanced monitoring methods are urgently needed to mitigate overfishing and ecological imbalances. Conventional fishing activity detection methods, including speed threshold-based approaches and Gaussian Mixture Models, often fail to accurately handle complex vessel trajectories, resulting in imprecise quantification of fishing effort and hindering effective monitoring of illegal, unreported, and unregulated (IUU) fishing activities. To address these limitations, we propose a spatiotemporal adaptive clustering and segmentation (STACS) framework for recognizing fishing activities. First, ST-DBSCAN clustering distinguishes concentrated fishing operations from transit movements. Second, an adaptive segmentation algorithm that incorporates heading stability and local density dynamically partitions trajectories into coherent segments, using spatiotemporal clusters as the basic units. Third, multiple features capturing temporal dynamics and spatial patterns are extracted to characterize fishing behaviors. Finally, an XGBoost classifier with run-length encoding post-processing converts point-level predictions to continuous fishing episodes. Experiments on fishing vessel trajectory datasets demonstrate that STACS outperforms conventional methods and advanced segmentation approaches, improving both point-level classification and segment-level coherence across diverse fishing scenarios. By enhancing IUU fishing detection and reducing classification inconsistencies, STACS provides valuable insights for marine conservation, policymaking, and fisheries management, bridging local behavioral dynamics with global trajectory analysis. Full article