Search Results (149)

Personalized federated learning (pFL) aims to address data heterogeneity by training client-specific models. However, it faces two critical challenges under few-shot conditions. First, existing methods often overlook the hierarchical structure of neural representations, limiting their ability to balance generalization and personalization. Second, recent approaches incorporate representation-level inductive biases that typically rely on rigid assumptions, such as fixed perturbation patterns or compact class clusters, making them vulnerable to distribution shifts in federated environments. To overcome these limitations, we propose pFedH2A, a novel hierarchical framework incorporating brain-inspired mechanisms, tailored for personalized federated learning in few-shot scenarios. First, we design a dual-branch hypernetwork (DHN) that employs two structurally distinct branches to generate aggregation weights. Each branch is biased toward capturing either low-level shared features or high-level personalized representations, enabling fine-grained personalization by mimicking the brain’s division of perceptual and representational processing. Second, we introduce a relation-aware module that learns an adaptive similarity function for each client, supporting few-shot classification by measuring whether a pair of samples belongs to the same class without relying on rigid prototype assumptions. Extensive experiments on public image classification datasets demonstrate that pFedH2A outperforms existing pFL baselines under few-shot scenarios, validating its effectiveness. Full article

The key components of spacecraft are typically present as circular or near-circular structures, and their precise and rapid extraction is essential for spacecraft attitude estimation. In response to the high precision and robust detection of ellipse components on space non-cooperative targets such as spacecraft docking rings, this paper proposes an efficient and robust ellipse detection method. This method first uses the arc-support line segment method to extract ellipse arc segments and then employs a hierarchical quadrant division strategy with a “coarse-to-fine” approach, integrating multiple constraints such as angle, quadrant, and relative position to combine arc segments and generate ellipse candidates. It uses a comprehensive score based on edge density, global coverage and local continuity to select the optimal ellipse from among the valid ellipses. Finally, a dynamic arc segment pruning method is introduced to dynamically remove relevant arcs from optimal ellipses, obtaining high-quality and non-redundant detection results. This method can achieve robust ellipse detection even when docking ring contours are partially obscured by shadows from robotic arms or nozzles. Full article

Fused polycyclic 1,7-naphthyridines are important N-heterocyclic scaffolds with potential applications in medicinal chemistry and materials science. Conventional methods for their synthesis often require harsh conditions or multiple steps, limiting functional group compatibility and scalability. Herein, we report a one-pot silver-catalyzed cyclization strategy that proceeds under mild conditions, tolerates diverse functional groups, and is amenable to gram-scale synthesis. The reaction features a simple workup involving celite filtration and standard purification. Preliminary studies indicate that these N-heterocycles exhibit promising photophysical and medicinal properties, highlighting their potential in light-emitting devices and therapeutic development. Full article

The bistatic radar has been widely applied in moving target detection and tracking due to its unique bistatic perspective, low power, and good concealment. With the growing demand for detecting remote and high-speed moving targets, two challenges inevitably arise in the bistatic radar. The first challenge is the range ambiguity and Doppler ambiguity caused by long-range and high-speed targets. The second challenge is the low signal-to-noise ratio (SNR) of the target caused by insufficient echo power. Addressing these challenges is essential for enhancing the performance of the bistatic radar. This paper proposes a robust two-step ambiguity resolution algorithm for detecting and tracking moving targets using a time-division multiple pulse repetition frequency (PRF) multiframe (TD-MPMF) under the bistatic radar. By exploring the coupling relationship between measurement data under different PRFs and frames, the data in a single frame is divided into multiple subframes to formulate a maximization problem, where each subframe corresponds to a specific PRF. Firstly, all possible state values of the measurement data in each subframe are listed based on the maximum unambiguous range and the maximum unambiguous Doppler. Secondly, a coarse threshold is applied based on prior knowledge of potential targets to filter out candidates. Thirdly, the sequence is transformed from the polar coordinate into the feature transform domain. Based on the linear relationship between the range and velocity of multiple PRFs with moving targets in the feature domain, the support vector machine (SVM) is used to classify the target measurements. By employing the SVM to determine the maximum margin hyperplane, the true target range and Doppler are derived, thereby enabling the generation of the target trajectory. Simulation results show better ambiguity resolution performance and more robust qualities than the traditional algorithm. An experiment using a TD-MPMF bistatic radar is conducted, successfully tracking an aircraft target. Full article

Employing commercial off-the-shelf coherent optical transmission components and methods to design a continuous variable quantum key distribution (CVQKD) system is a promising trend of achieving QKD with high security key rate (SKR) and cost-effectiveness. In this paper, we explore a CVQKD system based on the widely used polarization division multiplexed (PDM) coherent optical transmission structure and pilot-aided digital signal processing methods. A simplified pilot-aided phase noise compensation scheme based on frequency division multiplexing (FDM) is proposed, which introduces less total excess noise than classical pilot-aided schemes based on time division multiplexing (TDM). In addition, the two schemes of training symbol (TS)-aided equalization are compared to find the optimal strategy for TS insertion, where the scheme based on block insertion strategy can provide the SKR gain of around 29%, 22%, and 15% compared with the scheme based on fine-grained insertion strategy at the transmission distance of 5 km, 25 km, and 50 km, respectively. The joint optimization of pilot-aided and TS-aided methods in this work can provide a reference for achieving a CVQKD system with a high SKR and low complexity in metropolitan-scale applications. Full article

Grain shape is a critical determinant of rice yield, quality, and market value. Recent advances in molecular biology, genomics, and systems biology have revealed a complex regulatory network governing grain development, integrating genetic loci, plant hormone signaling, transcriptional regulation, protein ubiquitination, epigenetic modifications, and environmental cues. This review summarizes key genetic components such as QTLs, transcription factors, and hormone pathways—including auxin, cytokinin, gibberellin, brassinosteroids, and abscisic acid—that influence seed size through regulation of cell division, expansion, and nutrient allocation. The roles of the ubiquitin–proteasome system, miRNAs, lncRNAs, and chromatin remodeling are also discussed, highlighting their importance in fine-tuning grain development. Furthermore, we examine environmental factors that impact grain filling and size, including temperature, light, and nutrient availability. We also explore cutting-edge breeding strategies such as gene editing, functional marker development, and wild germplasm utilization, along with the integration of multi-omics platforms like RiceAtlas to enable intelligent and ecological zone-specific precision breeding. Finally, challenges such as pleiotropy and non-additive gene interactions are discussed, and future directions are proposed to enhance grain shape improvement for yield stability and food security. Full article

With the widespread deployment of 5G technology, high-precision positioning in global navigation satellite system (GNSS)-denied environments is a critical yet challenging task for emerging 5G applications, enabling enhanced spatial resolution, real-time data acquisition, and more accurate geolocation services. Traditional methods relying on single-source measurements like received signal strength information (RSSI) or time of arrival (TOA) often fail in complex multipath conditions. To address this, the positional encoding multi-scale residual network (PE-MSRN) is proposed, a novel deep learning framework that enhances positioning accuracy by deeply mining spatial information from 5G channel state information (CSI). By designing spatial sampling with multigranular data and utilizing multi-source information in 5G CSI, a dataset covering a variety of positioning scenarios is proposed. The core of PE-MSRN is a multi-scale residual network (MSRN) augmented by a positional encoding (PE) mechanism. The positional encoding transforms raw angle of arrival (AOA) data into rich spatial features, which are then mapped into a 2D image, allowing the MSRN to effectively capture both fine-grained local patterns and large-scale spatial dependencies. Subsequently, the PE-MSRN algorithm that integrates ResNet residual networks and multi-scale feature extraction mechanisms is designed and compared with the baseline convolutional neural network (CNN) and other comparison methods. Extensive evaluations across various simulated scenarios, including indoor autonomous driving and smart factory tool tracking, demonstrate the superiority of our approach. Notably, PE-MSRN achieves a positioning accuracy of up to 20 cm, significantly outperforming baseline CNNs and other neural network algorithms in both accuracy and convergence speed, particularly under real measurement conditions with higher SNR and fine-grained grid division. Our work provides a robust and effective solution for developing high-fidelity 5G positioning systems. Full article

The increasing frequency and severity of forest fires, driven by climate change and intensified human activities, pose substantial threats to ecological security and sustainable development. However, most assessments remain centered on occurrence risk, lack a resilience-oriented perspective and comprehensive indicator systems, and therefore offer limited guidance for building system resilience. This study developed a forest fire resilience (FFR) assessment framework with 25 indicators in three levels and six domains across four resilience dimensions. Balancing expert judgment and data, we obtained indicator weights by integrating the Analytic Hierarchy Process (AHP) and the Criteria Importance Through Intercriteria Correlation (CRITIC) via a game-theoretic scheme. The analysis revealed that, among the level-2 indicators, climate factors, infrastructure, and vegetation characteristics exert the greatest influence on FFR. At the level-3 indicator scale, monthly minimum relative humidity, fine fuel load per unit area, and the deployment of smart monitoring systems were critical. Among the four resilience dimensions, absorption capacity plays the predominant role in shaping disaster response. Building on these findings, the study proposes targeted strategies to enhance FFR and applies the assessment framework to twelve administrative divisions of Baise City, China, highlighting marked spatial variability in resilience levels. The results offer valuable theoretical insights and practical guidance for strengthening FFR. Full article

Regarding the impact of hull roughness on ship resistance and propulsive performance, most existing studies rely heavily on numerical hulls or simplified models, while systematic analysis focusing on the heterogeneous roughness of actual ships remains insufficient. Taking the 2433 TEU container ship SITC CAGAYAN as the research object, this study adopts a method that combines CFD numerical simulation with actual ship operation data. It employs a resistance prediction model based on the “roughness influence factor” to explore the mechanism by which local roughness affects ship resistance. Meanwhile, this study innovatively proposes the index of “fuel consumption increment per unit wetted surface area” and the concept of “fuel consumption factor,” thereby realizing the quantitative characterization of the impact of local rough areas on fuel consumption. The purpose of this study is to provide theoretical support and technical pathways for the optimization of ship energy efficiency and the development of green shipping. Full article

Micro-pulse photon-counting LiDAR has difficulty accurately extracting geophysical information in strong-noise environments, with solar noise interference being a key limiting factor. This study proposes a hierarchical coarse-to-fine denoising framework, combining grid-based pre-filtering with an optimized horizontal and vertical recursive division method using Otsu’s method to achieve high time efficiency and denoising accuracy. First, an adaptive meshing strategy is employed to remove most of the noise in the data while retaining more than 99.1% of the signal. Subsequently, an alternating horizontal and vertical recursive division algorithm with automatically selected parameters is applied for denoising; the method was validated on ICESat-2 ATL03 data, GlobeLand30 V2020 data, and USGS 3DEP airborne radar data, where the method achieved a classification accuracy of more than 91.2%, with a several-fold reduction in runtime compared to traditional clustering methods. The framework demonstrates high efficiency, robustness, and computational scalability across diverse terrains, including polar, forest, and plains. It can contribute to geographic mapping, environmental protection, and ecological monitoring. Full article

Recent approaches to geo-referencing X posts have focused on the use of language modelling techniques that learn geographic region-specific language and use this to infer geographic coordinates from text. These approaches rely on large amounts of labelled data to build accurate predictive models. However, obtaining significant volumes of geo-referenced data from Twitter, recently renamed X, can be difficult. Further, existing language modelling approaches can require the division of a given area into a grid or set of clusters, which can be dataset-specific and challenging for location prediction at a fine-grained level. Regression-based approaches in combination with deep learning address some of these challenges as they can assign coordinates directly without the need for clustering or grid-based methods. However, such approaches have received only limited attention for the geo-referencing task. In this paper, we adapt state-of-the-art neural network models for the regression task, focusing on geo-referencing wildlife Tweets where there is a limited amount of data. We experiment with different transfer learning techniques for improving the performance of the regression models, and we also compare our approach to recently developed Large Language Models and prompting techniques. We show that using a location names extraction method in combination with regression-based disambiguation, and purely regression when names are absent, leads to significant improvements in locational accuracy over using only regression. Full article

The Elfeija Dune Field (EDF) is a continental aeolian system in an arid region of southeastern Morocco. Studying this system is critical for understanding the effects of mounting climatic and anthropogenic pressures. This study provides a comprehensive characterization of the EDF’s morphology, sedimentology, aeolian dynamics, genesis, and recent evolution. A multi-scale, multidisciplinary approach was adopted, integrating field observations, sedimentological analyses, MERRA-2 reanalysis wind data, cartographic analysis, digital terrain modeling, and morphometric measurements. The results reveal an active 30 km² dune field, elongated WSW-ENE, which is divisible into three morphodynamic zones with a high dune density (80–90 dunes/km²). The wind regime is predominantly from the W to WSW, driving a net ENE sand transport and creating conditions conducive to barchan formation (RDP/DP > 0.78). Sediments are quartz dominated, with significant calcite and various clay minerals (illite, kaolinite, and smectite). Dune sands are primarily fine- to medium-grained and well sorted, in contrast to the more poorly sorted interdune deposits. The landscape is dominated by barchans (mean height H = 2.5 m; mean length L = 50 m) and their coalescent forms, indicating sustained aeolian activity. The potential sand flux was estimated at 1.7 kg/m/s, with a dune collision probability of 32%. The field’s genesis is hypothesized to be controlled by a topographically induced Venturi effect, with an initiation approximately 1000 years ago, potentially linked to the Medieval Climatic Optimum. Significant anthropogenic impacts from expanding irrigated agriculture are observed at the dune field margins. By providing a detailed characterization of the EDF and its sensitivity to natural and anthropogenic forcings, this study establishes a critical baseline for the sustainable management of arid environments. Full article

Deep learning (DL), as a cutting-edge technology in artificial intelligence, has significantly impacted fields such as computer vision and natural language processing. Loss function determines the convergence speed and accuracy of the DL model and has a crucial impact on algorithm quality and model performance. However, most of the existing studies focus on the improvement of specific problems of loss function, which lack a systematic summary and comparison, especially in computer vision and natural language processing tasks. Therefore, this paper reclassifies and summarizes the loss functions in DL and proposes a new category of metric loss. Furthermore, this paper conducts a fine-grained division of regression loss, classification loss, and metric loss, elaborating on the existing problems and improvements. Finally, the new trend of compound loss and generative loss is anticipated. The proposed paper provides a new perspective for loss function division and a systematic reference for researchers in the DL field. Full article

Brassinosteroids (BRs) are steroid hormones that are essential for plant growth, development, and environmental adaptation. They control the division, elongation, and differentiation of various cell types throughout the entire plant life cycle, affecting growth and the stress response. Therefore, fine-tuning of BR biosynthesis and modulation of signaling pathways offer possibilities for developing cultivars characterized by adjusted plant architecture or improved stress tolerance to benefit crop production. Additionally, precise BR treatments can be employed to increase the productivity of crop plants. This review aims to provide a comprehensive summary of the genetic basis of traits related to BR metabolism and signaling in cucurbits, the second largest vegetable family, which contributes significantly to global vegetable production and nutritional security. We summarize the current knowledge concerning BR biosynthesis mutants, the role of BRs in stress mitigation, and the potential of the exogenous application of BRs to alleviate stress during cucurbit production. We also discuss how genes related to BR metabolism can be used to develop gene editing strategies to advance precision breeding in cucurbits. Full article

Accurate and automated detection and tracking of cells in microscopy images is a persistent challenge in biotechnology and biomedical research. Effective detection and tracking are crucial for understanding biological processes and extracting meaningful data for subsequent simulations. In this study, we present an integrated pipeline that leverages a fine-tuned YOLOv8x model for detecting cells and cell divisions across microscopy image series. While YOLOv8x exhibits strong detection capabilities, it occasionally misses certain cells, leading to gaps in data. To mitigate this, we incorporate the DeepSORT tracking algorithm, which enhances data association and reduces the cells’ identity (ID) switches by utilizing a pre-trained convolutional network for robust multi-object tracking. This combination ensures continuous detection and compensates for missed detections, thereby improving overall recall. Our approach achieves a recall of 93.21% with the enhanced DeepSORT algorithm, compared to the 53.47% recall obtained by the original YOLOv8x model. The proposed pipeline effectively extracts detailed information from structured image datasets, providing a reliable approximation of cellular processes in culture environments. Full article