Search Results (564)

Aircraft trajectory prediction (ATP) is a critical technology for air traffic control (ATC), safeguarding aviation safety and airspace resource management. To address the limitations of existing methods—kinetic models’ susceptibility to environmental disturbances and machine learning’s lack of physical interpretability—this paper proposes a Spatial–Temporal Physics-Constrained Multilayer Perceptron (STPC-MLP) model. The model employs a spatiotemporal attention encoder to decouple timestamps and spatial coordinates (longitude, latitude, altitude), eliminating feature ambiguity caused by mixed representations. By fusing temporal and spatial attention features, it effectively extracts trajectory degradation patterns. Furthermore, a Hidden Physics-Constrained Multilayer Perceptron (HPC-MLP) integrates kinematic equations (e.g., maximum acceleration and minimum turning radius constraints) as physical regularization terms in the loss function, ensuring predictions strictly adhere to aircraft maneuvering principles. Experiments demonstrate that STPC-MLP reduces the trajectory point prediction error (RMSE) by 7.13% compared to a conventional optimal Informer model. In ablation studies, the absence of the HPC-MLP module, attention mechanism, and physical constraint loss terms significantly increased prediction errors, unequivocally validating the efficacy of the STPC-MLP architecture for trajectory prediction. Full article

Pesticide usage in the integrated rice–crayfish system has aroused lots of attention all over the world. Especially in China, fish farmers often use copper sulfate and pendimethalin to remove moss from aquaculture water and glyphosate to remove weeds in and around crayfish–crab mixed culture ponds. To explore the stress response mechanism of CuSO₄, pendimethalin, and glyphosate to the hepatopancreas of Procambarus clarkii (Girard, 1852), seven treatment groups including control, CuSO₄ (1 and 2 mg·L⁻¹), pendimethalin (PND, 5 and 10 μg·L⁻¹), and glyphosate (5 and 10 μg·L⁻¹) experimental groups were set up; the transcriptome responses were detected at 4, 8, and 12 days, respectively. The irregular structure and vacuoles were shown in the hepatopancreas for 2 mg·L⁻¹ CuSO₄ and 10 μg·L⁻¹ glyphosate exposures at 12 d, while narrowed hepatic sinusoids were revealed after 10 μg·L⁻¹ pendimethalin exposure. The pathways of ribosome, lysosome, and peroxisome were significantly enriched for differential expression genes (DEGs); in addition, tyrosine metabolism, starch, and sucrose metabolism were enriched under the stress of the three inputs. Genes in related pathways such as glycerophospholipid metabolism, oxidative phosphorylation, and glycerolipid metabolism also changed, and the expression of genes associated with oxidative phosphorylation changed significantly under the stress of the three inputs. Oxidative stress, neurotoxicity, metabolism, and energy supply have been significantly affected by the above herbicide exposure. High concentrations and/or long-term duration exposure may result in metabolic disorders rather than eliminate toxicity through adaptability responses. Full article

Personalized image generation has gained significant attention with the advancement of text-to-image diffusion models. However, existing methods face challenges in effectively mixing multiple visual attributes, such as structure and appearance, from separate reference images. Finetuning-based methods are time-consuming and prone to overfitting, while finetuning-free approaches often suffer from feature entanglement, leading to distortions. To address these challenges, we propose FreeMix, a finetuning-free approach for multi-concept mixing in personalized image generation. Given separate references for structure and appearance, FreeMix generates a new image that integrates both. This is achieved through Disentangle-Mixing Self-Attention (DMSA). DMSA first disentangles the two concepts by applying spatial normalization to remove residual appearance from structure features, and then selectively injects appearance details via self-attention, guided by a cross-attention-derived mask to prevent background leakage. This mechanism ensures precise structural preservation and faithful appearance transfer. Extensive qualitative and quantitative experiments demonstrate that our method achieves superior structural consistency and appearance transfer compared to existing approaches. In addition to personalization, FreeMix can be adapted to exemplar-based image editing. Full article

In recent years, hybrid models that integrate Convolutional Neural Networks (CNNs) with Vision Transformers (ViTs) have achieved significant improvements in hyperspectral image classification (HSIC). Nevertheless, their complex architectures often lead to computational redundancy and inefficient feature fusion, particularly struggling to balance global modeling and local detail extraction in high-dimensional spectral data. To solve these issues, this paper proposes a Spectral-Cube Gated Harmony Network (SCGHN) that achieves efficient spectral–spatial joint feature modeling through a dynamic gating mechanism and hierarchical feature decoupling strategy. There are three primary innovative contributions of this paper as follows: Firstly, we design a Spectral Cooperative Parallel Convolution (SCPC) module that combines dynamic gating in the spectral dimension and spatial deformable convolution. This module adopts a dual-path parallel architecture that adaptively enhances key bands and captures local textures, thereby significantly improving feature discriminability at mixed ground object boundaries. Secondly, we propose a Dual-Gated Fusion (DGF) module that achieves cross-scale contextual complementarity through group convolution and lightweight attention, thereby enhancing hierarchical semantic representations with significantly lower computational complexity. Finally, by means of the coordinated design of 3D convolution and lightweight classification decision blocks, we construct an end-to-end lightweight framework that effectively alleviates the structural redundancy issues of traditional hybrid models. Extensive experiments on three standard hyperspectral datasets reveal that our SCGHN requires fewer parameters and exhibits lower computational complexity as compared with some existing HSIC methods. Full article

In recent years, the research trend of HSI classification has focused on the innovative integration of deep learning and Transformer architecture to enhance classification performance through multi-scale feature extraction, attention mechanism optimization, and spectral–spatial collaborative modeling. However, due to the excessive computational complexity and the large number of parameters of the Transformer, there is an expansion bottleneck in long sequence tasks, and the collaborative optimization of the algorithm and hardware is required. To better handle this issue, our paper proposes a method which integrates RWKV linear attention with Transformer through a novel TC-Former framework, combining TimeMixFormer and HyperMixFormer architectures. Specifically, TimeMixFormer has optimized the computational complexity through time decay weights and gating design, significantly improving the processing efficiency of long sequences and reducing the computational complexity. HyperMixFormer employs a gated WKV mechanism and dynamic channel weighting, combined with Mish activation and time-shift operations, to optimize computational overhead while achieving efficient cross-channel interaction, significantly enhancing the discriminative representation of spectral features. The pivotal characteristic of the proposed method lies in its innovative integration of linear attention mechanisms, which enhance HSI classification accuracy while achieving lower computational complexity. Evaluation experiments on three public hyperspectral datasets confirm that this framework outperforms the previous state-of-the-art algorithms in classification accuracy. Full article

Existing fault diagnosis methods assume the identical distribution of training and test data, failing to adapt to source–target domain differences in industrial scenarios and limiting generalization. They also struggle to explore inter-domain correlations with scarce labeled target samples, leading to poor convergence and generalization. To address this, our paper proposes a cross-domain few-shot intelligent fault diagnosis method based on Mixup data augmentation. Firstly, a Mixup data augmentation method is used to linearly combine source domain and target domain data in a specific proportion to generate mixed-domain data, enabling the model to learn correlations and features between data from different domains and improving its generalization ability in cross-domain few-shot learning tasks. Secondly, a feature decoupling module based on the self-attention mechanism is proposed to extract domain-independent features and domain-related features, allowing the model to further reduce the domain distribution gap and effectively generalize source domain knowledge to the target domain. Then, the model parameters are optimized through a multi-task learning mechanism consisting of sample classification tasks and domain classification tasks. Finally, applications in classification tasks on multiple sets of equipment fault datasets show that the proposed method can significantly improve the fault recognition ability of the diagnosis model under the conditions of large distribution differences in the target domain and scarce labeled samples. Full article

Mechanochemical methods have received much attention in the synthesis and design of all-solid-state battery materials in recent years due to their advantages of being green, efficient, easy to operate, and solvent-free. In this review, common mechanochemical methods, including high-energy ball milling, twin-screw extrusion (TSE), and resonant acoustic mixing (RAM), are introduced with the aim of providing a fundamental understanding of the subsequent material design. Subsequently, the discussion focuses on the application of mechanochemical methods in the construction of solid-state electrolytes, anode materials, and cathode materials, especially the research progress of mechanical energy-induced polymerization strategies in building flexible composite electrolytes and enhancing interfacial stability. Through the analysis of representative work, it is demonstrated that mechanochemical methods are gradually evolving from traditional physical processing tools to functional synthesis platforms with chemical reaction capabilities. This review systematically organizes its development and research trends in the field of all-solid-state battery materials and explores potential future breakthrough directions. Full article

With the increasing global demand for sustainable building materials, coal gangue, as a potential supplementary cementitious material (SCM), has attracted widespread attention. Coal gangue is primarily composed of clay minerals, among which the kaolinite content can significantly enhance its cementitious properties after activation. However, there are various grades of coal gangues, which restrain their application, especially for the low kaolinite content coal gangue. This paper investigates the feasibility of using iron-rich coal gangue with low kaolinite content as a cement substitute through high-temperature activation treatment. In the current study, activated coal gangue replaced cement clinker at proportions of 10%, 15%, and 20%, which was further mixed with limestone powder to form a new cementitious material system. The mechanical attributes of the systems were assessed using compressive strength and microhardness tests. The influence of hydration products and microstructural changes on system performance was further explored through electrochemical impedance spectroscopy (EIS) and quantitative X-ray diffraction (XRD) analysis. The findings suggest that a well-balanced addition of coal gangue can effectively substitute for cement clinker, thereby enhancing both the mechanical properties and microstructure of the systems. These results demonstrate that through appropriate activation treatments, coal gangue can be utilized as an effective SCM. While traditional SCMs like fly ash (FA) and ground granulated blast-furnace slag (GGBFS) have near-zero allocated carbon footprints, their global supply is diminishing and increasingly unreliable. In contrast, our approach valorizes a vast industrial waste stream, aligning with circular economy principles and offering a scalable, sustainable, and low-carbon alternative for the construction industry. Full article

High-entropy alloy (HEA) catalysts have attracted significant attention from researchers. In many cases, HEAs exhibit high activity and selectivity for catalytic reactions due to four “core effects”: high entropy effect, lattice distortion effect, slow diffusion effect, and mixing effect. However, a systematic summary of HEA catalyst design and understanding is lacking. In this review, the reasons for the outstanding performance of HEA catalysts are first discussed from multiple perspectives, such as excellent mechanical properties, ultra-high-performance stability, and the potential for compositional optimization. Furthermore, to deepen our understanding of HEA catalysts, the rational design of HEA catalysts is introduced, covering design principles, element selection, and the use of algorithms for prediction. Next, several common preparation methods for HEAs are introduced, including chemical co-reduction, solution combustion, mechanical alloying, and sol–gel methods. Finally, the research progress of HEA catalysts in hydrogen evolution reactions, oxygen evolution reactions, and oxygen reduction reactions is presented. Unlike existing reviews, this work establishes a unified framework connecting HEA fundamentals (entropy effects), computational design, scalable synthesis, and application-specific performance, while identifying underexplored pathways like lattice-oxygen-mediated mechanisms (LOM) for future research. Full article

Despite extensive research on green consumption, consumer purchase intentions for bamboo products under China’s “replacing plastic with bamboo” policy remain underexplored, given growing plastic pollution concerns. Research remains focused on established green products (e.g., green agriculture, energy-efficient appliances, new energy vehicles), overlooking consumer behavior and cognition toward emerging bamboo alternatives. This study employs eye-tracking technology to examine purchase intentions and visual attention allocation mechanisms for bamboo versus plastic products, analyzing the role of green consumption values (GCVs). Using a 2 (material: bamboo/plastic) × 2 (GCVs: high/low) mixed design, we recorded fixation duration, fixation count, and heatmaps from 70 participants. Behavioral results revealed significantly higher purchase intention for bamboo products, particularly among high-GCV consumers. Eye-tracking data showed greater visual attention (fixation duration/count) to bamboo products, with high-GCV participants exhibiting significantly stronger attentional bias toward bamboo. Findings demonstrate that bamboo’s eco-friendly attributes enhance both purchase intention and visual attention allocation, validating material salience in green decision-making. High GCVs strengthen automatic attentional bias toward sustainable materials, reinforcing purchase inclinations. This research provides empirical support for VBN theory at the cognitive level and offers policy-relevant insights for promoting “Bamboo Instead of Plastic” initiatives. Full article

The precise mapping of rock joint traces is fundamental to the design and safety assessment of foundations, retaining structures, and underground cavities in building and civil engineering. Existing deep learning approaches either impose prohibitive computational demands for on-site deployment or disrupt the topological continuity of subpixel lineaments that govern rock mass behavior. This study presents BATNet-Lite, a lightweight encoder–decoder architecture optimized for joint segmentation on resource-constrained devices. The encoder introduces a Boundary-Aware Token-Mixing (BATM) block that separates feature maps into patch tokens and directionally pooled stripe tokens, and a bidirectional attention mechanism subsequently transfers global context to local descriptors while refining stripe features, thereby capturing long-range connectivity with negligible overhead. A complementary Multi-Scale Line Enhancement (MLE) module combines depth-wise dilated and deformable convolutions to yield scale-invariant responses to joints of varying apertures. In the decoder, a Skeletal-Contrastive Decoder (SCD) employs dual heads to predict segmentation and skeleton maps simultaneously, while an InfoNCE-based contrastive loss enforces their topological consistency without requiring explicit skeleton labels. Training leverages a composite focal Tversky and edge IoU loss under a curriculum-thinning schedule, improving edge adherence and continuity. Ablation experiments confirm that BATM, MLE, and SCD each contribute substantial gains in boundary accuracy and connectivity preservation. By delivering topology-preserving joint maps with small parameters, BATNet-Lite facilitates rapid geological data acquisition for tunnel face mapping, slope inspection, and subsurface digital twin development, thereby supporting safer and more efficient building and underground engineering practice. Full article

Background: Autoimmune diseases and other immune-mediated disorders are associated with an increased risk of malignancy, influenced by chronic inflammation, immune dysregulation, and treatment-related factors. Clarifying cancer risk patterns across specific conditions is essential to improve clinical vigilance and inform screening practices. Objective: The aim of this study was to synthesise current evidence on the association between autoimmune and immune-mediated diseases and cancer, with a focus on practical implications for clinicians. Methods: Recent cohort studies, meta-analyses, and expert consensus documents were analysed to describe cancer epidemiology, pathogenic mechanisms, high-risk phenotypes, and treatment considerations across major autoimmune diseases and other immune-mediated conditions. The review covers idiopathic inflammatory myopathies, Sjögren’s syndrome, systemic sclerosis, systemic lupus erythematosus, rheumatoid arthritis, antiphospholipid syndrome, ANCA-associated vasculitis, giant cell arteritis, polymyalgia rheumatica, sarcoidosis, mixed connective tissue disease, IgG4-related disease, VEXAS syndrome, and eosinophilic fasciitis. Special attention was given to identifying warning features for underlying malignancy and evaluating cancer screening strategies. Results: The magnitude and distribution of cancer risk vary across diseases. In some conditions such as dermatomyositis, systemic sclerosis or Sjögren’s syndrome, increased risk is well established, particularly for haematological and certain solid tumours. However, tumour patterns may differ across populations, and findings are not always consistent. Distinct clinical and serological features help stratify individual cancer risk and may guide the intensity of screening. The first years after disease onset often represent a window of higher vulnerability, during which intensified surveillance may be warranted in selected patients. Conclusions: Cancer risk in autoimmune diseases should be assessed on an individual basis. Awareness of disease-specific risk factors and clinical warning signs supports early recognition of malignancy and informs screening decisions in routine practice. Full article

Permian shale gas is a kind of energy resource with commercial development potential. The characteristics of its organic source and enrichment have received extensive attention in recent years. This study systematically analyzed the variations in types and assemblages of hydrocarbon-forming organisms across different stratigraphic layers of Permian shale in western Hubei through scanning electron microscopy (SEM) and microscopic observations. Moreover, the source characteristics and enrichment mechanisms of organic matter in Permian shale were identified. Hydrocarbon generation in Permian shale is primarily attributed to planktonic algae-derived acritarchs, supplemented by higher plants and green algae, based on the observation under the SEM and microscope. The hydrocarbon-forming microorganisms in the Gufeng Formation are predominantly characterized by acritarchs. A notable decrease in acritarch content is observed at the bottom of the Wujiaping Formation, accompanied by a significant increase in higher plant constituents and a slight rise in green algae abundance. Subsequently, from the middle-upper members of the Wujiaping Formation through the Dalong Formation, acritarch concentrations rebound while higher plants and green algae contributions diminish. The organic matter in the studied layer is predominantly generated from planktonic algae (acritarchs and green algae), with subordinate contributions from terrestrial higher plants. During the sedimentary stage of the Gufeng Formation, rising sea levels sustained a deep siliceous shelf environment in the E’xi Trough, where organic matter was primarily sourced from acritarchs, with limited terrigenous input. The regressive phase at the bottom of the Wujiaping Formation resulted in coastal marsh throughout the E’xi Trough, creating a mixed organic matter assemblage of aquatic planktonic algae and enhanced terrestrial higher plant material. As sedimentation progressed into the middle-upper Wujiaping Formation and Dalong Formation, the E’xi Trough evolved into a deep siliceous shelf and platform-margin slope environment. During this stage, organic matter was again predominantly supplied by planktonic algae (mainly acritarchs), with reduced terrestrial organic input. These findings provide valuable theoretical insights for guiding Permian shale gas exploration and development strategies. Full article

Green hydrogen is gaining global attention as a zero-carbon energy carrier with the potential to drive sustainable energy transitions, particularly in regions facing rising fossil fuel costs and resource depletion. In sub-Saharan Africa, financing mechanisms and structured off-take agreements are critical to attracting investment across the green hydrogen value chain, from advisory and pilot stages to full-scale deployment. While substantial funding is required to support a green economic transition, success will depend on the effective mobilization of capital through smart public policies and innovative financial instruments. This review evaluates financing mechanisms relevant to sub-Saharan Africa, including green bonds, public–private partnerships, foreign direct investment, venture capital, grants and loans, multilateral and bilateral funding, and government subsidies. Despite their potential, current capital flows remain insufficient and must be significantly scaled up to meet green energy transition targets. This study employs a mixed-methods approach, drawing on primary data from utility firms under the H₂Atlas-Africa project and secondary data from international organizations and the peer-reviewed literature. The analysis identifies that transitioning toward Net-Zero emissions economies through hydrogen development in sub-Saharan Africa presents both significant opportunities and measurable risks. Specifically, the results indicate an estimated investment risk factor of 35%, reflecting potential challenges such as financing, infrastructure, and policy readiness. Nevertheless, the findings underscore that green hydrogen is a viable alternative to fossil fuels in sub-Saharan Africa, particularly if supported by targeted financing strategies and robust policy frameworks. This study offers practical insights for policymakers, financial institutions, and development partners seeking to structure bankable projects and accelerate green hydrogen adoption across the region. Full article

Mobile traffic classification serves as a fundamental component in network security systems. In recent years, pre-training methods have significantly advanced this field. However, as mobile traffic is typically mixed with third-party services, the deep integration of such shared services results in highly similar TCP flow characteristics across different applications. This makes it challenging for existing traffic classification methods to effectively identify mobile traffic. To address the challenge, we propose MS-PreTE, a two-phase pre-training framework for mobile traffic classification. MS-PreTE introduces a novel multi-level representation model to preserve traffic information from diverse perspectives and hierarchical levels. Furthermore, MS-PreTE incorporates a focal-attention mechanism to enhance the model’s capability in discerning subtle differences among similar traffic flows. Evaluations demonstrate that MS-PreTE achieves state-of-the-art performance on three mobile application datasets, boosting the F1 score for Cross-platform (iOS) to 99.34% (up by 2.1%), Cross-platform (Android) to 98.61% (up by 1.6%), and NUDT-Mobile-Traffic to 87.70% (up by 2.47%). Moreover, MS-PreTE exhibits strong generalization capabilities across four real-world traffic datasets. Full article