Search Results (8,120)

In tool wear monitoring, the efficient fusion of multi-source sensor signals poses significant challenges due to their inherent heterogeneous characteristics. In this paper, we propose a Multi-Sensor Multi-Domain feature fusion Transformer (MSMDT) model that achieves precise tool wear prediction through innovative feature engineering and cross-modal self-attention mechanisms. Specifically, we first develop a physics-aware feature extraction framework, where time-domain statistical features, frequency-domain energy features, and wavelet packet time–frequency features are systematically extracted for each sensor type. This approach constructs a unified feature matrix that effectively integrates the complementary characteristics of heterogeneous signals while preserving discriminative tool wear signatures. Then, a position-embedding-free Transformer architecture is constructed, which enables adaptive cross-domain feature fusion through joint global context modeling and local feature interaction analysis to predict tool wear values. Experimental results on the PHM2010 demonstrate the superior performance of MSMDT, outperforming state-of-the-art methods in prediction accuracy. Full article

Retinal vessel segmentation in fundus images is critical for diagnosing microvascular and ophthalmologic diseases. However, the task remains challenging due to significant vessel width variation and low vessel-to-background contrast. To address these limitations, we propose WDM-UNet, a novel spatial-wavelet dual-domain fusion architecture that integrates spatial and wavelet-domain representations to simultaneously enhance the local detail and global context. The encoder combines a Deformable Convolution Encoder (DCE), which adaptively models complex vascular structures through dynamic receptive fields, and a Wavelet Convolution Encoder (WCE), which captures the semantic and structural contexts through low-frequency components and hierarchical wavelet convolution. These features are further refined by a Gated Fusion Transformer (GFT), which employs gated attention to enhance multi-scale feature integration. In the decoder, depthwise separable convolutions are used to reduce the computational overhead without compromising the representational capacity. To preserve fine structural details and facilitate contextual information flow across layers, the model incorporates skip connections with a hierarchical fusion strategy, enabling the effective integration of shallow and deep features. We evaluated WDM-UNet in three public datasets: DRIVE, STARE, and CHASE_DB1. The quantitative evaluations demonstrate that WDM-UNet consistently outperforms state-of-the-art methods, achieving 96.92% accuracy, 83.61% sensitivity, and an 82.87% F1-score in the DRIVE dataset, with superior performance across all the benchmark datasets in both segmentation accuracy and robustness, particularly in complex vascular scenarios. Full article

Efficient task offloading for delay-sensitive applications, such as autonomous driving, presents a significant challenge in multi-hop Vehicular Edge Computing (VEC) networks, primarily due to high vehicle mobility, dynamic network topologies, and complex end-to-end congestion problems. To address these issues, this paper proposes a graph attention-based reinforcement learning algorithm, named GAPO. The algorithm models the dynamic VEC network as an attributed graph and utilizes a graph neural network (GNN) to learn a network state representation that captures the global topological structure and node contextual information. Building on this foundation, an attention-based Actor–Critic framework makes joint offloading decisions by intelligently selecting the optimal destination and collaboratively determining the ratios for offloading and resource allocation. A multi-objective reward function, designed to minimize task latency and to alleviate link congestion, guides the entire learning process. Comprehensive simulation experiments and ablation studies show that, compared to traditional heuristic algorithms and standard deep reinforcement learning methods, GAPO significantly reduces average task completion latency and substantially decreases backbone link congestion. In conclusion, by deeply integrating the state-aware capabilities of GNNs with the decision-making abilities of DRL, GAPO provides an efficient, adaptive, and congestion-aware solution to the resource management problems in dynamic VEC environments. Full article

Under the global context of climate governance and sustainable development, low-carbon energy transition has become a strategic imperative. As a critical force in resource allocation, the financial system’s impact on energy transition has attracted extensive academic attention. This paper presents the first comprehensive literature review on energy transition research in the context of financial development. We develop a “Financial Functions-Energy Transition Dynamics” analytical framework to comprehensively examine the theoretical and empirical evidence regarding the relationship between financial development (covering both traditional finance and emerging finance) and energy transition. The understanding of financial development’s impact on energy transition has progressed from linear to nonlinear perspectives. Early research identified a simple linear promoting effect, whereas current studies reveal distinctly nonlinear and multidimensional effects, dynamically driven by three fundamental factors: economy, technology, and resources. Emerging finance has become a crucial driver of transition through technological innovation, risk diversification, and improved capital allocation efficiency. Notable disagreements persist in the existing literature on conceptual frameworks, measurement approaches, and empirical findings. By synthesizing cutting-edge empirical evidence, we identify three critical future research directions: (1) dynamic coupling mechanisms, (2) heterogeneity of financial instruments, and (3) stage-dependent evolutionary pathways. Our study provides a theoretical foundation for understanding the complex finance-energy transition relationship and informs policy-making and interdisciplinary research. Full article

The increasing depletion of high-grade nickel sulfide deposits and the growing demand for nickel have intensified global interest in oxidized nickel ores (ONOs), particularly those located in Kazakhstan. This study presents a comprehensive review of the mineralogical and chemical characteristics of ONOs from the Shevchenkovskoye cobalt–nickel ore deposit and other Kazakhstan deposits, highlighting the challenges they pose for conventional beneficiation and metallurgical processing. Current industrial practices are analyzed, including pyrometallurgical, hydrometallurgical, and pyro-hydrometallurgical methods, with an emphasis on their efficiency, environmental impact, and economic feasibility. Special attention is given to the potential of hydro-catalytic leaching as a flexible, energy-efficient alternative for treating low-grade ONOs under atmospheric conditions. The results underscore the necessity of developing cost-effective and sustainable technologies tailored to the unique composition of Kazakhstani ONOs, particularly those rich in iron and magnesium. This work provides a strategic framework for future research and the industrial application of advanced leaching techniques to unlock the full potential of Kazakhstan’s nickel resources. Full article

Wheat (Triticum aestivum L.) is a crucial global food crop. The intensive crop farming, monoculture cultivation, and impact of climate change affect the susceptibility of wheat cultivars to biotic stresses, mainly caused by soil fungal pathogens, especially those belonging to the genus Fusarium. This situation threatens yield and grain quality through root and crown rot. While conventional chemical fungicides face resistance issues and environmental concerns, biological alternatives like seed priming with natural metabolites are gaining attention. Polyamines, including putrescine, spermidine, and spermine, are attractive priming agents influencing plant development and abiotic stress responses. Spermine in particular shows potential for in vitro antifungal activity against Fusarium. Optimising spermine concentration for seed priming is crucial to maximising protection against Fusarium infection while ensuring robust plant growth. In this research, we explored the potential of the polyamine spermine as a seed treatment to enhance wheat resilience, aiming to identify a sustainable alternative to synthetic fungicides. Our findings revealed that a six-hour seed soak in spermine solutions ranging from 0.5 to 5 mM did not delay germination or seedling growth. In fact, the 5 mM concentration significantly stimulated root weight and length. In complementary in vitro assays, we evaluated the antifungal activity of spermine (0.5–5 mM) against three Fusarium species. The results demonstrated complete inhibition of Fusarium culmorum growth at 5 mM spermine. A less significant effect on Fusarium graminearum and little to no impact on Fusarium oxysporum were found. The performed analysis revealed that the spermine had a fungistatic effect against the pathogen, retarding the mycelium growth of F. culmorum inoculated on the seed surface. A pot experiment with Bulgarian soft wheat cv. Sadovo-1 was carried out to estimate the effect of seed priming with spermine against infection with isolates of pathogenic fungus F. culmorum on plant growth and disease severity. Our results demonstrated that spermine resulted in a reduced distribution of F. culmorum and improved plant performance, as evidenced by the higher fresh weight and height of plants pre-treated with spermine. This research describes the efficacy of spermine seed priming as a novel strategy for managing Fusarium root and crown rot in wheat. Full article

Micronutrients play a prominent role in plant growth and development, and their bioavailability is a growing global concern. Zinc is one of the most important micronutrients in the plant life cycle, acting as a metallic cofactor for numerous biochemical reactions within plant cells. Zinc deficiency in plants leads to various physiological abnormalities, ultimately affecting nutritional quality and posing challenges to food security. Biofortification methods have been adopted by agronomists to increase Zn concentrations in crops through optimal foliar and soil applications. Changing climatic conditions and conventional agricultural practices alter edaphic factors, reducing zinc bioavailability in soils due to abrupt weather changes. Precision agriculture emphasizes need-based and site-specific technologies to address these nutritional deficiencies. Nanoscience, a multidimensional approach, reduces particle size to the nanometer (nm) scale to enhance their efficiency in precise amounts. Nanoscale forms of Zn⁺² and their broad applications across crops are gaining attention in agriculture under varied application methods. This review focuses on the significance of Zn oxide (ZnO) nanoparticles (ZnONPs) and their extensive application in crop production. We also discuss optimum dosage levels, ZnONPs synthesis, application methods, toxicity, and promising future strategies in this field. Full article

Asthma is a persistent ailment that impacts the respiratory system and stands as a formidable public health challenge globally. Inhaled corticosteroids and bronchodilators, while effective in asthma management, are accompanied by side effects and high costs. Recently, nutraceuticals have gained significant attention as adjuvant therapy due to their promising outcomes. Given the antioxidant properties, nutrient richness, and an array of health benefits, beetroot and its bioactive compounds have been tested as an adjuvant therapy for asthma management. Although its main bioactive compound, betalains (betanin), has demonstrated promising results in mouse studies, beetroot juice has been found to worsen asthma. This review investigated the full spectrum of active compounds associated with beetroots to understand the underlying factors contributing to the conflicting findings. The finding suggests that individual bioactive compounds, such as phenolic compounds, flavonoids, nitrates, betalains, saponins, vitamins, fiber, and carotenoids, possess asthma-managing properties. However, the consumption of juice may exacerbate the condition. This discrepancy may be attributed to the presence of sugars and oxalates in the juice, which could counteract the beneficial effects of the bioactive compounds. Full article

Long-range underwater gliders (LRUGs) have emerged as essential platforms for sustained and autonomous observation in deep and remote marine environments. This paper provides a comprehensive review of their developmental status, performance characteristics, and application progress. Emphasis is placed on two critical enabling technologies that fundamentally determine endurance: lightweight, pressure-resistant hull structures and high-efficiency buoyancy-driven propulsion systems. First, the role of carbon fiber composite pressure hulls in enhancing energy capacity and structural integrity is examined, with attention to material selection, fabrication methods, compressibility compatibility, and antifouling resistance. Second, the evolution of buoyancy control systems is analyzed, covering the transition to hybrid active–passive architectures, rapid-response actuators based on smart materials, thermohaline energy harvesting, and energy recovery mechanisms. Based on this analysis, the paper identifies four key technical challenges and proposes strategic research directions, including the development of ultralight, high-strength structural materials; integrated multi-mechanism antifouling technologies; energy-optimized coordinated buoyancy systems; and thermally adaptive glider platforms. Achieving a system architecture with ultra-long endurance, enhanced energy efficiency, and robust environmental adaptability is anticipated to be a foundational enabler for future long-duration missions and globally distributed underwater glider networks. Full article

Emotion analysis based on electroencephalogram (EEG) sensors is pivotal for human–machine interaction yet faces key challenges in spatio-temporal feature fusion and cross-band and brain-region integration from multi-channel sensor-derived signals. This paper proposes MB-MSTFNet, a novel framework for EEG emotion recognition. The model constructs a 3D tensor to encode band–space–time correlations of sensor data, explicitly modeling frequency-domain dynamics and spatial distributions of EEG sensors across brain regions. A multi-scale CNN-Inception module extracts hierarchical spatial features via diverse convolutional kernels and pooling operations, capturing localized sensor activations and global brain network interactions. Bi-directional GRUs (BiGRUs) model temporal dependencies in sensor time-series, adept at capturing long-range dynamic patterns. Multi-head self-attention highlights critical time windows and brain regions by assigning adaptive weights to relevant sensor channels, suppressing noise from non-contributory electrodes. Experiments on the DEAP dataset, containing multi-channel EEG sensor recordings, show that MB-MSTFNet achieves 96.80 ± 0.92% valence accuracy, 98.02 ± 0.76% arousal accuracy for binary classification tasks, and 92.85 ± 1.45% accuracy for four-class classification. Ablation studies validate that feature fusion, bidirectional temporal modeling, and multi-scale mechanisms significantly enhance performance by improving feature complementarity. This sensor-driven framework advances affective computing by integrating spatio-temporal dynamics and multi-band interactions of EEG sensor signals, enabling efficient real-time emotion recognition. Full article

The construction sector is responsible for over 40% of waste generated in Australia. Construction materials are responsible for around 11% of global carbon dioxide emissions, and a third of these materials can end up wasted on a construction site. Attention in research and industry has been directed towards waste management and recycling, resulting in 78% of construction and demolition waste being diverted from landfill. However, the waste hierarchy emphasises avoiding the generation of waste in the first place. In this paper, the PRISMA approach is used to conduct a systematic review with the objective of identifying waste reduction strategies employed across all stages of projects in the Australian construction industry. Scopus and Web of Science databases were used. The search returned 523 publications which were screened and reviewed; this resulted in 24 relevant publications from 1998 to 2025. Qualitative analysis identifies strategies categorised into five groupings: pre-demolition, design, culture, materials and procurement, and on-site activities. The review finds a distinct focus on strategies within the materials and procurement category. The reviewed literature includes fewer strategies for the avoidance of waste than for any of the other levels of the waste hierarchy, evidencing the need for further focus in this area. Full article

Visible-Infrared Person Re-Identification (VI-ReID) is of crucial importance in applications such as monitoring and security. However, challenges faced from intra-class variations and cross-modal differences are often exacerbated by inaccurate infrared analysis and insufficient structural modeling. To address these issues, we propose Parsing-guided Differential Enhancement Graph Learning (PDEGL), a novel framework that learns discriminative representations through a dual-branch architecture synergizing global feature refinement with part-based structural graph analysis. In particular, we introduce a Differential Infrared Part Enhancement (DIPE) module to correct infrared parsing errors and a Parsing Structural Graph (PSG) module to model high-order topological relationships between body parts for structural consistency matching. Furthermore, we design a Position-sensitive Spatial-Channel Attention (PSCA) module to enhance global feature discriminability. Extensive evaluations on the SYSU-MM01, RegDB, and LLCM datasets demonstrate that our PDEGL method achieves competitive performance. Full article

Due to the challenges in obtaining full-body point clouds and the time-consuming registration of parametric body models, we propose an end-to-end Front Point Cloud Parametric Body Regression Network (FPCR-Net). This network directly regresses the pose and shape parameters of a parametric body model from a single front point cloud of the human body. The network first predicts the label probabilities of corresponding body parts and the back point cloud from the input front point cloud. Then, it extracts equivariant features from both the front and predicted back point clouds, which are concatenated into global point cloud equivariant features. For pose prediction, part-level equivariant feature aggregation is performed using the predicted part label probabilities, and the rotations of each joint in the parametric body model are predicted via a self-attention layer. Shape prediction is achieved by applying mean pooling to part-invariant features and estimating the shape parameters using a self-attention mechanism. Experimental results, both qualitative and quantitative, demonstrate that our method achieves comparable accuracy in reconstructing body models from front point clouds when compared to implicit representation-based methods. Moreover, compared to previous regression-based methods, vertex and joint position errors are reduced by 43.2% and 45.0%, respectively, relative to the baseline. Full article

Privacy-sensitive electricity scene classification requires robust models under data localization constraints, making federated learning (FL) a suitable framework. Existing FL frameworks face two critical challenges in multi-label electricity scene classification: (1) Label correlations and their strengths significantly impact classification performance. (2) Electricity scene data and labels show distributional inconsistencies across regions. However, current FL frameworks lack explicit modeling of label correlation strengths, and locally trained regional models naturally capture these differences, leading to regional differences in their model parameters. In this scenario, the server’s standard single-stage aggregation often over-averages the global model’s parameters, reducing its discriminative ability. To address these issues, we propose FMMAN, a federated multi-stage attention neural network for multi-label electricity scene classification. The main contributions of this FMMAN lie in label correlation learning and the stepwise model aggregation. It splits the client–server interaction into multiple stages: (1) Clients train models locally to encode features and label correlation strengths after receiving the server’s initial model. (2) The server clusters these locally trained models into K groups to ensure that models within a group have more consistent parameters and generates K prototype models via intra-group aggregation to reduce over-averaging. The K models are then distributed back to the clients. (3) Clients refine their models using the K prototypes with contrastive group-specific consistency regularization to further mitigate over-averaging, and sends the refined model back to the server. (4) Finally, the server aggregates the models into a global model. Experiments on multi-label benchmarks verify that FMMAN outperforms baseline methods. Full article

Hyperspectral image (HSI) classification is an important task in the field of remote sensing, with far-reaching practical significance. Most Convolutional Neural Networks (CNNs) only focus on local spatial features and ignore global spectral dependencies, making it difficult to completely extract spectral information in HSI. In contrast, Vision Transformers (ViTs) are widely used in HSI due to their superior feature extraction capabilities. However, existing Transformer models have challenges in achieving spectral–spatial feature fusion and maintaining local structural consistency, making it difficult to strike a balance between global modeling capabilities and local representation. To this end, we propose a Prompt-Gated Transformer with a Spatial–Spectral Enhancement (PGTSEFormer) network, which includes a Channel Hybrid Positional Attention Module (CHPA) and Prompt Cross-Former (PCFormer). The CHPA module adopts a dual-branch architecture to concurrently capture spectral and spatial positional attention, thereby enhancing the model’s discriminative capacity for complex feature categories through adaptive weight fusion. PCFormer introduces a Prompt-Gated mechanism and grouping strategy to effectively model cross-regional contextual information, while maintaining local consistency, which significantly enhances the ability for long-distance dependent modeling. Experiments were conducted on five HSI datasets and the results showed that overall accuracies of 97.91%, 98.74%, 99.48%, 99.18%, and 92.57% were obtained on the Indian pines, Salians, Botswana, WHU-Hi-LongKou, and WHU-Hi-HongHu datasets. The experimental results show the effectiveness of our proposed approach. Full article