Search Results (17,931)

Adenosine triphosphate (ATP) serves as a central energy currency and signaling molecule in cellular processes, with ATP-binding sites in proteins playing critical roles in enzymatic catalysis, signal transduction, and gene regulation. The accurate identification of ATP-binding sites is essential for understanding protein function mechanisms and facilitating drug discovery, enzyme engineering, and disease pathway analysis. In this study, we present a novel hybrid deep learning framework that synergizes heterogeneous learning paradigms based on protein sequence information for accurate ATP-binding site prediction. Our approach integrates two complementary base classifiers. One is a Transformer-based model, which leverages high-level contextual embeddings generated by Evolutionary Scale Modeling 2 (ESM-2), a state-of-the-art protein language model, combined with a local–global dual-attention mechanism that enables the model to simultaneously characterize short-segment and long-range contextual dependencies across the entire protein sequence. The other is a deep Q-network (DQN)-inspired classifier that achieves residue-level prediction as a sequential decision-making process. The final predictions are generated using a weighted ensemble strategy, where optimal weights are determined via cross-validations to leverage the strengths of both models. The prediction results on benchmark independent testing sets indicate that our method achieves satisfactory performance on key metrics. Beyond predictive efficacy, this work uncovers the intrinsic biological mechanisms underlying protein–ATP interactions, including the synergistic roles of local structural motifs and global conformational constraints, as well as family-specific binding patterns, endowing the research with substantial biological significance. The research in this work offers a deeper understanding of the protein–ligand recognition mechanisms and supportive efforts on large-scale functional annotations that are critical for system biology and drug target discovery. Full article

Low-dose computed tomography (LDCT) can effectively reduce ionizing radiation; however, the associated image noise and artifacts can severely compromise the accuracy of clinical diagnosis. To address the challenge of balancing noise suppression and detail preservation in LDCT images, this study proposes a deep learning (DL)-based image denoising method termed Progressive Fusion Distillation Network (PFDN). Building upon the Information Multi-distillation Network (IMDN), the proposed method incorporates a pixel attention (PA) mechanism and a progressive fusion strategy, and further designs a Pixel Parallel Extraction Block (PPEB) together with a Progressive Fusion Distillation Block (PFDB) to fully exploit multi-scale and multi-channel features, thereby optimizing the image denoising network through efficient feature separation and re-fusion. In addition, by explicitly leveraging the noise characteristics specific to LDCT images, the method establishes an end-to-end training framework suitable for medical imaging. Experimental results demonstrate that PFDN not only effectively reduces image noise and artifacts, but also enhances overall image quality while preserving diagnostically relevant image structures under the adopted evaluation setting. Full article

Wind turbine blade surface defect detection remains challenging due to large variations in defect scales, blurred edge textures, and severe interference from complex backgrounds, which often lead to insufficient detection accuracy and high false and missed detection rates. To address these issues, this paper proposes an improved RTDETR-based detection framework, termed CEA-DETR, for wind turbine blade surface defect inspection. First, a Cross-Scale Multi-Edge feature Extraction (CSME) backbone is designed by integrating multi-scale pooling and edge-enhancement units with a dual-domain feature selection mechanism, enabling effective extraction of fine-grained texture and edge features across different scales. Second, an Efficient Multi-Scale Feature Fusion Network (EMSFFN) is constructed to facilitate deep cross-level feature interaction through adaptive weighted fusion and multi-scale convolutional structures, thereby enhancing the representation of multi-scale defects. Furthermore, an adaptive sparse self-attention mechanism is introduced to reconstruct the AIFI module, strengthening global dependency modeling and guiding the network to focus on critical defect regions under complex background conditions. Experimental results demonstrate that CEA-DETR achieves mAP50 and mAP50:95 of 89.4% and 68.9%, respectively, representing improvements of 3.1% and 6.5% over the RT-DETR-r18 baseline. Meanwhile, the proposed model reduces computational cost (GFLOPs) by 20.1% and parameter count by 8.1%. These advantages make CEA-DETR more suitable for deployment on resource-constrained unmanned aerial vehicles (UAVs), enabling efficient and real-time autonomous inspection of wind turbine blades. Full article

To address the challenges posed by the strong uncertainty of high-proportion renewable energy sources (RES) to the secure and stable operation of distributed real-time power dispatch (D-RTPD) in new-type power systems, this paper proposes an integrated solution combining a neighborhood feature aggregation-based graph attention network (NFA-GAT) and multi-agent deep deterministic policy gradient (MADDPG). First, the D-RTPD problem is modeled as a decentralized partially observable Markov decision process (Dec-POMDP), which effectively captures the stochastic game characteristics of multi-regional agents and the partial observability of grid states. Second, the NFA-GAT is designed to enhance agents’ perception of grid operating states: by introducing a spatial discount factor, it realizes rational aggregation of multi-order neighborhood information while modeling the attenuation of electrical quantity influence with topological distance. Third, a prior-guided mechanism is integrated into the MADDPG framework to eliminate constraint-violating actions by setting their actor logits to negative infinity, improving training efficiency and strategy reliability. Simulation validations on the IEEE 118-bus test system (75.2% RES installed capacity ratio) show that the proposed method achieves efficient training convergence. Compared with the multi-layer perceptron (MLP) structure, it attains higher cumulative reward values and scenario win rates. When compared with traditional model-driven (ADMM) and data-driven (Q-MIX) methods, the proposed method balances solution efficiency, operational safety (98.7% maximum line load rate, zero power flow violation rate), and economic performance ($12,845 daily dispatch cost), providing a reliable technical support for D-RTPD under high-proportion RES integration. Full article

Infrared and visible image fusion aims to integrate complementary information from heterogeneous images captured by different optical sensors based on distinct imaging principles; however, existing methods often exhibit modality bias, leading to weakened targets or the loss of crucial texture details. To address this, we propose MBFTFuse, an adversarial fusion network based on modality balancing and feature tracing, which consists of a triple-path generator and dual discriminators. The architecture employs a generator with a triple-path structure: a central modality-balancing path for deep feature fusion and dual edge feature-tracing paths for modality-specific enhancement. Specifically, a multi-cognitive modality-balancing module is introduced to achieve feature weight equilibrium, while a Feature-Tracing Attention Module self-enhances single-modality features to compensate for information loss in the fusion results. Furthermore, a pixel loss based on intensity histograms is designed to optimize inter-modal balance at the pixel level. Comparative experiments against nine state-of-the-art methods across three public datasets demonstrate that MBFTFuse effectively highlights infrared targets while preserving intricate visible textures. The superior performance of this method in both quantitative metrics and downstream object detection tasks contributes to extending the boundaries of sensor-driven computer vision technologies. Full article

Electric power station confined spaces are high-risk and complex environments characterized by significant illumination variations. Whether safety helmets are properly worn directly affects the operational safety of workers in confined spaces. However, helmet detection in such environments faces several challenges, including drastic lighting changes and difficulties in small-object detection. Moreover, existing object detection models typically contain a large number of parameters, making real-time helmet detection difficult to deploy on field devices with limited computational resources. To address these issues, this paper proposes a lightweight safety helmet wearing detection algorithm named GSA-YOLO. To mitigate the effects of severe illumination variation and detail loss in confined spaces, a GCA-C2f module integrating GhostConv and the CBAM attention mechanism is embedded into the backbone network. This design reduces the number of parameters and computational cost while enhancing the model’s feature extraction capability under challenging lighting conditions. To improve detection performance for occluded targets, an improved efficient channel attention (I-ECA) mechanism is introduced into the neck structure, which suppresses irrelevant channel features and enhances occluded object detection accuracy. Furthermore, to alleviate missed detections of small objects and inaccurate localization under low-light conditions, a P2 detection branch is added to the head, and the WIoU loss function is adopted to dynamically adjust the weights of hard and easy samples, thereby improving small-object detection accuracy and localization robustness. A confined space helmet detection dataset containing 5000 images was constructed through on-site data collection for model training and validation. Experimental results demonstrate that the proposed GSA-YOLO achieves an mAP@0.5 of 91.2% on the self-built dataset with only 2.3 M parameters, outperforming the baseline model by 2.9% while reducing the parameter count by 23.6%. The experimental results verify that the proposed algorithm is suitable for environments with significant illumination variation and small-object detection challenges. It provides a lightweight and efficient solution for on-site helmet detection in confined space scenarios, thereby contributing to the reduction in industrial safety accidents. Full article

The Sentinel-3 Ocean and Land Colour Instrument (OLCI) is designed for water monitoring. Its 21-spectral bands serve as the basis for the precise retrieval of water quality parameters. However, its coarse resolution restricts the depiction of the spatial distribution of water quality parameters in small inland water bodies. Spatial–spectral fusion is a common method to address the inherent constraints between the spatial and spectral resolutions of sensors. Central to the popular methods is the deep learning-based method. Nonetheless, deep-learning-based models still face challenges in fusing Sentinel-2 Multi-Spectral Instrument (MSI) and Sentinel-3 OLCI data. Here, we propose a Multi-Scale-Attention-based Unsupervised Generative Adversarial Network (MSA-UGAN), which effectively integrates OLCI’s spectral advantage and MSI’s spatial resolution. Quantitative evaluation was conducted against five benchmark methods, including traditional approaches (GS, SFIM, MTF-GLP) and deep learning models (SRCNN, UCGAN). The results show that MSA-UGAN achieves the best overall performance: QNR (0.9709) and SSIM (0.9087) are the highest, while SAM (1.1331), spatial distortion (D_S = 0.0389), and spectral distortion (D_λ = 0.0252) are the lowest. This shows that MSA-UGAN can better preserve the spatial details of S2 MSI and the spectral features of S3 OLCI data. Moreover, ERGAS (2.2734) also performs excellently in the comparative experiments. The experiment of Chlorophyll-a inversion using the fused image in Chen Lake revealed a spatial gradient ranging from 3.25 to 19.33 µg/L, with the highest concentrations in the southwestern nearshore waters, likely associated with aquaculture. These results jointly indicate that MSA-UGAN can generate high-spatial-resolution multispectral images, and the fused images can be effectively utilized for water quality monitoring, thereby providing essential data support for the precision management and scientific decision-making regarding inland lakes. Full article

Symmetry and structural balance play a fundamental role in the collective behavior of networked agent systems (NASs). In particular, cluster formation tracking, representing the emergence and maintenance of symmetric group structures, has attracted significant attention due to its wide applications in robotics and autonomous systems. However, most existing approaches assume autonomous leaders, which may not be applicable in scenarios where human intervention is required. With this in mind, this paper addresses the cluster formation tracking problem for NASs with collision avoidance, where the leader receives control inputs from a human-in-the-loop (HiTL), making the leader a non-autonomous system. A distributed control protocol is developed so that followers can track the trajectories of their designated leaders using only relative information from neighboring agents. Sufficient conditions are established to guarantee collision-free cluster formation tracking, and Lyapunov-based analysis is employed to prove the asymptotic convergence of the subgroup tracking errors. In the proposed framework, human intervention is incorporated through external commands applied to the leaders, which makes the leader dynamics non-autonomous while preserving the distributed nature of the follower controllers. Simulation studies on a 13-agent network with three subgroups show that all followers achieve the desired time-varying cluster formations under HiTL-driven leader motions, with convergence times ranging from 4.21 s to 5.12 s. Moreover, the final tracking errors of all followers are reduced below $9.07\times {10}^{-5}$, while the minimum pairwise distances within each subgroup remain strictly above the prescribed safety threshold. These quantitative results verify both the effectiveness of the proposed protocol and the practical feasibility of integrating HiTL commands into collision-free cluster formation tracking. Full article

This study presents a systematic review of Social Network Analysis (SNA) applications in Egyptology, examining methodological developments, current achievements, and future research directions. Despite Egypt’s exceptional documentary legacy spanning three millennia—administrative papyri, diplomatic correspondence, and prosopographical inscriptions—Egyptology has adopted network analytical methods more slowly than other archaeological disciplines. The review evaluates existing research across major historical periods, assessing methodological approaches and contributions to understanding Egyptian administrative structures, elite strategies, and social organization. Critical gaps identified include limited coverage of the Late Period, insufficient attention to economic and religious networks, minimal focus on gender and household-level analysis, and geographic concentration in Upper Egypt. The review also identifies methodological challenges specific to Egyptian sources: temporal depth, hierarchical social structures, preservation biases, and integration of diverse evidence types. Priority areas for development include large-scale collaborative projects, computational relationship extraction from digitised sources, and temporal network analysis capitalising on Egypt’s exceptional chronological span. The field stands at a critical juncture where coordinated development could transform understanding of ancient Egyptian society while contributing to broader archaeological network science. Full article

Manganese (Mn) is an essential micronutrient required for plant growth, photosynthesis and metabolic regulation. Its importance is related to the involvement in several metabolic processes that ensure proper cellular function and balanced plant development throughout the production cycle. In plants, Mn is absorbed predominantly as Mn²⁺, and its availability is strongly influenced by soil pH, aeration, and other mineral nutrients in the soil solution. After uptake by roots, Mn is translocated to the shoot, accumulating primarily in metabolically active organs such as stems, young leaves and flowers. Although Mn exhibits limited mobility in the phloem, adequate concentrations are necessary to sustain both vegetative development and reproductive growth. Adequate Mn concentration is directly reflected in fruit development, as well-nourished plants show improved flowering, greater assimilate translocation capacity, and better fruit filling, thereby positively influencing yield and quality. However, Mn deficiency is common in alkaline soils or soils with high organic matter, causing interveinal chlorosis in young leaves, reduced growth, and lower biomass production. Under prolonged conditions, deficiency leads to less vigorous plants with reduced metabolic efficiency. Conversely, Mn toxicity, typically associated with acidic and poorly drained soils, restricts root development and induces nutritional imbalances with other elements, such as calcium, magnesium, and iron. Therefore, proper Mn management is essential to ensure nutritional balance and optimal performance of agricultural crops. Overall, this review synthesizes advances in Mn transport, cellular compartmentalization, and metabolic regulation, emphasizing how Mn interacts with other mineral nutrients to influence plant physiology. Attention is given to the integration of Mn with redox networks, photosynthetic regulation, and reproductive development. By linking transport mechanisms with physiological outcomes, this review identifies key patterns governing Mn homeostasis and highlights implications for crop nutrition and sustainable nutrient management. Full article

Identifying microscopic textural anomalies and filtering out complicated industrial background noise remain significant hurdles in inspecting metallic surfaces. To tackle these operational bottlenecks, our research introduces a refined multi-scale detection framework built upon the YOLOv8l architecture. Specifically, we engineer a fine-grained detection pathway utilizing the P2 layer, which aims to preserve critical details of miniature flaws that are otherwise discarded during feature extraction. Furthermore, a Bi-directional Feature Pyramid Network model is embedded to reconstruct the feature fusion path, balancing the preservation of shallow geometric textures with enhanced multi-scale representation capabilities. To bolster anti-interference performance, a Convolutional Block Attention Module (CBAM) is integrated prior to the detection head, employing adaptive channel and spatial weighting to suppress unstructured background noise. Experimental results utilizing TTA demonstrate that the mAP@0.5 reached 76.3%. Detection accuracies for patches and inclusions reached 93.1% and 85.3%. Full article

The increasing proportion of renewable energy leads to frequent changes in turbine load, making the regulating stage more prone to degradation. Traditional anomaly detection methods lack sufficient sensitivity and generalization. To address this issue, this study proposes a method combining multi-attention gated fusion and physical information learning. A gated fusion mechanism is proposed to adaptively extract and fuse key temporal and feature information. Furthermore, the generalization ability of the model is improved by introducing physical constraints derived from the relationship between pressure, temperature, and valve position. Finally, a dynamic temperature prediction model is established using the multi-output long short-term memory neural network. Experiments using actual power plant data demonstrate that the proposed method effectively improves the accuracy of post-regulating-stage temperature prediction and the sensitivity of anomaly detection. The proposed gating fusion method improves prediction accuracy by 4.6% compared to direct addition, while the fusion of physical information reduces the generalization error by more than 6%. In addition, compared to traditional deep learning and machine learning models, the proposed method improves anomaly detection accuracy by at least 3.9%. This research is of great significance for the safe operation of thermal power units and the power grid. Full article

This study addresses the low operational efficiency and high energy storage cost of wind–solar hybrid energy storage systems due to the strong volatility and intermittency of wind and photovoltaic power. Instead, the authors propose a dual-layer optimization model based on convolutional neural network–long short-term memory–attention mechanism (CNN-LSTM-AM) forecasting. First, a CNN-LSTM-AM forecasting model is constructed based on convolutional neural networks and long short-term memory networks. Then, the model is applied to wind and solar power forecasting to dynamically optimize the output power ratio of renewable sources and batteries based on predicted power, thereby reducing the start–stop frequency of compressed air energy storage (CAES) and improving operational efficiency. For lower-layer optimization, a weight evaluation model based on AHP is constructed and subsequently used to optimize the capacity configuration of the hybrid energy storage system to achieve overall system optimality. Case studies indicate that after upper-layer optimization, the number of CAES start–stop cycles decreases from 25 to 17, and further declines to 14 after optimization of the lower-layer capacity configuration, while the energy storage cost is reduced by 5.43% and the curtailment rate decreases by 0.15%. This validates the effectiveness of the proposed model in improving the economic performance and stability of renewable hybrid energy storage systems. Full article

Accurate fault diagnosis of rotating machinery in complex industrial environments demands an optimal trade-off between feature representation capability and computational efficiency. Existing single-modality models relying solely on 1D time-series signals or heavy 2D time-frequency images often fail to simultaneously capture high-frequency transient impacts and long-range degradation trends. CLiST (Complementary Lightweight Spatiotemporal Network), a novel lightweight multimodal framework driven by time-frequency fusion, was proposed to overcome this limitation. The architecture of CLiST employs a synergistic dual-stream design: a LightTS module efficiently extracts global operational trends from 1D vibration signals with linear complexity, while a structurally pruned LiteSwin integrated with Triplet Attention captures local high-frequency textures from 2D continuous wavelet transform (CWT) images. This mechanism establishes explicit cross-dimensional dependencies, effectively eliminating feature blind spots without excessive computational overhead. The experimental results show that CLiST not only achieves perfect accuracy on the fundamental CWRU benchmark but also exhibits exceptional spatial generalization when independently evaluated on non-dominant sensor axes of the XJTUGearbox dataset. Furthermore, validation on the real-world dataset (Guangzhou port) proves that the framework has excellent robustness to the attenuation of the signal transmission path and reduces the performance fluctuation between remote measurement points. Ultimately, CLiST delivers highly reliable AI-driven image and signal-processing solutions for vibration monitoring in industrial equipment. Full article

Social network content is increasingly used as an auxiliary evidence stream for financial monitoring, risk assessment, and short-horizon decision support, yet many reported gains are hard to interpret because observability, timing, and attribution are handled inconsistently across studies. This review critically synthesizes the end-to-end pipeline that transforms social posts, interaction traces, linked artifacts, and related signals into decision-facing indicators, emphasizing evidence provenance, sampling bias, conditioning (bot/spam filtering, entity linking, timestamp alignment), and the modeling blocks typically used (text, temporal, relational, and fusion components) under deployment constraints. Across sentiment, relational, and multimodal or cross-platform signals, the analysis finds that apparent improvements often depend more on alignment discipline and conservative attribution than on architectural novelty, and that performance can be inflated by attention confounds, temporal leakage, and visibility effects. Relational indicators are most defensible for monitoring coordination and propagation patterns, while multimodal gains require clear ablations and realistic missing-modality tests. To support decision readiness, the paper consolidates assurance requirements covering manipulation, degraded observability, calibration and traceability, and provides compact reporting checklists and failure-mode mitigations. Overall, the review supports bounded claims and argues for time-aware evaluation and auditable pipelines as prerequisites for operational use. Full article