Search Results (441)

Rotating compressors are foundational in various industrial processes, particularly in the oil-and-gas sector, where reliable fault detection is crucial for maintaining operational continuity. While Graph Attention Network (GAT) frameworks are widely available, this study advances the state of the art by introducing a Bayesian GAT method specifically tailored for vibration-based compressor fault diagnosis. The approach integrates domain-specific digital-twin simulations built with Rotordynamic software (1.3.0), and constructs dual adjacency matrices to encode both physically informed and data-driven sensor relationships. Additionally, a hybrid forecasting-and-reconstruction objective enables the model to capture short-term deviations as well as long-term waveform fidelity. Monte Carlo dropout further decomposes prediction uncertainty into aleatoric and epistemic components, providing a more robust and interpretable model. Comparative evaluations against conventional Long Short-Term Memory (LSTM)-based autoencoder and forecasting methods demonstrate that the proposed framework achieves superior fault-detection performance across multiple fault types, including misalignment, bearing failure, and unbalance. Moreover, uncertainty analyses confirm that fault severity correlates with increasing levels of both aleatoric and epistemic uncertainty, reflecting heightened noise and reduced model confidence under more severe conditions. By enhancing GAT fundamentals with a domain-tailored dual-graph strategy, specialized Bayesian inference, and digital-twin data generation, this research delivers a comprehensive and interpretable solution for compressor fault diagnosis, paving the way for more reliable and risk-aware predictive maintenance in complex rotating machinery. Full article

Reservoir-induced landslides threaten infrastructures and downstream communities, making continuous deformation monitoring vital. Time-series InSAR, notably the SBAS algorithm, provides high-precision surface-displacement mapping but suffers from voids due to layover/shadow effects and temporal decorrelation. Existing deep-learning approaches often operate on fixed-size patches or ignore irregular spatio-temporal dependencies, limiting their ability to recover missing pixels. With this objective, a hybrid spatio-temporal Graph Attention (ST-GAT) framework was developed and trained on SBAS-InSAR values using 24 influential features. A unified spatio-temporal graph is constructed, where each node represents a pixel at a specific acquisition time. The nodes are connected via inverse distance spatial edges to their K-nearest neighbors, and they have bidirectional temporal edges to themselves in adjacent acquisitions. The two spatial GAT layers capture terrain-driven influences, while the two temporal GAT layers model annual deformation trends. A compact MLP with per-map bias converts the fused node embeddings into normalized LOS estimates. The SBAS-InSAR results reveal LOS deformation, with 48% of missing pixels and 20% located near the Dasu dam. ST D-GAT reconstructed fully continuous spatio-temporal displacement fields, filling voids at critical sites. The model was validated and achieved an overall R² (0.907), ρ (0.947), per-map R² ≥ 0.807 with RMSE ≤ 9.99, and a ROC-AUC of 0.91. It also outperformed the six compared baseline models (IDW, KNN, RF, XGBoost, MLP, simple-NN) in both RMSE and R². By combining observed LOS values with 24 covariates in the proposed model, it delivers physically consistent gap-filling and enables continuous, high-resolution landslide monitoring in radar-challenged mountainous terrain. Full article

Decision making is challenging in autonomous driving (AD) under highway scenarios because of the unpredictable behaviors of neighbor vehicles, leading to the necessity of accurately modelling interactions between vehicles. Though ego-attention, a variant of self-attention, provides a way for object interaction extraction, its feature expression still needs to improve. This paper improves the original ego-attention by reweighting the encoding vehicle features, forcing them to pay more attention to significant features. Moreover, we designed a rule-based driver assistance module (DAM) to alleviate mis-decisions by constraining action space. Finally, we constructed our final AD decision-making model by integrating the proposed reweighting ego-attention and the DAM into the dual-input decision-making framework trained by enhanced deep reinforcement learning (DRL). We evaluated our decision-making model on highway scenarios. The results show that our model achieves better performance in success step (39.95 steps/episode), speed (29.15 m/s), lane-changing times (5.64 times/episode), and task completion rate (98%) than existing models, including DRL-GAT-SA, AE-D3QN-DA, and ego-attention-based ones, implying the competitive driving accuracy, safety, and comfort of our model. Full article

With the increasing integration of renewable energy and smart technologies in residential energy systems, proactive household energy management (HEM) have become critical for reducing costs, enhancing grid stability, and achieving sustainability goals. This study proposes a ultra-short-term forecasting-driven proactive energy consumption optimization strategy that integrates advanced forecasting models with multi-objective scheduling algorithms. By leveraging deep learning techniques like Graph Attention Network (GAT) architectures, the system predicts ultra-short-term household load profiles with high accuracy, addressing the volatility of residential energy use. Then, based on the predicted data, a comprehensive consideration of electricity costs, user comfort, carbon emission pricing, and grid load balance indicators is undertaken. This study proposes an enhanced mixed-integer optimization algorithm to collaboratively optimize multiple objective functions, thereby refining appliance scheduling, energy storage utilization, and grid interaction. Case studies demonstrate that integrating photovoltaic (PV) power generation forecasting and load forecasting models into a home energy management system, and adjusting the original power usage schedule based on predicted PV output and water heater demand, can effectively reduce electricity costs and carbon emissions without compromising user engagement in optimization. This approach helps promote energy-saving and low-carbon electricity consumption habits among users. Full article

The development of non-noble metal catalysts for gas-phase propylene epoxidation with H₂/O₂ remains challenging due to their inadequate activity and stability. Herein, we report a Cs⁺-modified Ni/TS-1 catalyst (9%Ni-Cs/TS-1), which exhibits unprecedented catalytic performance, giving a state-of-the-art PO formation rate of 382.9 g_PO·kg_cat⁻¹·h⁻¹ with 87.8% selectivity at 200 °C. The catalyst stability was sustainable for 150 h, far surpassing reported Ni-based catalysts. Ni/TS-1 exhibited low catalytic activity. However, the Cs modification significantly enhanced the performance of Ni/TS-1. Furthermore, the intrinsic reason for the enhanced performance was elucidated by multiple techniques such as XPS, N₂ physisorption, TEM, ²⁹Si NMR, NH₃-TPD-MS, UV–vis, and so on. The findings indicated that the incorporation of Cs⁺ markedly boosted the reduction of Ni, enhanced Ni⁰ formation, strengthened Ni-Ti interactions, reduced acid sites to inhibit PO isomerization, improved the dispersion of Ni nanoparticles, reduced particle size, and improved the hydrophobicity of Ni/TS-1 to facilitate propylene adsorption/PO desorption. The 9%Ni-Cs/TS-1 catalyst demonstrated exceptional performance characterized by a low cost, high activity, and long-term stability, offering a viable alternative to Au-based systems. Full article

Objectives: The objective of this study was to evaluate the agreement and clinical interchangeability of intraocular pressure (IOP) measurements obtained with the mechanical Haag-Streit AT900 Goldmann applanation tonometer (mGAT) and the digital Huvitz HT5000 applanation tonometer (dGAT). Methods: This retrospective comparative study included 53 eyes of 28 patients undergoing routine ophthalmologic evaluation. Each eye underwent IOP measurement using both mGAT and dGAT in a randomized sequence. Central corneal thickness (CCT) was also recorded. Pearson’s correlation coefficient was used to determine correlation between paired IOP measurements. Bland–Altman plots were graphed for the analysis of differences for IOP between the instruments. Results: A total of 53 eyes of 28 patients (15 males) were included in the study. The mean age of the patients was 62.6 years. The mean mGAT and dGAT measurements were 16.3 ± 6.6 mmHg (range 9–50) and 16.4 ± 6.2 mmHg (range 8.8–45.9), respectively (p = 0.53). A strong, significant positive correlation was found for paired IOP measurements by the two instruments (r = 0.98; p < 0.0001). Bland–Altman analysis revealed 95% limits of agreement from −2.5 to +2.3 mmHg, with a small but statistically significant proportional bias favoring mGAT at higher IOP levels. Additionally, 91% of paired measurements were within ±2 mmHg. CCT-related differences were statistically and clinically insignificant. Conclusions: IOP measurements obtained with mGAT and dGAT were highly correlated and clinically interchangeable for the range tested. The Huvitz HT5000 may serve as a reliable alternative to the classic Goldmann tonometer in routine clinical settings. Full article

Adequate treatment of the organic fraction of municipal solid waste (OFMSW) in co-digestion with sewage sludge (SS) through dark fermentation (DF) technologies has been widely studied and recognized. However, there is little experience with a high-solids approach, where practical and scalable conditions are established to lay the groundwork for further development of feasible industrial-scale projects. In this study, the biochemical hydrogen potential of OFMSW using a 7 L batch reactor at mesophilic conditions was evaluated. Parameters such as pH, redox potential, temperature, alkalinity, total solids, and substrate/inoculum ratio were adjusted and monitored. Biogas composition was analyzed by gas chromatography. The microbial characterization of SS and post-reaction percolate liquids was determined through metagenomics analyses. Results show a biohydrogen yield of 38.4 NmLH₂/gVS OFMSW, which forms ~60% of the produced biogas. Aeration was proven to be an efficient inoculum pretreatment method, mainly to decrease the levels of methanogenic archaea and metabolic competition, and at the same time maintain the required total solid (TS) contents for high-solids conditions. The microbial community analysis reveals that biohydrogen production was carried out by specific anaerobic and aerobic bacteria, predominantly dominated by the phylum Firmicutes, including the genus Bacillus (44.63% of the total microbial community), Clostridium, Romboutsia, and the phylum Proteobacteria, with the genus Proteus. Full article

The selection of appropriate biomarkers in clinical practice aids in the early detection, treatment, and prevention of disease while also assisting in the development of targeted therapeutics. Recently, multi-omics data generated from advanced technology platforms has become available for disease studies. Therefore, the integration of this data with associated clinical data provides a unique opportunity to gain a deeper understanding of disease. However, the effective integration of large-scale multi-omics data remains a major challenge. To address this, we propose a novel deep learning model—the Multi-Omics Graph Attention biomarker Discovery network (MOGAD). MOGAD aims to efficiently classify diseases and discover biomarkers by integrating various omics data such as DNA methylation, gene expression, and miRNA expression. The model consists of three main modules: Multi-head GAT network (MGAT), Multi-Graph Attention Fusion (MGAF), and Attention Fusion (AF), which work together to dynamically model the complex relationships among different omics layers. We incorporate clinical data (e.g., APOE genotype) which enables a systematic investigation of the influence of non-omics factors on disease classification. The experimental results demonstrate that MOGAD achieves a superior performance compared to existing single-omics and multi-omics integration methods in classification tasks for Alzheimer’s disease (AD). In the comparative experiment on the ROSMAP dataset, our model achieved the highest ACC (0.773), F1-score (0.787), and MCC (0.551). The biomarkers identified by MOGAD show strong associations with the underlying pathogenesis of AD. We also apply a Hi-C dataset to validate the biological rationality of the identified biomarkers. Furthermore, the incorporation of clinical data enhances the model’s robustness and uncovers synergistic interactions between omics and non-omics features. Thus, our deep learning model is able to successfully integrate multi-omics data to efficiently classify disease and discover novel biomarkers. Full article

Kinase is an enzyme responsible for cell signaling and other complex processes. Mutations or changes in kinase can cause cancer and other diseases in humans, including leukemia, neuroblastomas, glioblastomas, and more. Considering these concerns, inhibiting overexpressed or dysregulated kinases through small drug molecules is very important. In the past, many machine learning and deep learning approaches have been used to inhibit unregulated kinase enzymes. In this work, we employ a Graph Neural Network (GNN) to predict the inhibition activities of kinases. A separate Graph Convolution Network (GCN) and combined Graph Convolution and Graph Attention Network (GCN_GAT) are developed and trained on two large datasets (Kinase Datasets 1 and 2) consisting of small drug molecules against the targeted kinase using 10-fold cross-validation. Furthermore, a wide range of molecules are used as independent datasets on which the performance of the models is evaluated. On both independent kinase datasets, our model combining GCN and GAT provides the best evaluation and outperforms previous models in terms of accuracy, Matthews Correlation Coefficient (MCC), sensitivity, specificity, and precision. On the independent Kinase Dataset 1, the values of accuracy, MCC, sensitivity, specificity, and precision are 0.96, 0.89, 0.90, 0.98, and 0.91, respectively. Similarly, the performance of our model combining GCN and GAT on the independent Kinase Dataset 2 is 0.97, 0.90, 0.91, 0.99, and 0.92 in terms of accuracy, MCC, sensitivity, specificity, and precision, respectively. Full article

Background: The reproductive ability of equine species is a critical component of equine breeding programs, with sperm quality serving as a primary determinant of reproductive success. In this study, we perform an integrative analysis of proteomics and metabolomics in seminal plasma to identify proteins and metabolites associated with sperm quality and reproductive ability in equine species. Methods: We utilized the CEROS instrument to assess the morphology and motility of sperm samples from three horses and three donkeys. Additionally, we statistically analyzed the mating frequency and pregnancy rates in both species. Meanwhile, the 4D-DIA high-throughput proteomic and metabolomic profiling of seminal plasma samples from horses and donkeys revealed a complex landscape of proteins and metabolites. Results: Our findings reveal a certain degree of correlation between seminal plasma proteins and metabolites and sperm quality, as well as overall fertility. Notably, we found that the proteins B3GAT3, XYLT2, CHST14, HS2ST1, GLCE, and HSPG2 in the glycosaminoglycan biosynthesis signaling pathway; the metabolites D-glucose, 4-phosphopantetheine, and 4-hydroxyphenylpyruvic acid in the tyrosine metabolism, starch, and source metabolisms; and pantothenate CoA biosynthesis metabolism present unique characteristics in the seminal plasma of equine species. Conclusions: This comprehensive approach provides new insights into the molecular mechanisms underlying sperm quality and has identified potential proteins and metabolites that could be used to indicate reproduction ability. The findings from this study could be instrumental in developing novel strategies to enhance equine breeding practices and reproductive management. Future research will focus on exploring their potential for clinical application in the equine industry. Full article

The construction of transition rules is the core and difficulty faced by the cellular automata (CA) model. Dynamic mining of transition rules can more accurately simulate urban land use change. By introducing a graph attention network (GAT) to mine CA model transition rules, the temporal and spatial dynamics of the model are increased based on the construction of a real-time dynamic graph structure. At the same time, by adding an agent-based model (ABM) to the CA model, the simulation evolution of different human decision-making behaviors can be achieved. Based on this, an urban expansion scenario prediction (UESP) model has been proposed: (1) the UESP model employs a multi-head attention mechanism to dynamically capture high-order spatial dependencies, supporting the efficient processing of large-scale datasets with over 50,000 points of interest (POIs); (2) it incorporates the behaviors of agents such as residents, governments, and transportation systems to more realistically reflect human micro-level decision-making; and (3) by integrating macro-structural learning with micro-behavioral modeling, it effectively addresses the existing limitations in representing high-order spatial relationships and human decision-making processes in urban expansion simulations. Based on the policy context of the Outline of the Beijing–Tianjin–Hebei (BTH) Coordinated Development Plan, four development scenarios were designed to simulate construction land change by 2030. The results show that (1) the UESP model achieved an overall accuracy of 0.925, a Kappa coefficient of 0.878, and a FoM index of 0.048, outperforming traditional models, with the FoM being 3.5% higher; (2) through multi-scenario simulation prediction, it is found that under the scenario of ecological conservation and farmland protection, forest and grassland increase by 3142 km², and cultivated land increases by 896 km², with construction land showing a concentrated growth trend; and (3) the expansion of construction land will mainly occur at the expense of farmland, concentrated around Beijing, Tianjin, Tangshan, Shijiazhuang, and southern core cities in Hebei, forming a “core-driven, axis-extended, and cluster-expanded” spatial pattern. Full article

This paper introduces a novel dual-stream collaborative architecture for remote sensing road segmentation, designed to overcome multi-scale feature conflicts, limited dynamic adaptability, and compromised topological integrity. Our network employs a parallel “local–global” encoding scheme: the local stream uses depth-wise separable convolutions to capture fine-grained details, while the global stream integrates a Swin-Transformer with a graph-attention module (Swin-GAT) to model long-range contextual and topological relationships. By decoupling detailed feature extraction from global context modeling, the proposed framework more faithfully represents complex road structures. Comprehensive experiments on multiple aerial datasets demonstrate that our approach outperforms conventional baselines—especially under shadow occlusion and for thin-road delineation—while achieving real-time inference at 31 FPS. Ablation studies further confirm the critical roles of the Swin Transformer and GAT components in preserving topological continuity. Overall, this dual-stream dynamic-fusion network sets a new benchmark for remote sensing road extraction and holds promise for real-world, real-time applications. Full article

Graph attention networks are pivotal for modeling non-Euclidean data, yet they face dual challenges: training oscillations induced by projection-based high-dimensional constraints and gradient anomalies due to poor adaptation to heterophilic structure. To address these issues, we propose LDC-GAT (Lyapunov-Stable Graph Attention Network with Dynamic Filtering and Constraint-Aware Optimization), which jointly optimizes both forward and backward propagation processes. In the forward path, we introduce Dynamic Residual Graph Filtering, which integrates a tunable self-loop coefficient to balance neighborhood aggregation and self-feature retention. This filtering mechanism, constrained by a lower bound on Dirichlet energy, improves multi-head attention via multi-scale fusion and mitigates overfitting. In the backward path, we design the Fro-FWNAdam, a gradient descent algorithm guided by a learning-rate-aware perceptron. An explicit Frobenius norm bound on weights is derived from Lyapunov theory to form the basis of the perceptron. This stability-aware optimizer is embedded within a Frank–Wolfe framework with Nesterov acceleration, yielding a projection-free constrained optimization strategy that stabilizes training dynamics. Experiments on six benchmark datasets show that LDC-GAT outperforms GAT by 10.54% in classification accuracy, which demonstrates strong robustness on heterophilic graphs. Full article

Single-cell Assay for Transposase-Accessible Chromatin using sequencing (scATAC-seq) technology enables single-cell resolution analysis of chromatin accessibility, offering critical insights into gene regulation, epigenetic heterogeneity, and cellular differentiation across various biological contexts. However, existing cell annotation methods face notable limitations. Cross-omics approaches, which rely on single-cell RNA sequencing (scRNA-seq) as a reference, often struggle with data alignment due to fundamental differences between transcriptional and chromatin accessibility modalities. Meanwhile, intra-omics methods, which rely solely on scATAC-seq data, are frequently affected by batch effects and fail to fully utilize genomic sequence information for accurate annotation. To address these challenges, we propose scAttG, a novel deep learning framework that integrates graph attention networks (GATs) and convolutional neural networks (CNNs) to capture both chromatin accessibility signals and genomic sequence features. By utilizing the nucleotide sequences corresponding to scATAC-seq peaks, scAttG enhances both the robustness and accuracy of cell-type annotation. Experimental results across multiple scATAC-seq datasets suggest that scAttG generally performs favorably compared to existing methods, showing competitive performance in single-cell chromatin accessibility-based cell-type annotation. Full article

Lipopolysaccharide (LPS) endotoxin is a well-characterized microbe-associated molecular pattern (MAMP) that forms the outer membrane of both pathogenic and commensal Gram-negative bacteria. It plays a crucial role in triggering inflammatory disorders such as mastitis, acidosis, and septicemia. In heifers, an LPS challenge induces a dynamic stress response, marked by elevated cortisol levels, increased body temperature, and altered immune function. Research indicates that LPS administration leads to a significant rise in cortisol post-challenge. Building on this understanding, the present study aimed to estimate genetic parameters for serum cortisol response to LPS challenge in Holstein heifers and its linear associations with production, health, reproduction, and conformation traits. Additionally, a genome-wide association study (GWAS) was conducted to identify genetic regions associated with cortisol response. A total of 252 animals were evaluated for cortisol response, with correlations estimated between cortisol levels and 55 genomic breeding values for key traits. Genetic parameters and heritability for cortisol response were estimated using Residual Maximum Likelihood (REML) in the Blupf90+ v 2.57 software. Single-Step GWAS (ssGWAS) employing a 10-SNP window approach and 42,123 SNP markers was performed to identify genomic regions that explained at least 0.5% of additive genetic variance. Finally, candidate genes and QTLs located 50 kb up and downstream of those windows were identified. The cortisol response showed significant but weak linear associations with cystic ovaries, body maintenance requirements, lactation persistency, milk yield, and protein yield (p-value ≤ 0.05) and showed suggestive weak linear associations with udder texture, clinical ketosis, heel horn erosion, and milking speed (p-value ≤ 0.15). Cortisol response showed significant additive genetic variance, along with moderate heritability of 0.26 (±0.19). A total of 34 windows explained at least 0.5% of additive genetic variance, and 75 QTLs and 11 candidate genes, comprising the genes CCL20, DAW1, CSMD2, HMGB4, B3GAT2, PARD3, bta-mir-2285aw, CFH, CDH2, ENSBTAG00000052242, and ENSBTAG00000050498, were identified. The functional enrichment analysis allowed us to infer two instances where these gene products could interfere with cortisol production: the first instance is related to the complement system, and the second one is related to the EMT (Epithelium–Mesenchymal Transition) and pituitary gland formation. Among the QTLs, 13 were enriched in the dataset, corresponding to traits related to milk (potassium content), the exterior (udder traits, teat placement, foot angle, rear leg placement, and feet and leg conformation), production (length of productive life, net merit, and type), and reproduction (stillbirth and calving ease). In summary, the cortisol response to LPS challenge in Holstein heifers seems to be moderately heritable and has weak but significant linear associations with important production and health traits. Several candidate genes identified could perform important roles, in at least two ways, for cortisol production, and QTLs were identified close to regions of the genome that explained a significant amount of additive genetic variance for cortisol response. Therefore, further investigations are warranted to validate these findings with a larger dataset. Full article