Search Results (18,528)

Bearing fault diagnosis is an important task for condition monitoring and predictive maintenance of rotating machinery. Nevertheless, many existing deep learning-based methods have difficulty in jointly modeling multi-scale fault characteristics, adaptively highlighting informative features, and maintaining robustness under noisy measurement conditions. To address these issues, this study presents MDCAD-Net, a multi-dilated convolution attention denoising network that integrates multi-scale temporal feature extraction, attention-based feature refinement, and explicit noise suppression within an end-to-end learning framework. Parallel dilated convolutions with different dilation rates are employed to capture short-duration transient impulses as well as long-range periodic patterns in vibration signals. Channel-wise feature recalibration using squeeze-and-excitation networks and spatial-temporal attention via a convolutional block attention module are combined to enhance informative representations. In addition, a denoising block with gated attention and residual connections is introduced to reduce noise interference while retaining fault-related signal components. Experiments conducted on the Case Western Reserve University bearing dataset show that the proposed method achieves a classification accuracy of 98.93% and yields competitive performance compared with several commonly used deep learning models. Ablation studies and feature visualization results further illustrate the contributions of the individual components and the separability of the learned feature representations under noisy conditions. The results indicate the potential of the proposed framework for practical bearing fault diagnosis under noisy operating conditions. Full article

Digital management of modern railway bridges, a substantial part of high-speed railway networks, is often hindered by manual interpretation of construction drawings for Building Information Modeling (BIM). While individual technologies like optical character recognition (OCR) and neural networks are well-established, their generic application often fails on complex engineering documents. To address this, a domain-adaptive automatic recognition and semantic interpretation framework is proposed for railway bridge construction drawings. The novelty of this work lies in a specialized hybrid data fusion strategy that intelligently merges vector CAD file parsing with morphology-denoised OCR, resolving spatial and semantic conflicts. Furthermore, a back-propagation (BP) neural network is explicitly adapted to classify the extracted text into specific engineering categories, overcoming the challenges of dense layouts and overlapping symbols. Finally, the framework achieves end-to-end integration by transforming these semantic entities directly into structured, IFC-compatible BIM parameters. Evaluated on 250 real-world drawings, the framework achieved an average F1-score of 91.0% in semantic classification and improved processing efficiency by 6.5 times compared to manual methods. Moreover, 93.8% of the extracted entities achieved strict BIM parameter correctness, defined as seamless mapping to Revit IFC attributes without manual intervention. Full article

The Industrial Internet of Things (IIoT) has become a cornerstone of modern industrial automation, enabling real-time monitoring, intelligent decision-making, and large-scale connectivity across cyber–physical systems. However, the growing scale, heterogeneity, and dynamic behavior of IIoT environments significantly expand the attack surface and challenge the effectiveness of conventional security mechanisms. In this paper, we propose DeepSense, a hybrid and adaptive anomaly and intrusion detection framework specifically designed for resource-constrained and heterogeneous IIoT deployments. DeepSense integrates three complementary components: DataSense, a realistic data pipeline and experimental testbed supporting synchronized sensor and network data processing; RuleSense, a lightweight rule-based detection layer that provides fast, deterministic, and interpretable anomaly screening at the edge; and NeuroSense, a learning-driven detection module comprising an adaptive ensemble of 22 machine learning and deep learning models spanning classical, neural, hybrid, and Transformer-based architectures. NeuroSense operates as a second detection stage that validates suspicious events flagged by RuleSense and enables both coarse-grained and fine-grained attack classification. To support rigorous and practical assessment, this work further introduces a comprehensive performance evaluation framework that extends beyond accuracy-centric metrics by jointly considering detection quality, latency, resource efficiency, and detection coverage, alongside an optimization-based process for selecting Pareto-optimal model ensembles under realistic IIoT constraints. Extensive experiments across diverse detection scenarios demonstrate that DeepSense exhibits strong generalization, lower false positive rates, and robust performance under evolving attack behaviors. The proposed framework provides a scalable and efficient IIoT security solution that meets the operational requirements of Industry 4.0 and the resilience-oriented objectives of Industry 5.0. Full article

Proteomic research in the genus Vitis has progressed from early biochemical studies of soluble proteins to high-resolution, quantitative analyses encompassing all major organs and derived products. This review provides a comprehensive synthesis of advances in grapevine and wine proteomics. In leaves, studies have revealed extensive remodeling of photosynthetic, antioxidant, and defense pathways under biotic (e.g., Plasmopara viticola, Erysiphe necator, Xylella fastidiosa, Candidatus Phytoplasma vitis) and abiotic stresses (drought, salinity, heat, light). Bud proteomics elucidated hormonal regulation and mechanisms of dormancy release, while root studies identified nitrate-dependent metabolic shifts and adaptive protein networks. Cell culture models enabled controlled investigation of elicitor responses, stilbene biosynthesis, and temperature-induced proteome changes. In berries, proteomics clarified developmental transitions from fruit set to ripening, emphasizing proteins related to secondary metabolism, vacuolar transport, and stress tolerance. Comparative analyses across cultivars and environments identified biomarkers linked to aroma, color, and texture. The wine proteome revealed selective persistence of grape-derived proteins (e.g., thaumatin-like proteins, chitinases) and yeast peptides influencing stability and sensory properties, while Botrytis cinerea infection significantly alters this balance by degrading PR proteins and introducing fungal enzymes. Altogether, the Vitis proteome emerges as a dynamic, multifunctional system crucial for understanding plant adaptation, enological quality, and biomarker discovery. Full article

CCAAT/enhancer-binding protein δ (C/EBPδ) is a rapidly responsive transcription factor that occupies an important regulatory position in adipocytes. Induced during the early stage of adipocyte differentiation, C/EBPδ integrates hormonal, inflammatory, metabolic, and stress-related cues and contributes to the coordination of downstream transcriptional and functional programs. Beyond its role in the initiation of differentiation, C/EBPδ is also involved in adipogenic progression, metabolic regulation, and immune-related functions in adipocytes. Current evidence indicates that C/EBPδ participates in early adipogenic regulatory networks, contributes to lipid metabolic programs, and is associated with immune-regulatory processes linked to lipid antigen presentation. Notably, the biological output of C/EBPδ is strongly shaped by tissue type, developmental stage, and microenvironmental context, ranging from promotion of adipogenic differentiation to regulation of inflammatory, metabolic, and adaptive stress responses under distinct physiological and pathological conditions. This review summarizes the upstream regulatory network, downstream functional framework, and context-dependent roles of C/EBPδ in adipocytes, and further discusses its potential relevance to adipose-related diseases as well as the opportunities and challenges for future precision intervention strategies. Full article

Background: Targeted therapies directed against oncogenic drivers have substantially improved outcomes for patients with epidermal growth factor receptor (EGFR)-mutant and anaplastic lymphoma kinase (ALK)-rearranged non-small cell lung cancer (NSCLC). Despite high initial response rates, most patients ultimately develop acquired resistance to tyrosine kinase inhibitors (TKIs), reflecting complex biological adaptations under therapeutic pressure. Methods: This narrative review synthesizes experimental, translational, and clinical studies examining how environmental and occupational respiratory exposures may influence resistance mechanisms in EGFR- and ALK-driven NSCLC. The review emphasizes exposure-associated signaling plasticity, inflammatory microenvironmental modulation, metabolic reprogramming, and pharmacokinetic alterations. Results: Recent evidence suggests that respiratory exposures, including cigarette smoke, air pollution, diesel exhaust, and occupational inhalational toxicants, can modulate oncogenic signaling networks relevant to resistance to targeted therapies. These mechanisms include aberrant EGFR activation, bypass signaling through the mesenchymal–epithelial transition receptor (MET) and SRC pathways, epithelial–mesenchymal transition (EMT), adaptive kinome remodeling, and exposure-associated inflammatory signaling, all of which may influence tumor evolution and therapeutic response. Conclusions: This review introduces a novel exposome-driven conceptual framework integrating environmental exposures with signaling plasticity and resistance evolution in oncogene-driven NSCLC. These findings support the concept that the respiratory exposome may represent an underrecognized modifier of targeted therapy response. Incorporating structured exposure assessment into precision oncology approaches may refine risk stratification and inform exposure-aware therapeutic strategies. Full article

Background: Intervertebral disc degeneration (IVDD) is driven by the interplay between inflammatory signaling, extracellular matrix (ECM) degradation, and impaired cellular adaptation. Although several nutraceutical compounds have been reported to exert protective effects in IVDD-related models, their multitarget mechanisms within integrated molecular networks remain incompletely characterized. Methods: An in silico framework integrating molecular docking with network-based analyses was employed to evaluate resveratrol, quercetin, melatonin, curcumin, and baicalein against a predefined panel of IVDD-associated targets, within an exploratory in silico framework. Binding affinities and interaction profiles were assessed using molecular docking, followed by protein–protein interaction (PPI) network construction, Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses, and hub gene identification. Results: Docking analyses revealed binding energies ranging from −4.59 to −13.25 kcal/mol, with curcumin and quercetin showing plausible docking poses across a subset of selected targets under the applied protocol. Network analysis showed a highly interconnected structure centered on key inflammatory regulators, including NFKB1, IL6, TNF, IL1B, STAT3, and NLRP3, together with ECM-associated components such as ACAN, COL2A1, SOX9, MMP13, and ADAMTS5. Enrichment analyses further suggested significant associations with inflammatory signaling pathways, cytokine regulation, and ECM organization. Conclusions: These findings are compatible with a distributed, multitarget interaction pattern of nutraceutical compounds within IVDD-associated molecular networks. By integrating molecular docking with network-based analyses, this study offers a system-level framework for interpreting previously reported effects within a disease-specific context. Docking-derived interaction patterns should be interpreted as qualitative and exploratory observations, as docking scores represent model-dependent estimates and do not establish comparable pharmacological effects across heterogeneous targets. The results should be considered hypothesis-generating and require experimental validation. Full article

This work explores the application of Spiking Neural Networks (SNNs) and Continual Learning (CL) methodologies to the problem of steering angle regression, using autonomous driving simulation as the experimental context, with a focus on energy efficiency and alignment with sustainable computing objectives. The primary goal was to design and implement CL techniques in SNNs to assess the model’s ability to maintain accuracy in explored environments while reducing CO${}_2$ emissions through the optimized use of a subset of the data. This study emerges in response to the increasing energy demand of deep learning models, which poses a challenge to sustainability. SNNs, inspired by the efficiency of biological neural systems, offer significant advantages in terms of computational and energy consumption, making them a promising alternative. CL techniques, such as Elastic Weight Consolidation and replay memory, are integrated to mitigate catastrophic forgetting in sequential learning tasks. The methodology includes adapting the PilotNet architecture for SNNs, preprocessing datasets generated in the Udacity driving simulator, and evaluating models in incremental learning scenarios. The experiments compare the performance of SNNs with CL against baseline models without CL, using mean squared error (MSE), computational efficiency, and equivalent CO${}_2$ emissions as evaluation metrics. The results demonstrate that replay memory enables the retention of prior knowledge with a limited increase in energy consumption. This work concludes that SNNs with CL are a viable alternative for sustainable AI applications. Future research directions include a focus primarily on hardware-specific implementations and real-world testing. Full article

Glycolysis is a defining feature of cancer metabolism, originally described by the Warburg effect. Increasing evidence indicates that cancer-associated glycolysis is not uniformly upregulated but dynamically rewired in response to oncogenic signaling, cellular demands, and microenvironmental cues. However, a framework integrating its temporal evolution and functional roles across tumorigenesis remains limited. In particular, how glycolytic rewiring drives malignant transformation, adapts during tumor progression, and generates context-dependent vulnerabilities has not been systematically synthesized. In this review, we examine glycolysis as a dynamic metabolic network evolving throughout tumor development. We discuss how early glycolytic rewiring, driven by oncogenic signaling and metabolic–epigenetic coupling, supports cell fate transitions and establishes redox and biosynthetic capacity during tumorigenesis. We then outline how glycolysis is remodeled during tumor progression through coordinated transcriptional, epigenetic, and post-translational regulation, as well as microenvironmental interactions and metabolic heterogeneity. Furthermore, we highlight glycolysis as an integrative hub linking immune evasion, cell death regulation, and metabolic plasticity, and discuss how glycolytic rewiring creates context-dependent metabolic dependencies that may be therapeutically exploited, along with emerging technologies that enable high-resolution characterization of tumor metabolism. Together, this review provides a conceptual framework for understanding glycolytic rewiring in cancer and outlines potential avenues for targeting metabolic vulnerabilities. Full article

Camera rotation estimation is a key component in video stabilization and motion analysis. In many practical scenarios, inertial measurements are unavailable or temporally unreliable, while classical geometric pipelines degrade under blur, low texture, and low illumination. This paper investigates whether substantially downsampled optical flow can retain sufficient structure for accurate frame-to-frame rotation regression. We present VisualRNet, a lightweight rotation-specific visual regression framework trained with cross-modal IMU supervision. Our design uses coordinate-aware feature encoding, depthwise separable convolutions, lightweight attention, and a compact 6D rotation head to model the spatial structure of rotational flow fields. On Deep-FVS, VisualRNet achieves a mean rotation error of 0.3151${}^{\circ }$ on the test set. The VisualRNet regression head contains 7.7 K parameters, 0.002 GFLOPs, and runs at 729 FPS, while the full pipeline with the FastFlowNetv2 frontend contains 1.374 M parameters, 7.194 GFLOPs, and runs at approximately 113 FPS. A cross-camera adaptation experiment on TUM VI further indicates that the learned motion representation can be aligned to a new camera system with limited calibration data. These results support low-resolution optical flow as a practical input for visual rotation estimation and suggest particular value in stabilization-oriented and cost-sensitive applications where approximate rotational trend matters more than full scene geometry. Full article

Infrared small-target segmentation (IRSTS) is crucial for a wide range of applications, including maritime search-and-rescue operations and intelligent traffic surveillance. However, current deep learning methods struggle with dynamic scale variations in infrared small targets, resulting in false detections and missed detections, alongside inadequate core localization accuracy. To address these challenges, we propose an infrared small-target segmentation framework founded on morphological attention and an energy core loss function, IRSTS_Unet. Specifically, we design a Dynamic Shape-adaptive Deformable Attention Module (DSDAM), which achieves parameterized feature extraction via “initial localization–offset deformation–precise sampling”. This approach enables the network to differentially focus on target cores and background cues to suppress clutter. To improve the efficiency of multi-scale feature aggregation, we embed the DSDAM within both the feature extraction and cross-layer fusion stages. Furthermore, we formulate a Core Energy-aware Core-Priority loss (CECP-Loss) function that incorporates the energy prior distribution of small targets, effectively counteracting the “core dilution” phenomenon endemic to conventional loss functions. Through extensive experiments on multiple public datasets, we demonstrate that IRSTS_U-Net outperforms state-of-the-art approaches in terms of both detection accuracy and robustness. Full article

This study proposes a robust data-driven control framework, LSTM-MPC, designed to enhance the velocity stabilization of Autonomous Underwater Vehicles (AUVs) operating under stochastic marine disturbances. Traditional control methods often struggle with the highly nonlinear and time-varying hydrodynamics of irregular waves. To address this, we employ a Long Short-Term Memory (LSTM) recurrent neural network to capture complex temporal dependencies and provide accurate multi-step-ahead velocity predictions. These predictions are integrated into a Model Predictive Control (MPC) scheme, which optimizes control actions while respecting actuator constraints. A key contribution is the integration of an error-triggered online learning mechanism. Utilizing run-time weight synchronization via MATLAB Coder, the framework dynamically adapts to plant mismatches and high-frequency MEMS noise without an explicit analytical model. The architecture was validated using experimental data from a Pixhawk/ArduSub baseline. Results demonstrate that, under these stochastic conditions, the data-driven approach significantly outperforms the standard PID-based baseline. While adaptive PID variants offer improvements, the suggested framework drastically reduces tracking errors in rotational axes while maintaining high precision in translational velocities. This research confirms that adaptive, data-driven strategies can effectively bridge the gap between simulation and real-world deployment, offering a scalable solution for robust AUV autonomy in unpredictable environments. Full article

To address the challenges of multi-scale defect perception and complex background interference in railway insulator detection, this paper proposes LSD-YOLO, a lightweight multi-scale fusion network based on an improved YOLO11n. The model integrates three core modules: a Large-Small (LS) module for multi-scale receptive field fusion, a Token Statistics Self-Attention (TSSA) module for efficient global context modeling, and a Detail-Preserving Contextual Fusion (DPCF) module for adaptive multi-scale feature fusion. Experiments on a multi-defect insulator dataset constructed from 4C inspection system images and public datasets show LSD-YOLO achieves 86.2% mAP@50, 4.1 percentage points higher than the baseline model. Its precision and recall reach 91.8% and 80.6% respectively, with only 2.30 M parameters. Its comprehensive detection performance outperforms mainstream comparative models. The proposed method enhances the integrated detection ability for both physical defects and pollution-flashover faults of insulators, and provides a reference for intelligent inspection in complex railway scenarios. Full article

Accurate electric vehicle (EV) charging load forecasting is essential for grid planning and resource allocation, yet existing approaches struggle with the inherent sparsity of charging data—a phenomenon characterized by excessive zeros representing periods of no charging activity. This paper addresses this challenge through a novel framework combining a Zero-Inflated Neural Network (ZINN) architecture with an Evolutionary Neural Architecture Search (ENAS) algorithm. ZINN explicitly decomposes the forecasting problem into binary classification (predicting charging occurrence) and regression (estimating energy magnitude conditioned on occurrence), enabling the model to learn distinct patterns for the absence and presence of charging events. Rather than relying on manually designed architectures, ENAS automatically discovers optimal encoder and decoder configurations from a comprehensive search space encompassing modern architectures (LSTM, GRU, Transformer, and iTransformer), layer configurations, activation functions, and hyperparameters. The evolutionary algorithm balances prediction accuracy with computational efficiency through multi-objective optimization. Extensive experiments on real-world EV charging data from 30 stations in Wuhan demonstrate that the ZINN+ENAS framework achieves the lowest prediction error compared to conventional baselines, with the discovered optimal configuration substantially outperforming hand-crafted designs. Comprehensive ablation studies reveal that the asymmetric dual-head architecture and adaptive regularization strategies are critical for handling data sparsity. These findings highlight the importance of explicit zero-inflation modeling and automated architecture discovery for specialized forecasting tasks, providing practitioners with an open-source framework for practical EV charging load prediction. Full article

Since the 1960s, research on sea-level rise (SLR) and land subsidence has grown significantly; however, comprehensive syntheses remain limited. This study presents a systematic review of 2171 publications spanning 1964–2025, combining a global perspective with a regional focus on the Gulf of Guinea, a critically underrepresented region within the African continent. The results show a steady increase in publications, exceeding 80 per year since 2015. A combined bibliometric and content analysis approach was adopted, integrating large-scale metadata analysis with an in-depth evaluation of 166 full-text studies corresponding to 311 study sites. Bibliometric analyses highlight four main themes: (1) factors driving SLR and subsidence, including climate, geophysical, and human effects; (2) monitoring methods such as tide gauges, GPS, and InSAR-based land motion tracking; (3) impacts on coastal communities, and ecosystems; and (4) strategies for adaptation and mitigation. A comparative assessment of global research output and Low-Elevation Coastal Zone (LECZ) exposure reveals a marked spatial mismatch, with critically vulnerable regions, such as the Gulf of Guinea, remaining significantly underrepresented (44 studies). The synthesis identifies key conceptual, methodological, and practical research gaps. Addressing these gaps requires holistic frameworks that integrate SLR and subsidence, long-term monitoring networks, advanced modeling, and evidence-based adaptation strategies. By linking bibliometric evidence with the interpretation of research trends and gaps, this study provides an analytical basis for supporting monitoring strategies, coastal planning, and adaptive responses. Additionally, the results highlight priority directions for future research directions in the Gulf of Guinea region. Full article