Search Results (977)

Deep learning has achieved remarkable progress in electrocardiogram (ECG) analysis, but its heavy dependence on labeled data greatly increases annotation cost. This work proposes wall-aligned vector embedding (WAVE), a self-supervised learning framework that effectively extracts prior knowledge from unlabeled ECGs to reduce reliance on labels. WAVE fully leverages the diversity, synergy, and lead correlation of multi-lead ECGs by explicitly incorporating the correspondence between ECG leads and cardiac walls. Specifically, a multi-branch network captures lead-wise diversity; wall-wise synergy is modeled by concatenating leads from the same wall and projecting them via shared projection; and a dual alignment task is designed to learn correlations both within and across cardiac walls. Experimental results demonstrate that WAVE consistently surpasses all baselines under various evaluation settings, and maintains strong performance even when only a small fraction of labeled ECGs is available. Furthermore, components such as dual alignment, shared projection, wall-based concatenation, and mean target embedding are empirically verified to significantly enhance pretraining quality. In summary, WAVE learns highly informative ECG representations from unlabeled data, enabling low-cost and label-efficient ECG analysis for real-world cardiovascular diagnostics. Full article

Anxiety disorders pose an increasing challenge to the mental health of individuals, particularly in regions with limited healthcare access. This study investigated the potential of integrating a brain–computer interface for processing electroencephalography (EEG) data with deep learning models to accurately classify anxious and non-anxious states. In the first phase, a convolutional neural network (CNN) was developed and validated on the public GAMEEMO dataset, achieving a classification accuracy of 95.72%. In the second phase, we conducted a separate experimental validation with seven participants (aged 18–60 years) using a within-subjects design. The protocol comprised a custom Stroop test to elicit acute cognitive stress and anxiety-related arousal, followed by a guided 4–7–8 breathing exercise to induce relaxation. EEG data from this experiment were used to classify anxious versus non-anxious states with the same CNN architecture after domain adaptation. On this self-collected dataset, the CNN achieved an accuracy of 86.58%. These results demonstrate proof-of-concept transferability while highlighting the performance gap between controlled benchmark data and real-world, small-sample recordings. The deep learning model can subsequently be coupled with neurofeedback techniques to manage anxiety levels. Overall, the findings support the potential of the developed automated system for detecting stress-induced anxious states, with possible future integration into neurofeedback-based management systems. Full article

A massive number of early-constructed small-to-medium-span bridges are collectively entering an “aging” phase in China. Meanwhile, vast amounts of unstructured bottom-level inspection texts remain underutilized. To address them, this paper proposes a data governance method. Large Language Models were leveraged to process unstructured defect data from 18,238 real-world bridges nationwide. The data were structurally cleaned and mapped into discrete features, revealing multidimensional vulnerabilities. On this basis, the Stable Contrastive Pattern Risk (SCPR) intelligent decision-making model was developed. The results demonstrate that, following robust filtration, 6 nationwide common risk rules were extracted from 2064 initial candidate combinations. These rules converge into three core risk patterns: the heavy-duty aging pattern, the substructure-dominated pattern, and the over-water small-span low-seismic-design pattern. Guided by these robust rules and specific damage enrichment characteristics, risk stratification and differentiated management strategies were further formulated for Class III bridges. This research facilitates a paradigm shift in bridge maintenance. It moves from reactive, post-event symptom characterization toward data-driven, proactive early warnings. This shift provides a substantive scientific foundation for optimizing resource allocation and enabling precise investment decisions at the road network level. Full article

The bus system plays an important role in the urban public transportation infrastructure system, providing a convenient way for the masses to travel. However, the operational resilience and functional stability of urban transit systems are frequently jeopardized by a variety of internal disruptions and external emergencies. Therefore, it is important to evaluate the robustness of urban bus networks. Based on the complex network theory, this research applies Space L and Space R methods to construct the bus stop network and bus line network models in Jinan, China. The topological characteristics of the two network models are studied, and the network robustness is analyzed using two attack strategies: random attack and deliberate attack. The robustness is optimized based on the network edge addition strategy. The results show that: (1) The bus stop network has a scale-free network property, but the bus stop network and the bus line network do not have the small-world network property. (2) The bus line network is more robust than the bus stop network when under attack, and the network under deliberate attack is more vulnerable than that under random attack. The maximum betweenness centrality node attack causes the most significant damage to the network. (3) Under random attack, both high betweenness centrality edge addition (HBA) and high degree edge addition (HDA) strategies are more effective at optimizing network robustness; under maximum degree node attack, both low betweenness centrality edge addition (LBA) and low degree edge addition (LDA) strategies are more effective on optimizing network robustness; under maximum betweenness centrality node attack, the LBA strategy has the best effect on optimizing network robustness. The research results can provide scientific guidance for the emergency scheduling and line optimization of urban public transportation system. Full article

Infrared small target detection (ISTD) has been a critical technology in various civilian and industrial applications over the past several decades, such as civilian patrol missions aboard UAVs or shipboard systems, and industrial inspection tasks like factory defect scanning. Nevertheless, moving infrared small target detection still faces considerable challenges: existing models suffer from insufficient spatio-temporal semantic correlation and are not lightweight-friendly, while algorithms that perform reliably across diverse scenarios are in great demand for real-world applications. To address these issues, we propose FeedbackSTS-Det, a sparse-frames-based spatio-temporal semantic feedback network. A closed-loop spatio-temporal semantic feedback strategy with paired forward and backward refinement modules that work cooperatively across the encoder and decoder is adopted to enhance information exchange between consecutive frames, effectively improving detection accuracy and reducing false alarms. Moreover, we introduce an embedded sparse semantic module (SSM), which operates by strategically grouping frames by interval, propagating semantics within each group, and reassembling the sequence to efficiently capture long-range temporal dependencies with low computational overhead. Extensive experiments on many widely adopted multi-frame infrared small target datasets demonstrate the consistent effectiveness of our proposed network across diverse scenes. Full article

Although exercise interventions have been shown to alleviate core symptoms of Autism Spectrum Disorder (ASD), the neural mechanisms underlying these improvements, particularly those involving the White Matter Network (WMN), remain poorly understood. This study investigated the effects of a Mini-Basketball Training Program (MBTP) on core symptoms and WMN in children with ASD. This study adopted a two-site cluster-Randomized Controlled Trial (cRCT) design. Participants from two special education centers in China were randomly assigned to either an intervention group (MBTP) or a control group (CON). The participants underwent a 12-week MBTP. Core symptom assessments and a Diffusion Tensor Imaging (DTI) scan were conducted before and after the intervention. The individual WMNs were constructed using Deterministic Fiber Tracking (DFT). Graph theoretical analysis was applied to examine changes in WMN topological properties after MBTP. The MBTP significantly improved core symptoms in children with ASD, alongside the decreased normalized clustering coefficient (Gamma, γ), characteristic path length (Lambda, λ), small-world attributes (Sigma, σ), and increased global efficiency (E_glob). The nodal clustering coefficient (NCC) increased in the left cuneus (CUN.L) and left cerebellum 9 (CRBL9.L). Notably, the increased NCC in CRBL9.L was significantly correlated with improvements in core symptoms following the MBTP. The improvement in core symptoms in children with ASD following exercise intervention is associated with the remodeling of the WMN, highlighting the cerebellum as a key node in this neural mechanism. Full article

Remote sensing image change detection is widely used in urban expansion analysis, land-use monitoring, and disaster assessment. Nevertheless, it still faces significant challenges due to pseudo-change interference in high-resolution imagery, the large-scale variation in small changed objects, and the need for lightweight models in real-world engineering applications. To address these issues, this paper proposes LDST-ChangeNet, a lightweight dual spatiotemporal attention network for change detection. The network adopts a Siamese EfficientNet-B1 as its dual-branch encoder and employs a differential bi-temporal feature fusion strategy (Diff) to explicitly model temporal discrepancies, enabling efficient feature extraction while significantly reducing model complexity. A Position Attention Module (PAM) is introduced at the encoder bottleneck to suppress pseudo changes caused by non-structural factors. Meanwhile, a lightweight Pyramid Pooling Module (PPM-lite) is incorporated at the entrance of the deepest decoder features to enhance multi-scale contextual representation. Furthermore, a Boundary Attention Module (BAM) is applied in the decoder output stage to improve boundary delineation and small-object change detection. Experimental results on the LEVIR-CD and WHU-CD datasets show that LDST-ChangeNet outperforms other state-of-the-art methods, achieving F1-scores of 90.67% and 91.08%, respectively. The model maintains a lightweight design, requiring only 11.72 M parameters and 10.03 GFLOPs on LEVIR-CD, and 11.77 M parameters and 9.12 GFLOPs on WHU-CD. Full article

Early wildfire detection (EWD) is of the utmost importance to enable rapid response efforts and thus minimize the negative impacts of wildfire spreads. To this end, we present PyroNear₂₀₂₅, a new dataset composed of both images and videos, allowing for the training and evaluation of smoke plume detection models, including sequential models. The data is sourced from the following: (i) web-scraped videos of wildfires from public networks of cameras for wildfire detection in-the-wild, (ii) videos from our in-house network of cameras, and (iii) a small portion of synthetic and real images. This dataset includes around 150,000 manual annotations on 50,000 images, covering 640 wildfires; PyroNear₂₀₂₅ surpasses existing datasets in size and diversity. It includes data from France, Spain, Chile, and the United States. Finally, it is composed of both images and videos, allowing for the training and evaluation of smoke plume detection models, including sequential models. We ran cross-dataset experiments using a lightweight state-of-the-art object detection model, similar to the ones used in real-world applications, and found that the proposed dataset is particularly challenging, with an F1 score of around 70%, but it is more stable than existing datasets. Finally, its use in concordance with other public datasets helps to reach higher results overall. Last but not least, the video part of the dataset enables another technical contribution, as it can be used to train a lightweight sequential model, improving global recall while maintaining precision for earlier detections. The output of this work has real-life implications, as it is used to automatically detect wildfires, with our models running on Raspberry Pi in several countries. We will make both our code and data available online. Full article

Background: Rifaximin is widely used in the management of small intestinal bacterial overgrowth (SIBO), but concerns remain regarding the potential risk of Clostridioides difficile infection (CDI), particularly with repeated antibiotic exposure. Aim: To evaluate the short-term risk of CDI following Rifaximin therapy in patients with SIBO. Materials and Methods: We conducted a retrospective cohort study using the TriNetX Collaborative Research Network. Adult patients with SIBO were identified and categorized based on Rifaximin exposure within 60 days of diagnosis. The primary analysis compared patients with SIBO treated with Rifaximin to those with SIBO who did not receive Rifaximin. Secondary analyses included comparisons between SIBO patients treated with Rifaximin and irritable bowel syndrome (IBS) patients receiving Rifaximin, as well as patients with SIBO receiving a single versus multiple Rifaximin courses. Propensity score matching (1:1) was performed to balance baseline characteristics. The primary outcome was CDI within 60 days of the index event. Secondary outcomes included hospitalization and emergency department (ED) visits. Results: After propensity score matching, 19,597 patients were included in each cohort in the primary comparison of SIBO treated with Rifaximin versus SIBO without Rifaximin. CDI occurred in 0.21% of Rifaximin-treated patients and 0.15% of untreated patients (p = 0.152). In the contextual comparison, CDI incidence was similar between SIBO patients receiving Rifaximin and IBS patients receiving Rifaximin (0.21% vs. 0.15%, p = 0.168). Among patients with SIBO receiving Rifaximin, CDI risk did not differ between single and multiple treatment courses (0.20% vs. 0.21%, p = 0.850). Conclusions: In this large real-world cohort, Rifaximin therapy for SIBO was not associated with a statistically significant increase in short-term CDI risk. However, given the low event rate, wide confidence intervals, and risk of type II error, these findings should be interpreted with caution. Full article

Accurate identification of tea diseases and pests is a key challenge in smart agriculture. Current approaches to tea disease and pest identification suffer from a scarcity of high-quality annotated image data and poor generalization of existing models in real-world field environments. To address these issues, this paper first constructs and releases a dataset of images of tea diseases and pests captured in real-world field scenarios. The dataset uses leaf-level annotations and covers six common tea disease and pest categories in Guizhou Province, China. It contains 549 high-resolution images covering varying lighting conditions, backgrounds, and disease severity levels. Based on this dataset, we propose a convolutional neural network model named GatedFCA-YOLO, which integrates a small-object detection layer with an adaptive attention mechanism. Specifically, the small-object detection layer preserves high-resolution details, effectively improving recall of minute lesions. Meanwhile, the GatedFCA module is designed to fuse a spatial gating mechanism with FCAttention. It enables adaptive feature enhancement and significantly boosts the model’s recognition robustness under complex backgrounds. Experimental results on our dataset show that GatedFCA-YOLO achieves 78.9% mAP@0.5, which is 3% increased compared to the baseline model YOLO11n, thereby verifying the effectiveness of the proposed method. Full article

The Capacitated Quadratic Assignment Problem (CQAP) arises in logistics and network design, requiring the allocation of tasks to agents under quadratic interaction costs and capacity constraints. Classical exact solvers become computationally infeasible for large-scale instances, while heuristic methods such as Genetic Algorithms suffer from scalability limitations and sensitivity to local optima, leaving a gap for principled scalable approximations. In this paper, we address CQAP using the Gromov–Wasserstein (GW) framework, derived from Optimal Transport (OT) theory. In particular, we propose a multi-initialization GW strategy (GW_MultiInit) that mitigates the local optima problem inherent to non-convex GW optimization and scales efficiently to large problem sizes. Computational experiments on synthetic CQAP instances show that GW_MultiInit consistently achieves solutions close to the exact optimum for small- and medium-scale problems, and outperforms heuristic baselines such as the genetic algorithm at large scale in both runtime and solution quality across the benchmarks tested. To validate generalizability, we further evaluate GW_MultiInit On 17 QAPLIB benchmark instances adapted to the CQAP setting, GW_MultiInit achieves the best approximate result on 15 out of 17 instances with an average optimality gap of 0.34%, demonstrating strong generalizability beyond synthetic data. Additional comparisons with Entropic GW and Fused GW highlight practical trade-offs between accuracy, speed, and parameter sensitivity, offering guidelines for real-world deployment. Our results suggest that GW-based methods, and GW_MultiInit in particular, offer a promising and scalable approach for CQAP and related large-scale assignment problems within the problem scales examined. Full article

Molecular trajectory prediction is fundamental to computational chemistry, drug discovery, and materials simulation, enabling insights into dynamics, reaction pathways, and conformational stability. Its natural alignment with graph-structured spatiotemporal data has made it a key frontier in GNN research. However, current mainstream spatiotemporal GNNs, while enforcing E(3)-equivariance, treat atoms as unconstrained point masses and lack explicit rigid geometric constraints, often yielding unphysical deformations that compromise predictive interpretability. To address this challenge, we propose STEGMN—the first spatiotemporal graph architecture for molecular trajectory prediction that explicitly encodes rigid constraints. Inspired by Graph Mechanics Networks, we design a constraint-preserving equivariant spatiotemporal attention mechanism that captures temporal dependencies while rigorously maintaining both E(3)-equivariance and rigid-body constraints. Additionally, we introduce a constraint-preserving equivariant pooling module that generates future states by performing a learnable weighted aggregation of historical angular velocities, followed by forward kinematics mapping. This ensures that all outputs simultaneously satisfy E(3)-equivariance and strict bond-length conservation. Evaluated on real-world molecular dynamics datasets, STEGMN consistently outperforms strong baselines. On the rMD17 benchmark, it achieves an average ∼40% reduction in prediction MSE relative to representative spatiotemporal graph models (ST-GNN, ST-GCN, and ST-EGNN) across eight small-molecule systems, highlighting the critical value of explicit constraint modeling for physically stable trajectory prediction. Full article

A Software-Defined Network (SDN) renders flexible traffic engineering, but consumes a lot of energy. There is an overhead on the control-plane because flow rule updates are always performed and there is energy consumption by the forwarding hardware. Current energy-aware SDN methods mostly focus on Static or Greedy optimizations. This can cause too many Ternary Content-Addressable Memory (TCAM) updates and unstable rule churn when traffic changes over time. This article introduces a Dynamic Flow Rule Placement (DFRP) framework for real-time energy optimization in SDN. It reduces network energy usage, TCAM update costs, and rule churn all at the same time. The suggested framework uses a convex relaxation method to take decisions on binary switches, links, and rule placement. It also uses a minimum-edit round scheme that only allows small rule changes between time slots. To further reduce instability in the control plane, batch scheduling and receding horizon optimization (RHO) techniques are used. The system uses predicted traffic for future time slots to make decisions, but only the actions for the current time slot are executed. The experiments are carried out on two real-world dynamic SNDlib topologies such as Germany50 and Nobel-Germany, using 288 five-minute traffic matrices over a one-day period. Comparative results against Static and Greedy baselines show that DFRP saves approx. 30% energy while cutting down on TCAM update overhead and rule churn by approx. 20%, consistently across both the networks. Hence DFRP can be applied on dynamic traffic large-scale networks for stable and energy-efficient SDN operations. Full article

Over the last two decades, the automotive industry has spearheaded a shift toward data-centric manufacturing, where Real-Time Ethernet (RTE) networks defined in IEC61784-2 serve as critical components for ensuring deterministic communication at the Operation Technology level. Although AI-based systems offer significant potential for predictive maintenance and cybersecurity, their effectiveness is currently limited by a lack of structured datasets from real-world industrial environments. Most existing research relies on small-scale simulations or laboratory setups that fail to capture the scale and complexity of actual production. To address this gap, this paper introduces a novel methodology for repurposing network data collected throughout a plant’s lifecycle, specifically during the commissioning and validation phases of RTE networks according to IEC61918. An additional important contribution is the creation of the first multi-plant dataset for real RTE (PROFINET) traffic in the automotive sector, aggregating 300 GB of data from 54,000+ devices across nearly 700 production lines in 17 industrial sites. The work defines standardized methodologies and replicable processes for systematic data acquisition, validation, and labeling to ensure long-term usability for training AI models. Finally, four case studies (focused on performance, maintenance, security, and machine learning) show how this dataset can be used to enhance the reliability of modern smart manufacturing. Full article

In multi-ethnic villages, public space serves as more than just a venue for social interaction; it is the vital ground where cultural integration and community identity take root. This study examines Cizhong Village in the Diqing Tibetan Autonomous Prefecture of Yunnan, employing a mixed-methods approach that combines questionnaire surveys (N = 120), semi-structured interviews (N = 32), and Social Network Analysis (SNA) to compare the village’s planned spatial network with residents’ actual movement patterns. Findings reveal a significant structural mismatch: while the planned network exhibits higher density (0.32) and clustering (0.70), the behavioral network demonstrates a stronger small-world index (2.14 vs. 1.94), indicating that villagers organically form compact activity clusters around key social hubs such as the church and supermarket. QAP correlation analysis further shows that Tibetan and Naxi behavioral networks are highly similar (r = 0.833, p < 0.001), whereas Han networks exhibit weaker correlations (r = 0.527–0.607, p < 0.05), revealing a spatial pattern of “broad integration with localized ethnic preferences”. Grounded theory coding of interview data (55 initial concepts, 14 categories, 4 core categories) validates these structural findings and identifies the core theme of “superposed space of multi-ethnic dynamic sharing”. Based on these results, three optimization strategies are proposed: improving connectivity between public spaces, revitalizing key social hubs, and respecting established ethnic spatial traditions. These insights provide an evidence-based framework for managing public spaces in multi-ethnic rural communities. Full article