Search Results (17,487)

In the field of Natural Language Inference (NLI), model interpretability remains an urgent and unresolved challenge. Existing interpretability-oriented annotated datasets are highly limited, and manually constructing natural language explanations is both costly and inconsistent, making it difficult to balance model performance and interpretability. To address this issue, this paper proposes an interpretable NLI framework based on active learning, Explanation Generation Model-Prediction Model (EGM-PM), and designs an active learning sampling algorithm, Explanation-aware Transition from Clustering to Margin (ETCM), that incorporates natural-language explanation information. In this framework, Large Language Models (LLMs) are employed to automate explanation annotation, reducing dependence on human experts in traditional active learning. A small number of high-value samples obtained via ETCM sampling are used to train the EGM, whose generated natural-language explanations are then used to guide the PM in label inference. Experimental results show that data sampled by ETCM substantially enhance the model’s ability to learn relational and logical structures between premise–hypothesis pairs. Compared with other active learning algorithms, ETCM approaches full-data performance more rapidly while using significantly fewer labeled samples. This finding confirms the value of natural language explanation semantics in improving both model performance and interpretability. Furthermore, this paper employs prompt engineering to construct an interpretability-oriented NLI dataset, Explainable Natural Language Inference (ExNLI), which augments traditional premise–hypothesis pairs with natural-language explanations. Human and automated evaluations confirm the consistency and faithfulness of these explanations. The dataset has been publicly released, offering a low-cost and scalable data construction approach for future research on explainable NLI. Full article

This study formulates and verifies a network-based evaluation methodology for appraising the sustainable competitiveness of community enterprises. Based on Social Capital Theory, the Resource-Based View (RBV), and Network Theory, the model defines high-quality networks as structural relational circumstances that facilitate resource sharing and knowledge sharing, serving as mediating mechanisms that improve competitive outcomes. A quantitative study approach was utilized, gathering survey data from 451 representatives of community enterprises around Thailand, and Structural Equation Modeling (SEM) was applied to assess both measurement features and structural relationships. The model demonstrates satisfactory internal reliability, convergent validity, and discriminant validity, affirming measurement adequacy. Empirical evidence indicates that high-quality networks are positively correlated with sustainable competitiveness, both directly and indirectly, with 49.2% of the overall effect conveyed through resource and knowledge exchange, emphasizing the practical value of network-based processes. The suggested model offers practical utility for policymakers and development agencies in search of evidence-based instruments to enhance competitiveness, network capacity, and long-term resilience in community enterprises. The cross-sectional methodology and lack of contextual control variables restrict causal inference and external generalizability, highlighting the necessity for longitudinal or quasi-experimental expansions. By emphasizing model creation and empirical validation, this study develops a systematic and reproducible methodological framework for assessment. Full article

To address the challenges of accurately extracting features from elongated scratches, irregular defects, and small-scale surface flaws on high-precision linear guide rails, this paper proposes a novel instance segmentation algorithm tailored for guide rail surface defect detection. The algorithm integrates the YOLOv8 instance segmentation framework with deformable convolutional networks and multi-scale feature fusion to enhance defect feature extraction and segmentation performance. A dedicated guide rail surface Defect (GSD) segmentation dataset is constructed to support model training and evaluation. In the backbone, the DCNv3 module is incorporated to strengthen the extraction of elongated and irregular defect features while simultaneously reducing model parameters. In the feature fusion network, a multi-scale feature fusion module and a triple-feature encoding module are introduced to jointly capture global contextual information and preserve fine-grained local defect details. Furthermore, a Channel and Position Attention Module (CPAM) is employed to integrate global and local features, improving the model’s sensitivity to channel and positional cues of small-target defects and thereby enhancing segmentation accuracy. Experimental results show that, compared with the original YOLOv8n-Seg, the proposed method achieves improvements of 3.9% and 3.8% in Box and Mask mAP₅₀, while maintaining a real-time inference speed of 148 FPS. Additional evaluations on the public MSD dataset further demonstrate the model’s strong versatility and robustness. Full article

Deep learning has emerged as a transformative methodology in modern cosmology, providing powerful tools to extract meaningful physical information from complex astronomical data. This paper implements a novel Bayesian graph deep learning framework for estimating key cosmological parameters in a primordial magnetic field (PMF) cosmology from simulated Cosmic Microwave Background (CMB) maps. Our methodology utilizes DeepSphere, a spherical convolutional neural network architecture specifically designed to respect the spherical geometry of CMB data through HEALPix pixelization. To advance beyond deterministic point estimates and enable robust uncertainty quantification, we integrate Bayesian Neural Networks (BNNs) into the framework, capturing aleatoric and epistemic uncertainties that reflect the model confidence in its predictions. The proposed approach demonstrates exceptional performance, achieving $R^2$ scores exceeding 89% for the magnetic parameter estimation. We further obtain well-calibrated uncertainty estimates through post hoc training techniques including Variance Scaling and GPNormal. This integrated DeepSphere-BNNs framework delivers accurate parameter estimation from CMB maps with PMF contributions while providing reliable uncertainty quantification, enabling robust cosmological inference in the era of precision cosmology. Full article

The emergence of low-cost edge devices has enabled the integration of automatic speech recognition (ASR) into IoT environments, creating new opportunities for real-time language assessment. However, achieving reliable performance on resource-constrained hardware remains a significant challenge, especially on the Artificial Internet of Things (AIoT). This study presents an AIoT-based framework for automated English-speaking assessment that integrates architecture and system design, ASR benchmarking, and reliability analysis on edge devices. The proposed AIoT-oriented architecture incorporates a lightweight scoring framework capable of analyzing pronunciation, fluency, prosody, and CEFR-aligned speaking proficiency within an automated assessment system. Seven open-source ASR models—four Whisper variants (tiny, base, small, and medium) and three Vosk models—were systematically benchmarked in terms of recognition accuracy, inference latency, and computational efficiency. Experimental results indicate that Whisper-medium deployed on the Raspberry Pi 5 achieved the strongest overall performance, reducing inference latency by 42–48% compared with the Raspberry Pi 4 and attaining the lowest Word Error Rate (WER) of 6.8%. In contrast, smaller models such as Whisper-tiny, with a WER of 26.7%, exhibited two- to threefold higher scoring variability, demonstrating how recognition errors propagate into automated assessment reliability. System-level testing revealed that the Raspberry Pi 5 can sustain near real-time processing with approximately 58% CPU utilization and around 1.2 GB of memory, whereas the Raspberry Pi 4 frequently approaches practical operational limits under comparable workloads. Validation using real learner speech data (approximately 100 sessions) confirmed that the proposed system delivers accurate, portable, and privacy-preserving speaking assessment using low-power edge hardware. Overall, this work introduces a practical AIoT-based assessment framework, provides a comprehensive benchmark of open-source ASR models on edge platforms, and offers empirical insights into the trade-offs among recognition accuracy, inference latency, and scoring stability in edge-based ASR deployments. Full article

Insulin resistance (IR) is a central driver of cardiometabolic disease and an increasingly recognized modifier of inflammatory and vascular pathology. Beyond impaired glucose homeostasis, IR emerges from chronic, metabolically induced inflammation (“meta-inflammation”) and convergent cellular stress programs that propagate across tissues and organ systems, ultimately shaping endothelial dysfunction, atherogenesis, and cardiometabolic complications. Here, we synthesize multilevel links between insulin receptor signaling, intracellular stress modules (oxidative, endoplasmic reticulum, inflammatory, and fibrotic pathways), tissue-level dysfunction, and systemic inflammatory amplification. This work is a conceptual narrative review informed by targeted database searches and citation tracking, with explicit separation of mechanistic/experimental evidence from human observational and interventional data; causal inferences are framed primarily on mechanistic and interventional findings, whereas associative statements are reserved for observational evidence. We propose an integrative framework in which stress-response pathways are context-dependent and become maladaptive when chronically activated under nutrient excess and persistent inflammatory cues, generating self-reinforcing loops between IR and inflammation that accelerate vascular injury. This framework highlights points of convergence that can guide mechanistic prioritization and translational hypothesis testing. Full article

This paper presents a real-time pedestrian situation detection framework for autonomous mobility platforms. The proposed approach extracts pedestrians from images acquired by a camera mounted on an autonomous mobility system, classifies their postures, tracks their trajectories, and subsequently detects pedestrian situations. A convolutional neural network (CNN) is employed for pedestrian detection and posture classification, where the YOLOv12 model is fine-tuned via transfer learning for this purpose. To improve detection and classification performance, a region of interest (ROI) is defined using camera calibration data, enabling robust detection of small-scale pedestrians over long distances. Using a custom-labeled dataset, the proposed method achieves a precision of 96.6% and a recall of 97.0% for pedestrian detection and posture classification. The detected pedestrians are tracked using the DeepSORT algorithm, and their situations are inferred through a rule-based analysis module. Experimental results demonstrate that the proposed system operates at an execution speed of 58.11 ms per frame, corresponding to 17.2 fps, thereby satisfying the real-time requirements for autonomous mobility applications. These results confirm that the proposed framework enables reliable real-time pedestrian extraction and situation awareness in real-world autonomous mobility environments. Full article

The accelerating energy demands from artificial intelligence (AI) deployment introduce systemic challenges for achieving carbon neutrality. Large language models (LLMs) represent a dominant driver of AI energy consumption, with inference operations constituting 80–90% of total energy usage. Current energy benchmarks report aggregate metrics without domain-level breakdowns, preventing accurate carbon footprint estimation for workloadspecific operations. This study addresses this critical gap by introducing a carbon-aware framework centered on the carbon cost of intelligence (CCI), a novel metric enabling workload-specific energy and carbon calculation that balances accuracy and efficiency across heterogeneous domains. This paper presents a comprehensive cross-domain energy benchmark using the massive multitask language understanding (MMLU) dataset, measuring accuracy and energy consumption in five representative domains: clinical knowledge (medicine), professional accounting (finance), professional law (legal), college computer science (technology), and general knowledge. Empirical analysis of GPT-4 across 100 MMLU questions, 20 per domain, reveals substantive variations: legal queries consume 4.3× more energy than general knowledge queries (222 J vs. 52 J per query), while energy consumption varies by domain due to input length differences. Our analysis demonstrates the evolution from simple ratio-based approaches (weighted accuracy divided by weighted energy) to harmonic mean aggregation, showing that the harmonic mean, by preventing bias from extreme values, provides more accurate carbon usage estimates. The CCI metric, calculated using weighted harmonic mean (analogous to P/E ratios in finance, where A/E represents accuracy-to-energy ratio), enables practitioners to accurately estimate energy and carbon emissions for specific workload mixes (e.g., 80% medicine + 15% general + 5% law). Results demonstrate that the domain workload mix significantly impacts carbon footprint: a law firm workload (60% law) consumes 96% more energy per query than a hospital workload (80% medicine), representing 49% potential savings through workload optimization. Carbon footprint analysis using US Northeast grid intensity (320 gCO₂e/kWh) shows domain-specific emissions ranging from 0.0046–0.0197 gCO₂ per query. CCI is validated through comparison with simple weighted average, demonstrating differences up to 12.1%, confirming that the harmonic mean provides more accurate and conservative carbon estimates essential for carbon reporting and neutrality planning. Our findings provide a novel cross-domain energy benchmark for GPT-4 and establish a practical carbon calculator framework for sustainable AI deployment aligned with carbon neutrality goals. Full article

Background/Objectives: Sarcopenia, obesity, and sarcopenic obesity (SO) are common in older adults and may be associated with functional limitations in Basic (BADL) and Instrumental (IADL) Activities of Daily Living. This study aimed to evaluate the association between body composition phenotypes and BADL/IADL limitations among older adults. Methods: A cross-sectional study included 440 community-dwelling adults aged ≥60 years (281 women, 159 men; mean age 74.7 ± 7.8 years). Sarcopenia was diagnosed according to EWGSOP2 criteria, obesity was defined as Percent Body Fat > 42% in women and >30% in men, and SO was classified based on the ESPEN/EASO recommendations. The reference phenotype was ‘non-sarcopenic, non-obese’. Functional status was evaluated using the Katz and Lawton scales, with limitations defined as BADL ≤ 5 and IADL ≤ 26 points, respectively. Multivariate logistic regression was performed to determine associations between body composition phenotypes and BADL/IADL limitations. Results: Over half of the participants (57.1%) had abnormal body composition: 31.6% obesity, 11.4% sarcopenia, and 13.2% SO. Sarcopenic obesity was associated with nearly threefold higher odds of BADL limitations (OR = 2.86; p = 0.003) and 3.7-fold higher odds of IADL limitations (OR = 3.68; p < 0.001), compared to the reference phenotype. Sarcopenia was associated with IADL limitations only in the unadjusted model (OR = 2.44; p = 0.010). Beyond adverse body composition phenotypes, BADL/IADL limitations were also associated with lower muscle strength, multimorbidity, and poorer nutritional status. Conclusions: SO was linked to both BADL and IADL limitations, while sarcopenia was associated only with IADL deficits. Isolated obesity showed no consistent relationship with functional impairment. These findings support prioritizing SO in screening and prevention, although the cross-sectional design precludes causal inference. Full article

Circular–circular regression models are widely used to investigate relationships between angular variables in various applied fields, including biostatistics. The classical von Mises (vM) circular–circular regression model, however, is known to be sensitive to outliers due to its light-tailed error structure. In this study, we investigate the wrapped Cauchy (WC) circular–circular regression model as a robust alternative to the vM-based approach for analyzing circular data contaminated by outliers. Parameter estimation is performed via maximum likelihood (ML) using a modern constrained gradient-based optimization algorithm, namely the limited-memory Broyden–Fletcher–Goldfarb–Shanno algorithm with box constraints (L-BFGS-B), allowing for stable estimation under natural parameter bounds. Extensive simulation studies demonstrate that, under contaminated settings, the WC model provides substantially more stable parameter estimates than the vM model, yielding markedly lower mean squared error and variability, particularly for high concentration regimes and directional outliers. The robustness advantage of the WC model is further illustrated through a real biostatistical application involving the circular relationship between the months of diagnosis and surgical intervention in gastric cancer patients. Overall, the results highlight the practical benefits of WC-based circular–circular regression for robust inference in the presence of outliers. Full article

Ontology learning from unstructured text has become a critical task for knowledge-driven applications in Big Data and Artificial Intelligence. While significant advances have been made in the automatic extraction of concepts and relations using neural and Transformer-based models, the generation of formal Description Logic axioms required for constructing logically consistent and computationally tractable ontologies remains largely underexplored. This paper puts forward a novel pipeline for automated axiom generation through schema mapping. Our paper introduces three key innovations: a deterministic mapping framework that guarantees logical consistency (unlike stochastic Large Language Models); guaranteed formal consistency verified by OWL reasoners (unaddressed by prior statistical methods); and a transparent, scalable bridge from neural extractions to symbolic logic, eliminating manual post-processing. Technically, the pipeline builds upon the outputs of a Transformer-based fusion model for joint concept and relation extraction. We then map lexical relational phrases to formal ontological properties through a lemmatization-based schema alignment step. Entity typing and hierarchical induction are then employed to infer class structures, as well as domain and range constraints. Using RDFLib and structured data processing, we transform the extracted triples into both assertional (ABox) and terminological (TBox) axioms expressed in Description Logic. Experimental evaluation on benchmark datasets (Conll04 and NYT) demonstrates the efficacy of the approach, with expert validation showing high acceptance rates (>95%) and reasoners confirming zero inconsistencies. The pipeline thus establishes a reliable, scalable foundation for automated ontology learning, advancing the field from extraction to formally verifiable knowledge base construction. Full article

Accurate lithologic maps derived from satellite imagery underpin structural interpretation, mineral exploration, and geohazard assessment. However, automated mapping in complex terranes remains challenging because spectrally similar units, narrow anisotropic bodies, and ambiguous contacts can degrade boundary fidelity. In this study, we propose SegNeXt-HFCA, a hierarchical multiscale fusion network with coordinate attention for lithologic segmentation from a Sentinel-2/DEM feature stack. The model builds on SegNeXt and introduces a hierarchical multiscale encoder with coordinate attention to jointly capture fine textures and scene-level structure. It further adopts a class-frequency-aware hybrid loss that combines boundary-weighted online hard-example mining cross-entropy with Lovász-Softmax to better handle long-tailed classes and ambiguous contacts. In addition, we employ a robust training and inference scheme, including entropy-guided patch sampling, exponential moving average of parameters, test-time augmentation, and a DenseCRF-based post-refinement. Two study areas in the Beishan orogen, northwestern China (Huitongshan and Xingxingxia), are used to evaluate the method with a unified 10-channel Sentinel-2/DEM feature stack. Compared with U-NetFormer, PSPNet, DeepLabV3+, DANet, LGMSFNet, SegFormer, BiSeNetV2, and the SegNeXt backbone, SegNeXt-HFCA improves mean intersection-over-union (mIoU) by about 3.8% in Huitongshan and 2.6% in Xingxingxia, respectively, and increases mean pixel accuracy by approximately 3–4%. Qualitative analyses show that the proposed framework better preserves thin-unit continuity, clarifies lithologic contacts, and reduces salt-and-pepper noise, yielding geologically more plausible maps. These results demonstrate that hierarchical multiscale fusion with coordinate attention, together with class- and boundary-aware optimization, provides a practical route to robust lithologic mapping in structurally complex regions. Full article

Modern healthcare systems increasingly depend on wearable Internet of Medical Things (IoMT) devices for the continuous monitoring of patients’ physiological parameters. It remains challenging to differentiate between genuine physiological anomalies, sensor faults, and malicious cyber interference. In this work, we propose a hybrid fusion framework designed to attribute the most plausible source of an anomaly, thereby supporting more reliable clinical decisions. The proposed framework is developed and evaluated using two complementary datasets: CICIoMT2024 for modelling security threats and a large-scale intensive care cohort from MIMIC-IV for analysing key vital signs and bedside interventions. The core of the system combines a supervised XGBoost classifier for attack detection with an unsupervised LSTM autoencoder for identifying physiological and technical deviations. To improve clinical realism and avoid artefacts introduced by quantised or placeholder measurements, the physiological module incorporates quality-aware preprocessing and missingness indicators. The fusion decision policy is calibrated under prudent, safety-oriented constraints to limit false escalation. Rather than relying on fixed fusion weights, we train a lightweight fusion classifier that combines complementary evidence from the security and clinical modules, and we select class-specific probability thresholds on a dedicated calibration split. The security module achieves high cross-validated performance, while the clinical model captures abnormal physiological patterns at scale, including deviations consistent with both acute deterioration and data-quality faults. Explainability is provided through SHAP analysis for the security module and reconstruction-error attribution for physiological anomalies. The integrated fusion framework achieves a final accuracy of 99.76% under prudent calibration and a Matthews Correlation Coefficient (MCC) of 0.995, with an average end-to-end inference latency of 84.69 ms (p95 upper bound of 107.30 ms), supporting near real-time execution in edge-oriented settings. While performance is strong, clinical severity labels are operationalised through rule-based proxies, and cross-domain fusion relies on harmonised alignment assumptions. These aspects should be further evaluated using realistic fault traces and prospective IoMT data. Despite these limitations, the proposed framework offers a practical and explainable approach for IoMT-based patient monitoring. Full article

This paper presents a framework for inverse modeling of microwave filters based on a conditional diffusion model developed to address the intrinsic non-uniqueness of reconstructing coupling matrices from specified S-parameter responses. In the forward diffusion process, Gaussian noise is progressively added to the filter design variables, and a denoising network conditioned on the target electrical responses is trained to predict the injected noise at arbitrary diffusion steps. At inference, we initialize with Gaussian noise and execute the learned reverse denoising dynamics process; independent seeds yield diverse sets of physically feasible design-variable solutions that satisfy identical electrical-response constraints. Experiments on fourth- and sixth-order filters show that the proposed method outperforms multivalued neural networks (MVNNs) and conditional generative adversarial networks (CGANs) in prediction accuracy, solution diversity, and cumulative training cost, thereby providing a robust and efficient framework for inverse microwave-filter modeling. Full article

The Iberá Wetlands in northeastern Argentina constitute the second largest wetland system in South America, yet the fern and lycophyte flora of this region remains poorly documented. The aims of this work were to update the species richness of these plant groups, evaluate the intensity of collecting efforts, identify conservation priorities, estimate the potential true species richness, and make biogeographical inferences. We compiled a database of species from multiple sources, and the study area (21,853 km²) was divided into 19 grid cells for analysis. Sampling effort and species richness were quantified, and non-parametric estimators (Chao2, ICE, Jack2) were used to evaluate inventory completeness. Several similarity analyses were performed using the Jaccard index, incorporating reference areas from the Chaco and Paranaense phytogeographic provinces. The Ituzaingó–La Paz geological fracture and the geological formations present in the area were also considered. We recorded 76 taxa, whereas estimators suggested a potential richness of 130–140 species. The center of the Iberá Wetlands showed the lowest sampling effort, while the eastern sector exhibited the highest species richness. The distribution of species appears to be correlated with geological formations. These findings emphasize the importance of continuing sampling in the area. Full article