Search Results (5,988)

Managing blood glucose in type 1 diabetes (T1D) remains a daily clinical challenge, and accurate short-term prediction of glucose levels can meaningfully improve insulin dosing decisions while reducing the risk of dangerous hypoglycaemic episodes. Although numerous machine learning approaches have been proposed for this task, comparing their relative merits is difficult because published studies differ widely in datasets, preprocessing choices, and evaluation criteria. In this work, we address this research gap by benchmarking ten machine learning methods—from a naïve persistence baseline through classical linear regressors, gradient-boosted ensembles, and recurrent neural networks to a novel hybrid that couples LightGBM with stochastic differential equation (SDE)-based glucose–insulin simulation—on two multi-patient datasets comprising 34 T1D subjects, across prediction horizons of 15, 30, 60, and 120 min. Every method is trained and tested under identical preprocessing and temporal splitting conditions to ensure a fair comparison. The proposed Hybrid LightGBM-SDE model consistently outperforms all alternatives, recording RMSE values of 22.42 mg/dL at 15 min, 28.74 mg/dL at 30 min, 33.89 mg/dL at 60 min, and 37.22 mg/dL at 120 min—an improvement of between 13.6% and 27.0% relative to standalone LightGBM. At the clinically important 30 min horizon, 99.7% of predictions lie within the acceptable A and B zones of the Clarke Error Grid. Wilcoxon signed-rank tests confirm that performance differences are statistically significant (p < 10⁻¹⁰), and SHAP-based analysis shows that the SDE-derived simulation features are among the most influential predictors, especially at longer horizons. All source code and evaluation scripts are publicly released to support reproducibility. Due to temporary data access constraints, all experiments reported here use physics-based synthetic datasets generated from the Bergman minimal model, replicating the structural properties of the D1NAMO and HUPA-UCM collections; validation on the original clinical recordings is planned. Among the two synthetic datasets, the D1NAMO-equivalent cohort (nine patients) proves more challenging, with systematically higher per-patient RMSE variance. The clinically acceptable prediction accuracy at the 30 min horizon (99.7% in Clarke zones A + B) suggests potential for integration into insulin dosing decision-support systems. Full article

Coastal reclaimed areas are characterized by complex strata and high groundwater levels, and pile foundations in such areas often suffer from insufficient uplift resistance. Compared with conventional cast-in-place piles, squeezed branch piles exhibit superior uplift performance; however, studies on squeezed branch piles in reclaimed areas remain limited. To investigate the uplift bearing performance of squeezed branch piles in the complex strata of coastal reclaimed areas, in situ full-scale uplift tests were conducted in the Shenzhen Binhai Avenue (Headquarters Base Section) traffic reconstruction project. Based on the actual physical and mechanical properties of the soil strata, a three-dimensional numerical model was established and validated against the load–displacement curves obtained from the in situ full-scale uplift tests. On this basis, the uplift bearing performance of squeezed branch piles, the differences in uplift bearing performance between branch and plate structures, and their applicable strata were analyzed. The plate structure and different branch configurations of squeezed branch piles exhibit distinct symmetric configuration characteristics, and these configuration differences influence the overall uplift bearing performance. The results show that the load–displacement curves of the uplift piles are generally smooth, without obvious abrupt rises or drops, exhibiting a gradual variation pattern, and the maximum pile-head displacements are all less than 100 mm. The mobilization of the bearing capacity of the branch and plate structures exhibits a distinct temporal and sequential pattern, with the plate structures at shallower embedment depths mobilized earlier than those at greater depths. Compared with conventional cast-in-place pile foundations, the presence of branches and plates endows squeezed branch piles with better elastic mechanical behavior and higher rebound ratios during unloading. Under identical stratum and loading conditions, the uplift bearing performance of the plate is 133% higher than that of the six-radial-branch configuration, while that of the six-radial-branch configuration is 34% higher than that of the four-radial-branch configuration. It is recommended to adopt the six-radial-branch configuration in clayey sandy gravel strata and the plate configuration in gravelly clayey soil and completely weathered coarse-grained granite strata, whereas neither branches nor plates are recommended in soil-like strongly weathered coarse-grained granite strata. Full article

This study examined how perceived social media affordances, self-presentation, and online engagement collectively shape experiences of social validation among Nigerian youths within an integrated framework that combines Affordance theory, Goffman’s Dramaturgical perspectives, and Uses and Gratifications. Using a quantitative survey of 480 active social media users across platforms (Facebook, Instagram, TikTok, and X), data were analysed using descriptive statistics, Pearson correlations, regression, and regression-based sequential mediation modelling. Our findings indicate that perceived social media affordances significantly predict self-presentation behaviours (β = 0.79, p < 0.001), self-presentation significantly predicts online engagement (β = 0.43, p < 0.001); and online engagement predicts perceived social validation (β = 051, p < 0.001). Our findings also reveal that self-presentation and online engagement jointly and sequentially mediate the relationship between perceived affordances and perceived social media validation, with a significant indirect effect (β = 0.13, 95% CI [0.09, 0.19]) and a non-significant direct path from affordances to validation. Within a connectivity-constrained environment of Nigerian youths, our findings support a process-based understanding of digital interaction, showing how technological affordances are translated into social outcomes via structured, theoretically grounded user practices. Apart from validation emerging as a salient gratification, the study noted other motivational cues (sociability, identity expression, and information seeking) behind youth engagement with social media, suggesting that validation is just one of many reasons underlying youth social media use. The study contributes to Global Majority Media scholarship by providing a theoretically integrated process-based framework and a mechanism-oriented narrative of social media use in a non-Western setting. Full article

Clothing classification by occasion is an important area in computer vision and artificial intelligence (AI). This task is particularly challenging because of the subtle visual similarities among clothing categories such as formal, party, and casual attire. Variations in color, fabric, patterns, and lighting further increase the complexity of this task. To address this challenge, we used the Fashionpedia dataset to create a balanced subset of 15,000 images. Specifically, we adopted two different methods for labeling these images: automated classification, which relies on category identifications (IDs) and components, and manual labeling performed by human annotators. We then implemented our preprocessing pipeline, which includes several steps: resizing, image normalization, background removal using segmentation masks, and class balancing. We benchmarked traditional models, including artificial neural networks (ANNs), support vector machines (SVMs), and k-nearest neighbors (KNNs), which use a histogram of oriented gradient (HOG) features, as well as deep learning models such as convolutional neural networks (CNNs), the Visual Geometry Group 16 (VGG16) model utilizing transfer learning, and the vision transformer (ViT) model, all evaluated using identical data splits and preprocessing procedures. The traditional models achieved moderate accuracy, ranging from 54% to 66%. In contrast, the ViT model achieved an accuracy of 81.78% with automated classification and 98.09% with manual labeling. This indicates that a higher label accuracy, along with the preprocessing steps used, significantly enhances the performance. Together, these factors improve the effectiveness of ViT in context-aware apparel classification and establish a reliable baseline for future research. Full article

This study examines the increasing concern regarding teacher job satisfaction, which has a direct impact on retention, instructional quality, and student outcomes. Traditionally, teacher satisfaction has been evaluated through questionnaires, which present limitations in terms of data efficiency and analyses. In this study, machine learning techniques were applied to data from the PISA 2022 teacher questionnaire in Morocco (N = 2998 lower-secondary teachers). Two multiclass classification targets were defined: overall job satisfaction (SATJOB_class) and satisfaction with the teaching profession (SATTEACH_class), each categorised into three balanced classes: low (<−0.5), medium (−0.5 to 0.5), and high (>0.5) classes. The methodology comprised four key stages. Initially, comprehensive pre-processing was conducted to address missing values, retaining features with fewer than 300 missing entries and applying mode imputation. Subsequently, nine classifiers, including logistic regression, K-nearest neighbours, multinomial naïve Bayes, support vector machine, decision tree, random forest, XGBoost, AdaBoost, and a feed-forward Artificial Neural Network, were evaluated using identical train/test splits and hyperparameter tuning. Third, the model performance was assessed using accuracy, precision, recall, and F1-score. Finally, the feature importance was derived from tree-based and permutation methods. The results indicated that XGBoost outperformed the other models for SATJOB_class with an accuracy (0.61), precision (0.62), recall (0.61), and F1-score (0.61), followed by Random Forest (accuracy = 0.59), Logistic Regression (accuracy = 0.59), and AdaBoost (accuracy = 0.59). For SATTEACH_class, Random Forest led with accuracy (0.59), followed closely by XGBoost (0.58), ANN (0.57), and AdaBoost (0.56). Key predictors of teacher job satisfaction included workload-related variables and school-environment factors, which consistently emerged as the most important features across the best-performing models. The methodology and open-source pipeline provide a reproducible framework for evidence-based interventions to improve teacher retention and instructional quality, offering valuable insights for policymakers and educational administrators. Full article

Social media platforms have become critical communication environments during disasters, where individuals express emotions, share information, and engage in public discourse. These platforms also reflect heterogeneous communication patterns shaped by different actor groups. However, existing studies predominantly focus on emotion classification and often overlook the combined role of actor identity and conflict dynamics. To address this gap, this study proposes an integrated AI-based analytical framework for actor-aware emotion and conflict analysis in post-disaster social media. An expert-annotated Turkish tweet dataset was constructed based on Ekman’s emotion model, including anger, fear, sadness, happiness, and surprise, along with an additional irrelevant/off-topic category and conflict-level labels. A Transformer-based model (BERTurk) was fine-tuned for multi-class emotion classification. Experimental results show that the proposed model achieves strong classification performance, with an accuracy of 0.931 and an F1-score of 0.912, outperforming conventional machine learning and deep learning baselines. Actor-based analysis reveals systematic differences in emotional and conflict patterns across groups. Scientists, journalists, and individual users exhibit higher levels of conflict and more pronounced negative emotional expressions, whereas institutionally oriented actors display comparatively balanced and supportive communication patterns. In addition, a web-based decision support system was developed to enable interactive visualization and actor-level exploration of emotional and conflict dynamics. Overall, the proposed framework provides a scalable, analytically robust approach to understanding social media discourse in disaster contexts and offers practical implications for AI-driven crisis communication and decision-support systems. Full article

We investigate the effects of dark matter on the properties of strange quark stars within the framework of general relativity with two fluids coupled only by gravity. Adopting the color–flavor-locked model for strange quark matter and considering both fermionic (free fermion gas) and bosonic (polytropic) equations of state for dark matter, we systematically study the structure and tidal deformability of dark matter-admixed strange stars. Our results show that the presence of dark matter significantly modifies the mass–radius relations, with the maximum mass of dark matter-admixed strange stars exhibiting a non-monotonic dependence on the dark matter mass fraction $\chi$, which reaches a minimum at an intermediate value of $\chi$. The tidal deformability $\Lambda$ of dark matter-admixed strange stars shows complex behavior depending on both the stellar mass and dark matter fraction, with $\Lambda -\beta$ (the compactness parameter) relations deviating from the universal relations observed for pure strange stars or dark stars. Our findings demonstrate that dark matter-admixed strange stars with different configurations but identical masses and radii can be distinguished by their tidal deformabilities, providing potential observational signatures for detecting dark matter in compact astrophysical objects. The results are compared with current astrophysical constraints from gravitational wave observations and pulsar measurements. Full article

Multi-label deep learning models are widely used in real-world applications where predictions depend on the joint presence of several semantically correlated labels. However, existing adversarial attacks largely overlook these inter-label dependencies, often perturbing outputs indiscriminately and producing structurally implausible or easily detectable changes. This paper presents CAPG (Context-Aware Perturbation Generation), a white-box, label-space targeted adversarial framework for generating selective and contextually consistent perturbations in multi-label settings. CAPG incorporates correlation-weighted regularization into the adversarial objective, enabling targeted manipulation of specific labels while preserving the contextual integrity of non-target outputs. Using the Pascal VOC 2012 dataset and a ResNet-101 multi-label classifier, we show that CAPG achieves higher Attack Success Rates (ASR) and substantially improved Contextual Consistency Scores (CCSs) than FGSM, PGD, CW, and DeepFool under identical perturbation budgets. CAPG also produces lower perceptual distortion, yielding adversarial examples that better preserve contextual structure. These results highlight the importance of correlation-aware adversarial evaluation for assessing the robustness of modern multi-label deep learning systems. Full article

Neural network-based visual identification of animals has significant potential for livestock farming and herd management. Real farm environments rarely provide controlled visual conditions for high-quality dataset collection, which often leads to reduced model performance on out-of-distribution inputs and makes confidence estimation essential for reliable application. This work introduces a conformal prediction framework for animal identification based on pretrained neural network embeddings (ResNet-50 and Swin Transformer), enabling the generation of prediction sets with formal confidence guarantees. By calibrating a nonconformity score derived from cosine distances in the embedding space, the method ensures that the true identity is included in the prediction set at a user-defined confidence level. Three nonconformity scoring functions are evaluated to determine which produces the most compact prediction sets. Experiments on cow and goat datasets demonstrate that the framework achieves empirical coverage close to the target confidence levels across different embedding models. The ratio-based nonconformity measure consistently outperforms others, reducing mean set sizes by up to 79% compared to alternative measures. Swin-T embeddings outperform ResNet-50 by up to 14 percentage points in singleton prediction rate. The proposed framework preserves formal validity guarantees, improving robustness and interpretability in practical livestock applications where standard identification methods return only the nearest match without reliability estimates. Full article

This research investigates the influence of environmental regulation on subjective evaluations of video quality within the Quality of Experience (QoE) paradigm. This work presents a supplementary experiment conducted in a controlled laboratory setting, building on our previous crowdsourcing studies carried out in uncontrolled, web-based conditions using the Prolific platform. Both tests utilized the identical crowdsourcing platform and complied with the International Telecommunication Union Telecommunication (ITU-T) P.910 Recommendations, ensuring external validity and methodological consistency. Participants assessed a collection of processed video sequences (PVS) comprising 46 distinct video clips utilizing the 5-point Absolute Category Rating (ACR) scale, while their response times were documented in milliseconds as measures of cognitive exertion and decision delay. The comparison analysis employs nonparametric tests (Mann–Whitney U and Kolmogorov–Smirnov) and a hierarchical Linear Mixed-Effects Model (LMM) to examine disparities in reaction time distributions, rating consistency, and the incidence of outliers across both environments. The results indicate that controlled settings produce statistically significantly less response variability and enhanced data reliability, whereas uncontrolled settings encompass greater external diversity and real-world unpredictability. These findings offer significant insights into the balance between experimental control and external validity in crowdsourced video quality assessment, advancing the development of scalable approaches for Quality of Experience research. Full article

Docker systems are gaining widespread use due to their consistency, scalability, and ease of application portability, which addresses specific security challenges. Traditional monitoring and intrusion detection systems based on predefined rules often struggle with advanced attack patterns due to a lack of the capability to correlate incoming log messages. This paper proposes a correlation-aware log analysis approach based on a Mixture-of-Experts (MoE) large language models, enabling detection of malicious activity by analyzing both individual log entries and their contextual relationships within sequences of logs. The system processes each log in the context of 50 preceding messages, allowing identification of attack patterns that are not observable from isolated logs. To evaluate the approach, we generated a comprehensive dataset based on OWASP Top 10 attack scenarios, enriched with zero-day attacks such as Log4j and React2Shell, deployed in a distributed Docker Swarm environment. Multiple LLMs were evaluated under identical hardware conditions to ensure fair comparison. Experimental results demonstrate that while most models achieve comparable performance on single-log detection, significant differences emerge in contextual analysis. The proposed MoE-based approach demonstrates superior effectiveness, achieving an F1 score from 0.993 to 0.998 for contextual-log analysis. The contribution of this research is the novel use of MoE LLMs for log analysis, the distinct novel attack log dataset, and the unique framework based on offline technology that conserves hardware resources and data privacy. Full article

Harmonic reducers exhibit non-stationary and phase-dependent degradation behavior during long-term service, challenging the ability of classical stochastic degradation models to accurately assess reliability. To address phase-dependent differences in degradation behavior, this paper proposes a reliability assessment model based on a two-phase hybrid stochastic degradation process. In the proposed framework, the Wiener process is employed to characterize early-phase gradual degradation dominated by stochastic fluctuations, while the Inverse Gaussian process is used to describe later-phase monotonically accelerated degradation driven by cumulative damage. The framework allows for sample-level variability in transition times to more realistically capture individual degradation behavior. The Schwarz Information Criterion is also adopted to detect change points. Maximum likelihood estimation is performed for model parameter inference, and analytical expressions for the reliability function, cumulative distribution function, and probability density function are derived. Numerical results indicate that a change point exists for each tested product and that the proposed model achieves the best goodness of fit among the considered candidates, demonstrating its superiority in capturing phase-dependent characteristics of harmonic reducer degradation. In terms of reliability assessment bias, the proposed model (0.06%) significantly outperforms the Wiener degradation model (32%) and the IG degradation model (9.9%). These results further confirm that, under an identical failure threshold, the proposed approach yields more accurate and realistic reliability assessment outcomes. Full article

Title-abstract screening remains labour-intensive, especially in interdisciplinary domains where shared terminology increases misclassification risk. This study compared five LLM coordination strategies—single-agent baseline, majority voting, recall-focused ensemble, confidence-weighted aggregation, and two-stage filtering—using four 4-bit quantised open-source models (Mistral 7B, LLaMA 3.1 8B, Granite 3.3 8B, Qwen 2.5 7B) in zero-shot and few-shot configurations. The evaluation was conducted on a Gold Standard of 200 papers from a corpus of 2036 records on blockchain-based e-voting. The best-performing configuration—a single-agent strategy with Qwen 2.5 7B in few-shot mode—achieved recall of 100%, precision of 70.4%, F1 of 82.6%, and a 43.4% reduction in manual screening effort, outperforming all multi-agent alternatives. Confidence-weighted aggregation produced results identical to majority voting, indicating that self-reported confidence from 7–8B parameter models did not add discriminative value. All screening decisions were logged on a private blockchain with timestamped anchoring for reproducibility. These results suggest that, for domain-specific screening tasks, careful model selection outweighs multi-agent coordination overhead, and that few-shot prompting with a well-matched model can achieve human-level recall with substantially reduced manual effort. Full article

Prostate cancer, particularly metastatic castration-resistant prostate cancer (mCRPC), presents therapeutic challenges rooted in adaptive lineage plasticity and neuroendocrine transdifferentiation. Conventional genome-based models fail to account for the divergent clinical trajectories observed among tumors that share identical driver mutations. This limitation requires reconceptualizing cancer as a dynamic system in which tumor cells can execute context-dependent molecular programs governed by epigenetic and transcriptional network remodeling. This review critically evaluates three convergent technological pillars reshaping prostate cancer research and clinical care. First, conditional reprogramming (CR) enables the rapid generation of patient-derived models that preserve genomic fidelity, intratumoral heterogeneity, and reversible phenotypic plasticity without genetic manipulation. Second, single-cell and spatial multi-omics approaches have clarified the cellular trajectories underlying luminal-to-neuroendocrine transdifferentiation, identifying a therapeutically actionable intermediate state. They have revealed the hierarchical transcription factor network (FOXA2–NKX2-1–p300/CBP) which orchestrates chromatin remodeling during this lethal transition. Third, physics-informed machine learning and digital twin architectures aim to move beyond correlative risk prediction toward mechanistically sound forecasting of tumor evolution, treatment response, and resistance emergence. We address unresolved challenges in prospective clinical validation, spatial heterogeneity capture, regulatory pathways for functional diagnostics, and the imperative for causal, as opposed to associative, inference from perturbational datasets. The integration of these three domains through closed-loop experimental–computational feedback cycles represents a paradigm shift from reactive to anticipatory precision oncology. Full article

Understanding individuals’ connection to nature is crucial for promoting sustainable attitudes and behaviors. The environmental identity (EID) scale, widely used to assess this connection, plays a key role in environmental research; however, its cross-cultural application requires rigorous psychometric validation. Although the revised 14-item EID scale has demonstrated good reliability, questions remain regarding its dimensionality and the potential influence of acquiescence due to exclusively positive worded items. This study examined both issues in Portuguese samples. In Study 1, exploratory and confirmatory factor analyses were conducted to test the factorial structure. Results supported a two-factor model with correlated dimensions: Restorative Connection to Nature (RCN) and Ecological Identity (EI), rather than a strictly unidimensional solution. In Study 2 acquiescence was assessed by comparing the original version with a balanced version that included partially reverse-worded items. Item distributions, factor loadings, and reliability were analyzed. The balanced version did not improve control of acquiescence; instead, reversed-worded items showed weaker loadings, lower explanation variance, and method effects, suggesting increased measurement bias. Overall, the findings support the robustness of the revised 14-item EID scale in Portugal while indicating that environmental identity is better conceptualized as a bidimensional construct portraying both reflective connection and identity-based engagement with nature. The results also highlight the limitations of reverse-worded items as a strategy for reducing response bias in value-laden constructs. Full article