Search Results (5,238)

Background/Objectives: Low back pain (LBP) is a leading cause of disability worldwide and is influenced by multiple biological and functional factors. While pain intensity is a well-established determinant of disability, the contribution of body composition and relative skeletal muscle mass remains insufficiently understood. This study aimed to investigate the associations between body composition parameters, Muscle-to-Weight Ratio (MWR), pain intensity, and functional disability in patients with LBP and to explore sex-related differences in these variables. Methods: A cross-sectional observational study was conducted in 98 adults with chronic non-specific LBP recruited from a rehabilitation department in Romania. Anthropometric and body composition measurements were obtained using bioelectrical impedance analysis (BIA). Pain intensity was assessed using the Visual Analogue Scale (VAS), and functional disability was evaluated using the Roland–Morris Disability Questionnaire (RMDQ). The MWR was calculated as skeletal muscle mass divided by body weight and expressed as a percentage. Sex comparisons, correlation analyses, and multiple linear regression analyses were performed. Results: The mean age of participants was 61.9 ± 10.0 years, and 53.1% were female. Female participants reported significantly higher pain intensity than males (60.5 ± 31.0 vs. 44.2 ± 35.5; p = 0.021) and demonstrated a different distribution of disability severity categories compared with males (Fisher–Freeman–Halton exact p = 0.021). Pain intensity showed the strongest positive correlation with disability (r = 0.56, p < 0.001), whereas MWR was negatively correlated with disability (r = −0.34, p = 0.001). In multivariable regression analysis, pain intensity (β = 0.49, p < 0.001), age (β = 0.22, p = 0.013), and MWR (β = −0.27, p = 0.018) remained significantly associated with disability after adjustment for sex and body fat percentage. The model explained 43.2% of the variance in RMDQ scores (R² = 0.432). Conclusions: Pain intensity, age, and MWR were significantly associated with functional disability in patients with chronic non-specific LBP. Lower MWR values were associated with greater disability after adjustment for age, sex, body fat percentage, and pain intensity. These findings suggest that assessment of body composition and MWR may provide additional information when evaluating patients with chronic non-specific low back pain. However, the cross-sectional design precludes conclusions regarding causality. Full article

To address the sampling misalignment and detail loss caused by fixed-grid downsampling for small-scale defects, as well as the insufficient differentiated modeling and interaction of defect details and structural context in UAV-acquired power-line images, an enhanced lightweight YOLOv8n-based framework for power-line defect detection is developed. First, a content-adaptive downsampling (CAD) module is developed to predict input-dependent sampling offsets and normalized aggregation weights and to perform differentiable resampling. Combined with local-global interactive depthwise separable convolution, CAD improves the preservation of small-object details while maintaining relatively low computational complexity. Second, a dynamic subspace gated exchange (DSGE) module is proposed to adaptively partition features into a high-frequency detail subspace and a low-frequency structural subspace according to the input content. Heterogeneous branches and bidirectional gated exchange are then employed to jointly model fine-grained details and structural context. In addition, the lightweight mixed local channel attention (MLCA) mechanism is incorporated in the detection head as an auxiliary feature-enhancement component. Experimental results show that the proposed model achieves mAP@0.50 and mAP@0.50:0.95 values of 92.3% and 62.9%, respectively, outperforming the compared models under the current evaluation protocol. With 1.90 M parameters and 5.6 G FLOPs, the model reaches an inference speed of 134.7 FPS on the desktop GPU platform, demonstrating that content-adaptive sampling and dynamic detail–structure interaction can improve small-defect detection and complex-background suppression while maintaining relatively low model complexity. Full article

To address the recognition challenges caused by the high proportion, low resolution, and significant multi-scale variations of small objects in UAV small-object detection tasks, a UAV small-object detection and recognition algorithm based on CEF-YOLOv8n is proposed. The proposed algorithm uses YOLOv8n as the baseline network and introduces a Partial Convolution-based Cross Partial Feature (CPF) module into the backbone network to enhance the local feature extraction capability for low-resolution small objects. In the neck network, the concept of feature focusing and diffusion is adopted to construct a Focusing Generalized Feature Pyramid Network (FGFPN). A Feature Semantic Fusion Module (FSFM) based on a cross-attention mechanism is designed to complementarily fuse shallow detail features with deep semantic features, thereby enhancing information interaction among objects at different scales. In addition, a Lightweight Weight-Sharing Detection Head (LWSD) is proposed to improve the computational efficiency and real-time performance of the model while maintaining detection accuracy. Publicly available datasets are used for network training and detection evaluation, and comparative experiments are conducted with other algorithms. The results show that the proposed detection and recognition algorithm achieves 37.6% and 22.6% in terms of mAP50 and mAP50-95, respectively, representing improvements of 3.4 and 2.6 percentage points over the original YOLOv8n. Meanwhile, the number of parameters and FLOPs are reduced from 3.2 M and 8.7 G to 2.5 M and 6.9 G, respectively. Full article

Reliable pore detection in in situ monitoring is essential for quality control in additive manufacturing, particularly in safety-critical applications. However, existing automated approaches often struggle with low-quality images, computational inefficiency, and the lack of reliable uncertainty estimates to identify the pores accurately. To address these limitations, this paper proposes U-SAMNet, an Uncertainty-Aware Self-Attention Multi-Task Network. The model jointly performs pore segmentation, image-level classification, and denoising on in situ monitoring images, while deriving epistemic uncertainty via Monte Carlo dropout variance to dynamically suppress unreliable attention features. This study uses electron-optical (ELO) images from the E-PBF process. A novel Uncertainty Guidance Attention (UGA) block is introduced. It suppresses channel attention weights using inverted uncertainty estimates. Unlike prior methods that modulate classification weights, U-SAMNet operates on pixel-wise feature maps. The model has only 1.69 M parameters. A single forward pass takes 17.46 ms per image, while uncertainty estimation is performed through multiple Monte Carlo dropout passes. The model was evaluated on real E-PBF images and achieved 99.42% pixel accuracy, 85.31% F1-score, and 74.38% IoU on a held-out test set of 43 real images. It also generalizes to other industrial defect detection benchmarks, reaching 85.09% F1-score on DAGM 2007 and 82.32% on DeepCrack. GAN-synthesized training data improves the F1-score by 21.34 percentage points over rotation augmentation alone. Ablation studies confirm that each component contributes meaningfully to the final performance. Full article

Background: Electroencephalographic (EEG) recordings simultaneously contain information about neurophysiological dynamics and subject-specific characteristics. While this duality may enable biomarker discovery and individual identification, it also raises concerns that machine-learning models may achieve high predictive performance by exploiting subject identity rather than physiologically relevant information. Methods: In this study, we investigated whether generalized weighted ordinal patterns (GWOP), a statistical-complexity representation incorporating both temporal ordering and amplitude fluctuations, support sleep-stage classification while minimizing identity-related confounding. Sleep EEG recordings from 31 healthy subjects were segmented into 30-s epochs and represented using 3150 GWOP features derived from multiple embedding dimensions, time delays, and entropic indices. XGBoost classifiers were evaluated under intra-subject and inter-subject validation schemes to quantify the impact of EEG fingerprinting on sleep-stage classification performance. An additional subject-identification analysis was conducted using the same feature representation. Results: Sleep-stage classification generalized well to previously unseen subjects, with accuracy decreasing only from 79.2% to 75.8% between intra-subject and inter-subject evaluations. Feature-importance analysis using SHAP revealed an almost perfect correspondence between the features driving classification in both validation schemes (Spearman $\rho =0.998$). Conclusions: While this suggests that the models effectively generalize across subjects without being heavily confounded by individual identities, it indicates a framework of partial separation rather than complete orthogonality across the global feature space. In contrast, GWOP features also supported subject identification with 63.9% accuracy across the 31 individuals, demonstrating that GWOP preserve substantial fingerprinting information. The most informative features for subject identification showed little overlap with those governing sleep-stage classification, suggesting a partial separation between identity-related and biomarker-related information within the same feature space. These findings suggest that EEG fingerprinting and biomarker extraction are not necessarily competing objectives and support GWOP-based statistical-complexity measures as a promising proof-of-concept framework for robust sleep EEG analysis, serving as a foundation for future scale-up precision-neuroscience applications. Full article

Accurate and timely identification of slippery road surfaces is essential for ensuring driving safety and operational efficiency on highways. However, blurred vehicle-background boundaries, uneven illumination, and water splashing caused by passing vehicles make existing image-based recognition methods prone to low accuracy. To address these challenges, this paper proposes an improved SegFormer-based framework with two task-specific innovations: (1) a novel Guided Multi-scale Fusion (GMF) module for task-guided multi-scale feature integration, designed to incorporate auxiliary information such as vehicle type, relative speed, and splash regions, enabling the network to focus on slipperiness-relevant road areas while suppressing background interference; and (2) an improved Boundary Attention Awareness (BAA) module with directional Sobel-based boundary initialization, which provides explicit geometric priors to preserve fine boundary details and reduce ambiguity in slippery regions with irregular or weak edges. A multi-scale input and enhancement strategy is further adopted, along with a weighted combination of cross-entropy loss and Dice loss to mitigate class imbalance. Experimental results on our self-constructed Guangzhou Beierhuan Expressway dataset achieve an mIoU of 95.80%, accuracy of 97.84%, and F1-score of 97.86%. To verify cross-domain generalization, we further evaluate the model on two additional benchmarks: it achieves an mIoU of 93.51% on the synthetic SYN-UDTIRI dataset, and attains an mIoU of 95.80% with an AmIoU of 76.20% on the public Cityscapes dataset, achieving competitive performance against several mainstream architectures. The proposed method offers considerable application potential for highway safety warning systems. Full article

Ransomware detection remains challenging because modern variants exhibit diverse, elusive, and partly benign behaviors and can propagate rapidly across interconnected enterprises and sensor-enabled cyber-physical systems, causing cascading operational failures. These characteristics undermine signature-based and static-detection methods. Although machine learning has improved detection, many approaches still rely on fixed objectives that weight samples uniformly, limiting their adaptation to heterogeneity and overlaps between ransomware and benign activities. To address this challenge, we introduce TL-RL-FusionNet, a reinforcement learning (RL)-guided hybrid framework that combines dual transfer learning (TL) backbones, EfficientNetB0 and InceptionV3, with a lightweight residual multi-Layer perceptron (MLP) classifier. The framework converts sandbox reports into RGB grids, extracts features using frozen CNN backbone networks, and fuses embeddings for classification. Training is guided by a tabular Q-learning sample-weighting agent, formulated as a per-sample bandit over discrete weight actions. To prevent cross-fold information leakage, the Q-table is freshly initialized in each cross-validation fold and updated only using the fold-local training partition, whereas the held-out fold is used for the final evaluation. The framework was evaluated using two datasets. On our dataset, TL-RL-FusionNet achieved the best overall performance on Dataset 1, with 99.20% accuracy, 99.40% recall, and 99.84% AUC. On the public EldeRan benchmark, it achieved 90.36% accuracy using the full dynamic feature space and 92.08% using a Mutual Information-selected compact subset. Paired Wilcoxon tests across five folds were used to assess the RL contribution, while additional grid-order sensitivity analysis showed that the image-based representation remained robust under five random 10 × 10 feature-grid permutations. Interpretability analysis using t-distributed stochastic neighbor embedding (t-SNE) and gradient-weighted class activation mapping feature-grid mapping further showed that the model captured discriminative behavioral patterns. Overall, these results demonstrate that RL-guided sample reweighting improves adaptive ransomware detection while maintaining efficiency and interpretability. The dataset and supporting code are publicly available on GitHub. Full article

Accurate short-term electrical load forecasting is of paramount importance for economic dispatch, reliable grid operation, and efficient demand-side management. However, hybrid forecasting frameworks constructed with deep learning models exhibit strong sensitivity to hyperparameter settings. Moreover, swarm-intelligence optimization algorithms are prone to premature convergence when tuning the hyperparameters of forecasting models, thereby degrading prediction performance. In addition, complex load sequences contain local fluctuations and key temporal segments that are difficult to capture using a single recurrent architecture. To address these challenges, this paper proposes a short-term electrical load forecasting method based on a BiGRU-Attention network optimized by an improved multi-strategy black-winged kite algorithm (IMBKA). The BiGRU extracts bidirectional temporal dependencies from historical load windows, while the attention module assigns adaptive weights to informative time steps and suppresses redundant historical information. To improve hyperparameter optimization, IMBKA introduces Sobol sequence initialization and adaptive elite differential mutation. Sobol sequence initialization enhances population coverage, and adaptive elite differential mutation strengthens information exchange among high-quality individuals. Experimental results on electrical load datasets from Singapore, Australia, and Belgium show that IMBKA-BiGRU-Attention achieves favorable forecasting performance among the compared models. The proposed model obtains RMSE values of 70.07 MW, 159.49 MW, 231.82 MW, and 163.43 MW in the Singapore, Australian, Belgian weekday, and Belgian weekend experiments, respectively. Compared with the best-performing model among the evaluated baselines in each experiment, the RMSE is reduced by 4.65%, 16.48%, 3.34%, and 11.39%, respectively. Full article

Accurate classification of cells from body fluid specimens can support cytological analysis, but microscopic images often present challenges such as low contrast, unclear boundaries, staining variation, class imbalance, and overlapping morphology. This study evaluated the impact of image enhancement techniques on deep learning-based multi-class classification of body fluid cells. The dataset comprised 7071 microscopic images from Srinagarind Hospital, Thailand, annotated by expert technologists. After preprocessing and cell extraction, 22,062 single-cell images across 13 cell types were obtained. A 70:30 train–test split was used, with augmentation and random undersampling applied only to the training set. Nine individual enhancement filters and five combined settings were tested using MobileNetV3, DenseNet121, ResNet50, and EfficientNetB3. Performance was measured using weighted accuracy, precision, recall, and F1-score. DenseNet121 with Edge Enhance achieved the best individual-filter performance (accuracy 83.36%, F1-score 83.08%). For combined settings, DenseNet121 with CLAHE followed by Detail performed best (accuracy 83.01%, F1-score 82.54%), though it did not surpass the top individual filter. Multi-step enhancement provided limited additional benefit. Class-wise results showed strong performance for distinct cell types, while macrophages, monocytes, and lymphocytes remained challenging. Grad-CAM visualization further indicated that model attention was generally concentrated on relevant cellular regions, including nuclei, cytoplasm, and cell boundaries. Overall, selected enhancement techniques offer modest improvements, but effectiveness depends on model architecture and data characteristics. As this study used a single-institution dataset without external validation, the approach should be considered an assistive framework rather than a clinically validated diagnostic system. Full article

Phased-array radar networks require real-time collaborative scheduling of search, tracking, and identification tasks under coupled resource, beam, time-window, and power constraints. Current decisions affect future residual power, task refresh intervals, and tracking uncertainty, making long-horizon scheduling particularly challenging. This paper proposes CS-Mamba, a long-horizon constraint-aware collaborative scheduling framework for homogeneous multiple phased-array radars. The scheduling problem is formulated as a finite-horizon constrained decision process with structured hybrid actions, where the discrete component represents radar–task matching and the continuous component represents transmit-power allocation. A Mamba-based temporal encoder is introduced to summarize long scheduling histories with linear sequence complexity. Based on the encoded representation, the scheduler predicts task priorities, constructs a masked radar–task bipartite graph, solves a constrained maximum-weight matching problem, and projects raw transmit powers onto the feasible power domain. In addition, an action-dependent radar model is incorporated to link transmit power, effective SNR, detection probability, measurement noise, and tracking covariance. The model is trained using behavioral cloning from constraint-aware heuristic trajectories followed by actor–critic fine-tuning. Experiments on the proposed MRSched-Bench show that CS-Mamba improves the normalized cost-effectiveness score from 0.62 to 0.78 compared with MAPPO in the Medium scenario, while reducing end-to-end decision latency from 24.5 ms to 12.8 ms per step. Additional ablation studies verify the contributions of temporal encoding, structured matching, feasible power projection, and two-stage training. Full article

Sunflower pectin is widely used as a food additive due to its gelling and stabilizing properties. However, its bioactive potential remains poorly understood. Here, we explored its effect on defecation. Using a diphenoxylate-induced constipation mouse model, we found that native sunflower pectins did not significantly promote defecation. Subsequently, we investigated whether they could be activated via biotransformation. For this, we enzymatically hydrolyzed the pectin and produced a number of fragments that covered a wide range of molecular weights (0.5 to 30 kDa) in two esterification states (0% and 10% methyl esterification). Interestingly, all fragments exhibited defecation-promoting effects. Moreover, the effect progressively increased as the molecular weight decreased, a trend that was observed with both esterified and non-esterified fragments. Comparative studies identified E3 as the most effective fraction. E3 also displayed a prebiotic effect in the gut of model mice. Structural analysis indicated that E3 comprises oligogalacturonides with degrees of polymerization from one to six, mainly DP3 and DP4. Overall, our study reveals an inverse correlation of molecular weight with defecation-promoting activities, and offers a simple and scalable approach to convert ineffective pectin into effective oligogalacturonides that have the potential to become functional food ingredients. Full article

Volatile fingerprints provide useful information for characterizing Astragali Radix (AR), a food–medicine homologous plant material, but differences among wild, wild-simulated, and cultivated samples remain unclear. In this study, headspace solid-phase microextraction coupled with gas chromatography–mass spectrometry (HS-SPME-GC–MS) and headspace gas chromatography–ion mobility spectrometry (HS-GC–IMS) were integrated with multivariate analysis and interpretable machine learning to characterize volatile profiles and identify candidate discriminatory compounds in 117 AR samples from different cultivation patterns. HS-SPME-GC–MS tentatively identified 29, 34, and 45 volatile compounds in wild, wild-simulated, and cultivated samples, respectively. Esters were the predominant class in all groups, although the relative abundance of esters and the overall chemical-class composition varied among cultivation patterns. HS-GC–IMS tentatively identified 57, 50, and 55 compounds, respectively, comprising mainly low-molecular-weight aldehydes, alcohols, and ketones and thereby providing complementary volatile fingerprint information. Partial least squares discriminant analysis (PLS-DA) showed that the volatile fingerprints captured cultivation-pattern-associated differences, with the HS-GC–IMS model showing clearer group separation. Random forest, support vector machine, and CatBoost models were further constructed using the HS-SPME-GC–MS profiling results. By integrating variable importance in projection (VIP) and SHapley Additive exPlanations (SHAP) values, γ-hexalactone, methyl eugenol, methyl (9Z,11E)-octadeca-9,11-dienoate, eugenol, and ethyl linoleate were selected as candidate discriminatory compounds. Based on the HS-GC–IMS results, 1-octen-3-one, pentyl acetate, (Z)-2-penten-1-ol, 2-heptanone, and the monomeric signal of 2-ethyl-6-methylpyrazine were also identified as candidate discriminatory compounds. These compounds may be related to fatty acid-derived metabolism, aromatic secondary metabolism, and terpenoid-related processes. The integration of two complementary volatile-analysis platforms with VIP- and SHAP-based interpretation provided broader coverage of volatile features and improved the interpretability of candidate-compound screening. These findings provide an interpretable analytical workflow and candidate discriminatory compounds that may support future rapid screening, cultivation-pattern authentication, and volatile-profile-based differentiation of AR, pending independent external validation. Full article

In the context of China’s carbon peaking and carbon neutrality goals, clarifying whether the Yellow River Basin can achieve a decoupling of economic growth from carbon emissions and sustain regional development through deep decarbonization is critical to both ecological protection and high-quality development of the region. This study integrates the Tapio decoupling model, the geographically and temporally weighted regression (GTWR) model, and an author-developed LEAP-YRB v5 macro-sectoral hybrid model to examine 95 prefecture-level cities from 2010 to 2022 and to project energy consumption and carbon emissions for the nine YRB provincial-level regions from 2022 to 2060. The results show that: (1) the urban decoupling status fluctuated among expansive coupling, strong decoupling, and weak decoupling, with weak decoupling becoming dominant and increasing to 62 cities in 2022; (2) per capita GDP and urbanization tended to increase the decoupling index and therefore inhibited decoupling, whereas more intensive construction-land use promoted decoupling, and industrial structure upgrading and green patents showed context-dependent effects; and (3) the basin cannot peak its emissions under the business-as-usual scenario, while the policy-driven scenario peaks at approximately 3.357 billion tons of CO₂ around 2030. Under the carbon-neutrality-oriented scenario, net emissions decline substantially to 825 million tons by 2060, indicating deep decarbonization but not full carbon neutrality. Full neutrality would require additional carbon sinks, cross-regional clean-electricity integration, stronger power-sector decarbonization, or negative-emission technologies beyond the endogenous measures represented in the model. Full article

Expanded Polystyrene (EPS) offers a viable pathway for balancing the fresh and hardened properties of infrastructure with environmental sustainability. This study evaluated six concrete mixes with varying EPS Styrofoam aggregate ratios and three water-to-binder (w/b) ratios, all of which incorporated silica fume and a superplasticizer. Eight machine learning (ML) algorithms (SVMs, GPR, ANNs, etc.) and a deep-learning LSTM model were utilized to preliminarily predict trends in EPS concrete properties. The experimental results indicated that the fine aggregate replacement outperformed the coarse aggregate replacement, retaining approximately 76% of the density of the control mixture, along with other property reductions. The fine aggregate replacement resulted in a compressive strength reduction of up to 46.4%, with losses in tensile strength of 20.9% and an improvement in workability of 3.4%. Finally, various Artificial intelligence (AI) models identified trends in the predictions of EPS properties based on the mixing ratio within a limited experimental dataset. In addition, explainable AI with SHAP analysis, quantifying feature contributions, ensured that the coarse aggregate replacement exerted a more significant negative impact on the mechanical properties and density than the fine aggregate replacement. Although these mixtures offer significant weight reduction, their use in structural applications requires further verification, as the reduction of nearly half of the compressive strength is significant. These findings provide strategies and a framework to facilitate the precise practical application of EPS concrete in nonstructural or lightly loaded applications. Full article

Depressive symptoms among university students are a growing public health concern, motivating unobtrusive monitoring with smartphone-based digital phenotyping. This study examined whether passively collected behavioral features can identify elevated depressive symptom risk. We collected smartphone sensing data from 36 university students over two weeks, yielding 551 participant-days. We extracted 21 digital phenotyping features, including 14 additional behavioral features and 7 baseline features. Multiple machine learning models were evaluated using repeated bootstrap validation, and participant-independent generalization was further assessed with Leave-One-Subject-Out (LOSO) validation. We also examined PHQ-9 thresholds, class-imbalance mitigation, and feature importance using SHAP. Tree-based ensemble models achieved the best performance under bootstrap validation, and the proposed feature set consistently outperformed the baseline set. However, performance dropped substantially under LOSO validation, indicating that participant-independent generalization remains challenging. Class weighting and SMOTE did not meaningfully improve performance. SHAP analysis identified home-stay behavior and time-of-day smartphone use as the most influential predictors. These findings highlight that participant-independent prediction remains challenging and underscore the importance of rigorous participant-level validation when developing smartphone-based digital phenotyping models. Full article