Search Results (29,145)

Subalpine grasslands represent highly sensitive ecosystems that are increasingly exposed to climate extremes, yet their long-term disturbance dynamics remain poorly documented. This study investigates climate-driven dieback of subalpine grasslands in Central Europe using a harmonized, multi-decadal satellite time series. We analyzed Landsat (TM, ETM+, OLI, OLI-2) and Sentinel-2 imagery spanning 1984–2024 to detect changes in grassland condition, supported by field-based validation, climatic indices, and geomorphological analysis. Several spectral indices related to non-photosynthetic vegetation were evaluated, with the Normalized Burn Ratio (NBR) providing the best discrimination of dead grassland. In spatially grouped cross-validation, NBR achieved very high accuracy for dead versus non-dead grassland, with AUC = 0.9996, precision = 1.00, recall = 0.82, and F1-score = 0.90 for Sentinel-2, and AUC = 0.9982, precision = 1.00, recall = 0.62, and F1-score = 0.76 for Landsat 9. Retrospective mapping revealed four dieback events since 2000: two short-term episodes with rapid within-season recovery (2000, 2003) and two long-term events characterized by persistent degradation and slow regeneration (2012, late 2018–2019). The largest short-term event, in 2003, affected 42.19 ha of total dieback and 96.95 ha including partially damaged or regenerating grassland. Dieback extent was negatively associated with water balance deficit, strongest for SPEI-12 (ρ = −0.548, p = 0.002), while winter frost under shallow-soil conditions likely contributed to long-term damage in 2012. Geomorphological analysis indicated that elevation, terrain curvature, and, to a lesser extent, wind exposure are the primary controls on dieback susceptibility, highlighting the importance of fine-scale environmental controls. Our results demonstrate the value of long-term, multi-sensor satellite observations for detecting and interpreting climate-driven disturbances in subalpine grasslands and provide a transferable framework to support monitoring and conservation of mountain ecosystems under ongoing climate change. Full article

Introduction: Colorectal cancer remains a leading cause of cancer-related morbidity and mortality, with adenomatous polyps representing a common precursor. Post-polypectomy polyp recurrence represents a significant risk of colorectal cancer, driving periodic colonoscopy surveillance and polypectomy as needed. In this study, we explore a multimodal machine learning approach that integrates endoscopic imaging with clinical and pathology data to improve recurrence risk prediction and support individualized surveillance planning. Methods: We developed and evaluated a multimodal artificial intelligence (AI) model to predict post-polypectomy colorectal polyp recurrence using the ERCPMP-v5 dataset. The cohort included 217 patients with 796 high-resolution endoscopic RGB images and 21 endoscopic videos; video data were converted to still frames at 2 frames per second. Images and frames were resized to 224 × 224 pixels and normalized. Patient-level demographic, morphological (Paris, Kudo Pit, JNET), anatomical, and pathological variables were encoded using standard scaling for continuous features and one-hot encoding for categorical features. Visual representations were extracted using a pretrained Vision Transformer backbone (ViT-Base-Patch16-224) with frozen weights. Structured metadata (79 variables) was encoded using a multilayer perceptron. A late fusion framework used image and metadata representations to generate a recurrence probability via a sigmoid classifier; probabilities were thresholded at 0.5 for binary prediction. Model performance was evaluated on a held-out test set using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). We additionally compared fusion performance with image-only and metadata-only baselines. Predicted probabilities were translated to surveillance recommendations using risk tiers: low risk (0.00 ≤ p < 0.20), moderate risk (0.20 ≤ p < 0.50), and high risk (p ≥ 0.50). Results: On the test set, the multimodal fusion model achieved 90.4% accuracy, 86.7% precision, 83.1% recall, 84.9% F1-score, and an AUC of 0.920. The image-only model achieved 84.6% accuracy (AUC 0.880), and the metadata-only model achieved 81.9% accuracy (AUC 0.850), indicating improved performance with multimodal fusion. Risk stratification enabled surveillance recommendations of 1–3 years for low risk, 6–12 months for moderate risk, and 3–6 months for high risk. Conclusions: A late-fusion multimodal model integrating endoscopic imaging with structured clinical and pathology variables demonstrated excellent performance for predicting post-polypectomy recurrence and generated actionable risk-based surveillance intervals. This approach may support individualized follow-up planning and more efficient allocation of surveillance resources, while prioritizing timely evaluation for patients at higher predicted risk. Full article

Hand range of motion (ROM) measurement is crucial for diagnosing joint limitations, tracking rehabilitation progress, and creating personalized treatment plans. In recent years, exergames combined with dedicated game controllers have emerged as promising tools to complement traditional hand rehabilitation; however, their validity as motor function assessment tools remains insufficiently explored. This study evaluates the validity of the eJamar game controller as a tool for measuring hand ROM and hand grip strength (HGS), by comparing its outputs with standard goniometry and dynamometry. In a prior technical validation using a robotic arm under controlled conditions, the device showed a mean error of approximately 1.5°, indicating high measurement precision under ideal conditions. In the clinical validation with 32 patients undergoing hand rehabilitation, performance was movement-dependent. Pronation and supination showed strong agreement (MAE < 3°) and higher agreement compared with other movements, whereas flexion, extension, and radial-ulnar deviation exhibited weaker correlations and substantially higher errors (around 20°). In contrast, grip strength measurements for more and less affected hands, respectively, showed high correlation (0.88–0.91) and moderate agreement (ICC 0.81–0.66) with MAE values around 4 kg-f. Overall, results suggest that the eJamar shows preliminary suitability for assessing HGS and forearm pronation and supination in clinical settings. However, for HGS, agreement should be interpreted with caution due to the observed bias and error levels, indicating that further validation and calibration are required before stronger clinical claims can be made. For wrist flexion, extension, and radial-ulnar deviation, the device currently shows limited accuracy and requires further improvement. Full article

Industrial Internet of Things (IIoT) and SCADA-connected networks are increasingly vulnerable to Distributed Denial of Service (DDoS) attacks, which can disrupt time-sensitive industrial processes and compromise operational continuity. Effective mitigation requires accurate and low-latency attack detection at the network edge, where industrial gateways operate under strict constraints in computation, memory, and energy. This study investigates Deep Reinforcement Learning (DRL) for real-time binary DDoS detection and proposes a detector based on Proximal Policy Optimisation (PPO) for deployment in resource-constrained IIoT environments. Four DRL agents, namely Deep Q-Network (DQN), Double DQN, Dueling DQN, and PPO, are trained and evaluated within a unified experimental pipeline incorporating automatic label mapping, numerical feature selection, robust scaling, and class balancing. Experiments are conducted on three representative benchmark datasets: CIC-DDoS2019, Edge-IIoTset, and CICIoT23. Performance is assessed using accuracy, precision, recall, F1-score, false positive rate, false negative rate, and CPU inference latency. The reward function is asymmetric: +1 for correct classification, −1 for false positive, and −2 for false negative, penalising missed attacks more heavily for IIoT safety. The results show that PPO provides a competitive accuracy–latency tradeoff across all three datasets, achieving the highest mean accuracy of 97.65% and ranking first on CIC-DDoS2019 with a score of 95.92%, while remaining competitive on Edge-IIoTset (99.11%) and CICIoT23 (97.92%). PPO also converges faster than the value-based baselines. Inference latency is below 0.8 ms per sample on a standard CPU (Intel i7-11800H), confirming real-time feasibility. To support practical deployment, the trained PPO policies are exported to ONNX format (≈9 KB per model), enabling lightweight and PyTorch-independent inference on industrial edge gateways. Full article

To address the challenges of complex, heterogeneous, and blurred sensitivity boundaries in the sensitive data sources of civil aviation passengers, this paper proposes a hierarchical measurement method. This model integrates information entropy and random forest, achieving measurable sensitivity. Firstly, the correlation between data sensitivity level and business characteristics is established. Then, a Random Forest-based Hierarchical Measurement with Sensitivity Information Content Analysis (RF-HM-SICA) model integrating information entropy and random forest is proposed to construct a sensitivity measurable hierarchical measurement method for passenger sensitive data. The experimental results show that the RF-HM-SICA model exhibits high stability, generalization capability, and boundary sample protection ability under different data sizes and sensitivity levels, making it suitable for solving the multidimensional heterogeneity measurement problem of sensitive data of civil aviation passengers and providing support for data security sharing protection. In particular, the recognition accuracy and precision for high-sensitivity data approach 1.0 across datasets of different scales, while RF-HM-SICA exhibits the lowest misclassification rate among all compared models. Full article

Background: Achieving facial harmony in patients with micrognathia requires precise chin augmentation. While conventional ready-made implants often fail to conform to unique mandibular surfaces, expensive patient-specific options like PEEK or Titanium lack intraoperative adjustability. We introduce an innovative, cost-effective workflow utilizing 3D-printed templates to fabricate customized Polymethyl Methacrylate (PMMA) implants, emphasizing their clinical feasibility and intraoperative versatility. Methods: We retrospectively analyzed 20 patients with mild-to-moderate micrognathia (<6 mm advancement) who underwent genioplasty between March 2021 and June 2022. Patient-specific templates were produced via Fused Deposition Modeling (FDM) using low-shrinkage Acrylonitrile Butadiene Styrene (ABS) filament. During surgery, final PMMA implants were molded using these sterilized templates. Accuracy was evaluated by comparing mental advancement across preoperative, virtual simulation, and 6-month postoperative stages using Vectra 3D scanning. Results: Quantitative analysis revealed high fidelity between virtual planning and clinical outcomes. The mean discrepancy in horizontal advancement was only 1.02 mm (Planned: 5.04 mm vs. Actual: 4.02 mm). Statistical analysis showed a strong positive correlation (r = 0.928, p = 0.001). Subjective patient satisfaction was high, with 90% reporting “exceptional” or “very improved” results on the Global Aesthetic Improvement Scale (GAIS). Two cases of transient numbness resolved spontaneously within two months. Conclusions: This workflow combines FDM-based template fabrication with intraoperative PMMA molding, enabling real-time adjustment of implant geometry. The results demonstrate a high level of agreement between virtual planning and postoperative outcomes, supporting the clinical reliability of this approach. It may serve as a practical alternative to conventional CAD/CAM methods, particularly in cases requiring both precision and intraoperative flexibility. Full article

Background: Gliomas are among the most common and heterogeneous primary brain tumors, exhibiting substantial molecular and transcriptomic diversity that complicates diagnosis, grading, and treatment planning. Advances in artificial intelligence (AI), particularly machine learning (ML), offer powerful opportunities to analyze high-dimensional gene expression data and support precision oncology. Methods: This study proposes an interpretable ML framework to classify brain tumor subtypes—glioblastoma, astrocytoma, and oligodendroglioma—and to predict tumor grades (2, 3, and 4) using microarray-based gene expression data. The analysis was conducted on the REMBRANDT dataset, comprising 464 labeled samples (221 glioblastoma, 148 astrocytoma, 67 oligodendroglioma, and 28 controls) and 314 tumor samples for grade classification. Results: The ML models achieved high performance for disease classification, with accuracies of 99.6% (AUC 99.89%) for glioblastoma, 98.3% (AUC 99.83%) for astrocytoma, and 98.95% (AUC 100%) for oligodendroglioma. Tumor grade predictions also performed strongly, achieving 83.7% accuracy (AUC 88.2%) for grade II vs. III, 91.3% (AUC 94.8%) for grade II vs. IV, and 84.2% (AUC 90.8%) for grade III vs. IV. SHAP analysis identified key genes contributing to the model predictions (e.g., WIF1, STX6, RGS5, and ACTR2), and KEGG enrichment identified the candidate pathways involved in vesicular transport, metabolism, and immune signaling. Conclusion: Overall, our findings demonstrate that interpretable ML models can accurately differentiate glioma subtypes and grades, and SHAP analysis can help identify the strongest predictors of our models. These findings provide additional insights into the heterogeneous genetic and molecular landscape of brain gliomas and are intended to complement, not replace, conventional histopathological diagnosis. Full article

:Piezoelectric actuators are core components in precision motion control due to their unique electromechanical coupling properties. This paper establishes a dynamic model for a partially laminated piezoelectric–metal–piezoelectric beam actuator based on the Euler–Bernoulli beam theory. The model comprises symmetrically bonded piezoelectric layers on both sides of a central metal substrate, with the piezoelectric material partially distributed along the beam length. The structure is analyzed segment-wise along the beam’s longitudinal length direction. By applying continuity conditions at the interfaces of varying cross-sections and leveraging the structural symmetry, analytical solutions for both the natural frequency and output displacement are derived. The analytical predictions are validated against finite-element results, and experiments also verify the accuracy of the analytical solution of the analytical voltage–displacement response. In addition, the effects of key geometric parameters on the dynamic performance are systematically investigated. The proposed model provides theoretical guidance for tuning the resonance characteristics and drive displacement design of the PMP actuators. Full article

This paper presents an absolute distance measurement system based on three-wavelength synchronous phase-shifting interferometry. A synthetic wavelength chain is established using three semiconductor lasers in an all-fiber Fizeau interferometer. By integrating a piezoelectric transducer (PZT)-driven sinusoidal phase modulation with multi-channel synchronous sampling for phase demodulation, and further combining it with a fractional multiplication method, the proposed system achieves high-precision absolute distance measurement over an extended range. Experimental results demonstrate an unambiguous measurement range of 240 μm, a static measurement precision better than 0.6 nm, and a dynamic displacement measurement accuracy superior to 2 nm in comparison with the reference device. The main error sources of the system, including synthetic wavelength uncertainty, phase measurement uncertainty, and air refractive index uncertainty, are systematically modeled and analyzed. In addition, the influence of dynamic factors, such as PZT nonlinearity, is discussed and compensated. The proposed method provides a robust and high-precision solution for absolute ranging and shows strong potential for applications in industrial precision inspection and optical sensing. Full article

The increasing prevalence of cancer in Thailand over the past decade has resulted in a substantial rise in the use of anticancer drugs, which are eventually discharged into municipal wastewater through hospital and domestic effluents. The inability of conventional wastewater treatment systems to completely remove these pharmaceuticals has been widely reported. The continuous release of these emerging anticancer agents into aquatic environments reduces water quality and threatens biodiversity. Even at trace levels, these compounds may act as persistent pollutants capable of impairing ecosystem. This study investigated the occurrence and concentration levels of three widely used chemotherapeutic agents including cyclophosphamide (COP), doxorubicin (DOX), and vincristine (VIN) in Bangkok’s municipal wastewater to evaluate their potential environmental risks. Thirty-two influent and effluent wastewater samples were collected from eight large-scale wastewater treatment plants (WWTPs) from October 2024 to January 2025. Samples were processed using solid-phase extraction (SPE) and analyzed by liquid chromatography–triple quadrupole mass spectrometry (LC–MS/MS). The analytical method demonstrated high precision and reproducibility, with relative standard deviations (%RSD) below the 20% acceptance limit for all compounds. Method accuracy ranged from 81.84% to 107.21%. Results showed the presence of only COP in almost influent and effluent at levels ranging from 0.26 to 2.06 µg/L. In contrast, DOX and VIN levels remained consistently below the limits of quantitation (LOQ) in all WWTP samples. This study establishes the first baseline for COP, DOX, and VIN contamination in Bangkok’s municipal wastewater. Notably, the residue of COP in wastewater suggests that current wastewater treatment facilities in Thailand are insufficient for its removal, posing a potential long-term risk to local aquatic ecosystems. Full article

Mangrove represent vital coastal ecosystems that contribute to shoreline stabilization, ecological balance, and environmental management. Nevertheless, the precise delineation of mangrove regions using remote sensing data is often impeded by spectral similarities with intertidal mudflats and aquatic features, alongside the irregular spatial patterns and intricate margins of mangrove stands. This research utilizes high-resolution Gaofen-6 (GF-6) satellite observations as the foundational data to develop Triplet Axial High-Resolution Network (TAHRNet), a semantic segmentation architecture derived from the High-Resolution Network with Object-Contextual Representations (HRNet-OCR) framework for mangrove identification. The model integrates a Triplet Attention module to facilitate cross-dimensional feature dependencies and an improved Multi-Head Sequential Axial Attention mechanism to capture long-range spatial context while maintaining structural consistency. Based on evaluations using the test dataset, TAHRNet yielded a Mean Intersection over Union (MIoU) of 92.01% and a Overall Accuracy of 96.38%. Relative to U-Net and SegFormer, the proposed approach showed MIoU improvements of 5.25% and 1.88%, with corresponding Accuracy gains of 2.68% and 0.94%. Further application to coastal mapping in Zhanjiang produced results that align with manual visual interpretation. These findings suggest that TAHRNet is a viable tool for mangrove extraction and can provide technical support for coastal monitoring and ecological analysis. Full article

Laser fiber-based collimation straightness measurement can eliminate the intrinsic drift of the laser source while offering a simple configuration and simultaneous measurement of straightness in two orthogonal directions. As a high-precision optoelectronic sensing method, it has been widely used for the measurement of straightness, parallelism, perpendicularity, and multi-degree-of-freedom geometric errors. However, two common issues remain in practical applications. One is the nonlinear response of the four-quadrant detector, the core position-sensitive sensor, which is caused by detector nonuniformity and the quasi-Gaussian distribution of the spot. The other is the degradation of measurement performance by atmospheric inhomogeneity and air turbulence along the optical path, particularly in long-distance measurements. To address these issues, a two-dimensional planar calibration method is first proposed to replace conventional one-dimensional linear calibration. A polynomial surface-fitting model is introduced to correct the nonlinear response and inter-axis coupling errors of the four-quadrant photoelectric sensor. Simulation and experimental results show that the proposed method significantly reduces the standard deviation of calibration residuals and improves measurement accuracy. In addition, based on our previously developed common-path beam-drift digital compensation method, comparative experiments were carried out on double-pass common-path and single-pass optical configurations employing corner-cube retroreflectors, and theoretical simulations were performed to analyze the influence of air-turbulence disturbances on measurement stability. Both theoretical and experimental results show that the double-pass common-path configuration exhibits more pronounced temporal drift. Therefore, a real-time digital compensation method for beam drift in long-distance single-pass common-path measurements is proposed. Experimental results demonstrate that the proposed method effectively suppresses drift induced by environmental air turbulence and thereby improving the accuracy and stability of long-travel geometric-error and related straightness measurement for machine-tool linear axes. Full article

Asymmetric Cascaded Multilevel Inverters (ACMLIs) have emerged as a prominent solution for medium- and high-power applications due to their ability to provide an increased number of output voltage levels with fewer power switches. However, maintaining low total harmonic distortion (THD) and ensuring robust stability under varying operating conditions remain significant challenges. This study experimentally validates a voltage-feedback Proportional-Resonant (PR) control strategy for a seven-level ACMLI. Unlike conventional current-feedback methods, the proposed approach directly regulates the output voltage, providing superior harmonic suppression and enhanced steady-state accuracy. The stability and dynamic performance of the controller were theoretically analyzed using Bode diagrams and root locus methods, and further verified through the MATLAB Curve Fitting Tool (CFT) with a high correlation (R² = 0.9989). Experimental results demonstrate that the integration of the PR controller significantly improves power quality, reducing the current THD from 6.55% to 3.68% and the voltage THD to 2.94%. These findings confirm that the system fully complies with IEEE 519 standards and outperforms several existing strategies in the literature. The results establish the voltage-feedback PR control as a robust, high-precision, and practical alternative for power quality-oriented multilevel inverter applications in modern energy systems. Full article

Transparent clinical decision-making remains a critical barrier to deploying deep learning in medical diagnosis. Post hoc explanation methods approximate model behaviour after training but cannot guarantee that explanations faithfully reflect the underlying reasoning. This study proposes a Self-Explaining Neural Network (SENN) for Parkinson’s Disease (PD) screening via Ground Reaction Force (GRF) gait analysis, enforcing intrinsic interpretability through learnable basis concepts and input-dependent relevance scores computed jointly with the prediction. The architecture combines a four-block residual CNN backbone with stochastic depth regularisation, a 16-concept encoder with diversity and stability constraints, and temperature-scaled probability calibration for reliable clinical operating points. Evaluated on the PhysioNet Gait in Parkinson’s Disease dataset (306 subjects, 16 GRF sensors per foot), SENN achieves a subject-level ROC-AUC of 0.916 [95% CI: 0.867–0.964], sensitivity of 0.913 [0.862–0.963], specificity of 0.671 [0.485–0.858], and Average Precision of 0.942 [0.918–0.967], reported across five independent random seeds. Comparative evaluation against four deep learning baselines—CNN-Residual, BiLSTM, CNN-LSTM, and CNN-Attention—confirms that the interpretability constraints impose no statistically significant reduction in discriminative performance, with all pairwise ROC-AUC confidence intervals overlapping. Concept-level analysis reveals that the three most discriminative concepts correspond to disrupted midfoot loading patterns, increased step-length variability, and bilateral cadence asymmetry—all established biomechanical hallmarks of parkinsonian gait—providing clinically grounded, patient-specific explanations without post hoc approximation. These findings demonstrate that rigorous intrinsic interpretability and competitive predictive accuracy are simultaneously achievable in deep gait analysis, supporting the clinical adoption of transparent diagnostic AI. Full article

Robust pose estimation and high-fidelity scene reconstruction in dynamic environments represent core challenges in the field of Visual Simultaneous Localization and Mapping (SLAM). Although 3D Gaussian Splatting (3DGS)-based techniques have demonstrated significant potential, existing methods typically assume static scenes and struggle to address the inconsistency between photometric and geometric observations in dynamic settings, leading to a notable degradation in pose estimation and map accuracy. To address these issues, this paper presents a novel dynamic SLAM method: Loop Closure with 3D Gaussian Splatting for Dynamic SLAM (LCD-Splat). Taking RGB-D images as input, LCD-Splat integrates Mask R-CNN with an improved multi-view geometry approach to detect dynamic objects, generating static scene maps and filling in occluded backgrounds. By leveraging 3DGS submaps and a frame to model tracking strategy, LCD-Splat achieves dense map construction. The method initiates online loop closure detection and employs a novel coarse to fine 3DGS registration algorithm to compute loop closure constraints between submaps. Global consistency is ultimately ensured through robust pose graph optimization. Experimental results on real-world datasets such as TUM RGB-D and Bonn demonstrate that LCD-Splat outperforms existing state-of-the-art SLAM methods in terms of tracking, scene reconstruction, and rendering performance. This approach provides novel insights for high-precision SLAM in dynamic environments and holds significant implications for scene understanding in complex settings. Full article