Search Results (1,250)

Fruit-tree pruning has to keep tree structure under control while continually renewing fruiting wood, and many decisions still depend on practical experience. This narrative review synthesizes 92 English-language publications from 1983 to 2026, identified through Google Scholar and backward citation tracking. As orchard systems become more regular and mechanization expands, mechanical pruning has been used to control canopy edges. Vision and 3D sensing are now being used to identify branches and locate pruning points, while robotic systems are beginning to attempt selective pruning. This review looks at the literature at canopy and branch scales. Mechanical canopy pruning is effective for quickly treating regular canopy profiles, but field trials show that regrowth, follow-up manual pruning, and crop-load management can change later yield and economic outcomes. Branch-level automation has moved from 2D recognition to 3D reconstruction, pruning-point generation, and small-scale robotic trials. The harder questions are increasingly about branch function and continuous whole-tree operation. For pruning automation, machine speed or a successful cut is only part of the result; post-pruning tree responses and longer-term production also have to be considered. Multi-temporal tree records, branch-function information, continuous operation, and long-term field testing deserve more attention. Full article

Generating a virtual anchor from speech has to satisfy three demands at once: the face must stay recognizable as the same person, the motion has to be temporally coherent, and the lips must follow the audio. Existing methods often fall short on the first two points because identity and expression share one entangled representation, and temporal dynamics are modeled only implicitly. We propose DynaID-VAE to address these problems. At its core is an identity–expression disentangled conditional VAE (DC-VAE) that splits the latent space into a time-varying expression subspace and a static identity subspace, held apart by mutual-information minimization and orthogonality regularization. A temporal memory module (TMM) then regularizes the expression trajectory: a GRU propagates sequential state, attention retrieves from a learnable key–value prototype memory, and residual fusion combines the two. Multiscale adversarial supervision and lip–audio synchronization losses complete the training objective. We evaluate on VirtualAnchor-100, a benchmark we recorded ourselves (100 h, 10 anchors), under two complementary protocols. Cross-identity driving is scored only with non-paired measures, namely lip synchronization, distributional video quality, and identity preservation; full-reference image metrics are confined to a self-reenactment protocol, where a genuine paired ground truth exists. DynaID-VAE outperforms the one-reference baselines Wav2Lip, PC-AVS, SadTalker, and DiffTalk under both protocols and on unseen VoxCeleb2 identities. The margins are stable across five identity-disjoint, nested cross-validation folds and are confirmed by an external SyncNet evaluator that never takes part in training, while the model runs at 41.2 FPS with 14.3 M parameters. Ablations separate the contribution of each regularizer and each TMM component. Linear and capacity-matched non-linear probes quantify the factorization as a large reduction of decodable reference identity; full independence is not claimed. A user study confirms the perceptual gains. Full article

Water-based perovskite solar cells (W-PSCs) provide a promising route toward reducing the use of hazardous organic solvents during perovskite fabrication. However, their development remains limited by sluggish precursor conversion, incomplete phase transformation, and poor control over film morphology. This review summarizes recent progress in W-PSCs, with particular emphasis on aqueous lead precursors and the subsequent conversion from precursor films to perovskite absorbers. The selection criteria for aqueous lead sources are first discussed in terms of water solubility, anion-Pb²⁺ interactions, precursor-solution stability, and ion-exchange behavior. Thermodynamic and kinetic considerations, including nucleation, crystal growth, reaction–diffusion coupling, and ion transport, are then discussed to provide a framework for understanding the conversion of aqueous precursor films into perovskites. Strategies for improving film formation are further classified into precursor-film and substrate engineering, conversion-process regulation, and ionic/compositional engineering. Particular attention is given to the role of precursor-film microstructure in regulating organic ammonium salt transport and conversion completeness. The photovoltaic performance of regular and inverted W-PSCs is subsequently compared, and the possible origins of their performance differences are discussed from the perspectives of precursor-film formation, perovskite conversion, film morphology, and interfacial properties. Finally, future opportunities in substrate-interface regulation, scalable aqueous processing, precursor and additive design, and life-cycle assessment are outlined. This review provides a reaction-diffusion-based perspective for understanding and improving water-based perovskite photovoltaics. Full article

Blood donation sustains an estimated 118 million annual donations worldwide, and while advances in infectious disease screening have greatly reduced recipient risk, the long-term health of repeat donors has received comparatively less attention. This cumulative review synthesises current evidence on the principal acquired complications of regular blood donation across all modalities—whole blood, plasmapheresis, and plateletpheresis—addressing iron deficiency, plasma protein depletion, apheresis-related lymphopenia, clonal haematopoiesis of indeterminate potential (CHIP), and micronutrient deficiency. Iron deficiency affects 15–36% of frequent whole blood donors and is systematically underdetected by haemoglobin-based screening alone; ferritin-guided interval adjustment and oral supplementation are effective countermeasures. Regular plasmapheresis depletes immunoglobulins (IgG below normal in 5–15% of high-frequency donors), albumin, and coagulation factors, compounded by cumulative citrate-mediated hypocalcaemia. Plateletpheresis causes measurable subset-selective T-cell and NK-cell depletion, with CD4⁺ counts below clinically significant thresholds in a minority of the most frequent donors, an observation of unknown significance. Emerging molecular data indicate that repeated haematopoietic stress selectively enriches low-risk, EPO-responsive DNMT3A clonal variants without increasing malignant risk. Regular blood donation if properly applied is a safe process. Across all domains, current eligibility criteria based on haemoglobin alone turn out to be inadequate; a shift to multiparameter, individualised and targeted donor monitoring—integrating ferritin, serum proteins, differential leucocyte counts, and micronutrient profiling—is both evidence-suggested and ethically worth considering to sustain the long-term health of voluntary donor populations. Full article

Background: Malnutrition is a significant clinical problem in patients with cancer, occurring not only during hospitalization but also throughout the recovery phase. It brings severe health and economic consequences, affecting patients on both physical and psychological levels. The American Society for Parenteral and Enteral Nutrition (ASPEN) and the European Society for Clinical Nutrition and Metabolism (ESPEN) emphasize the critical importance of early detection of nutritional disorders and timely intervention in oncology populations. The aim of this study was to determine the prevalence of malnutrition and factors associated with malnutrition among hospitalized Polish oncology patients and to draw attention to the need for early nutritional assessment in patients with cancer so as to ensure appropriate nutritional care. Methods: A multicenter cross-sectional study was conducted in accordance with the Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) guidelines among adult patients diagnosed with cancer and undergoing oncological treatment. Data collection involved a structured survey questionnaire, anthropometric measurements, and validated screening tools: Mini Nutritional Assessment (MNA), Nutritional Risk Screening Score 2002 (NRS 2002), and Subjective Global Assessment (SGA). Results: The study group comprised 560 patients with a mean age of 55 ± 13.95 years, including 59% women and 41% men. The mean duration of illness was 3.37 years. Advanced-stage cancer was present in 43% of participants, and 66% were undergoing chemotherapy. The mean Body Mass Index (BMI) for the study group was 23.14 kg/m², with a mean MNA score of 16.23 points and a mean NRS 2002 score of 2.39 points. Based on Subjective Global Assessment, moderate malnutrition was identified in 45% of patients, whereas severe malnutrition was confirmed in 27% of the study population. Conclusions: The prevalence of malnutrition among oncology patients is high. Early screening and regular monitoring are essential for the prompt identification of patients at risk, enabling the implementation of appropriate nutritional therapy and the improvement of clinical outcomes. Full article

Background/Objectives: To achieve effective clinical decision-making from radiographic images, accurate diagnosis of bone fractures is required, but this is difficult due to anatomical variation, subtle fracture appearance, and variable imaging conditions. Existing deep learning studies for fracture detection are predominantly limited to binary classification or single anatomical regions, limiting their real-world clinical utility. This study demonstrates that a single deep learning model can effectively classify multi-region bone fractures by transforming the task into a 22-class classification problem, utilizing the publicly available MultiBoneX dataset. Methods: The proposed model utilizes an EfficientNet-B3 convolutional neural network integrated with a Convolutional Block Attention Module (CBAM) to enhance feature representation by focusing on diagnostically significant areas. We used regularized preprocessing, data augmentation, and structured training to support strong model learning and generalization. Model predictions were interpreted using Gradient-weighted Class Activation Mapping (Grad-CAM) to highlight the image regions that were most important for class selection. Results: When tested on a held-out test set of 3280 images, the model achieved an overall accuracy of 75.03% (95% CI: 73.57–76.43%), with precision, recall, and F1-score of 77.09% (95% CI: 75.28–78.77%), 72.85% (95% CI: 71.00–74.60%), and 73.45% (95% CI: 71.49–75.15%), respectively. The overall multi-class Matthews Correlation Coefficient (MCC) was 0.7361, providing an additional class-imbalance-aware measure of classification performance. Conclusions: These findings demonstrate the feasibility of a unified, multi-class system for diagnosing bone fractures across diverse anatomical sites, providing a scalable foundation for future AI-assisted radiography. Full article

Identifying the small group of customers who hold a given policy in severely imbalanced tabular data is a recurring screening problem in insurance analytics. This study considers binary caravan-insurance policy-ownership classification on the COIL 2000 benchmark, where the positive-class prevalence is below 6%. The benchmark is a single cross-section, so the label describes current ownership rather than a future purchase event. We propose an Attention-based Symmetric AutoEncoder (ASAE) that combines an auxiliary symmetric reconstruction branch, a channel attention gate, and a marginal log-variance regularizer on a 32-dimensional latent representation. The regularizer operates on individual latent variances and is treated as a heuristic rather than as an estimator of joint differential entropy. Under a common tuning and evaluation protocol on a stratified partition, the ASAE is compared with five conventional machine learning methods and seven neural models. Across five paired runs, it achieves an F1-score of 0.6008 ± 0.0115 and an area under the receiver operating characteristic curve (AUC) of 0.8584 ± 0.0034. Relative to TabNet, the strongest baseline considered, the mean differences are 0.064 in F1-score (95% confidence interval 0.043–0.085) and 0.032 in AUC (95% confidence interval 0.017–0.048). The ordering is preserved across five stratified re-splits, four imbalance-handling configurations, and a complete type-consistent preprocessing rerun in which nominal attributes are one-hot encoded, oversampled with SMOTENC, and reconstructed with categorical cross-entropy losses (F1-score 0.6241 ± 0.0074, AUC 0.8702 ± 0.0050). All reported results use stratified random partitions of COIL 2000. Because 27% of the records share an identical predictor vector with another record, the official challenge separation and two grouped partitions are also defined, so that exact-duplicate and sociodemographic overlap can be isolated from the primary split. The training code, split indices, and per-run predictions used for the reported tables are publicly available. Full article

Physical exercise is considered an effective and relatively safe practice to reduce or control levels of pro-inflammatory mediators during aging. However, findings are often interpreted primarily through statistical significance, while the magnitude and potential clinical relevance of observed effects receive less attention. Therefore, the primary objective of this cross-sectional study was to investigate whether regular physical exercise was associated with differences in circulating levels of systemic inflammatory mediators (high-sensitivity C-reactive protein [hsCRP], TNF-α, IL-6, IL-8, IL-10, and IL-12) among community-dwelling older adults, emphasizing the magnitude and potential clinical relevance of these differences rather than an interpretation based exclusively on statistical significance. The results suggest that exercisers exhibited hsCRP levels 0.68 mg/L lower than those observed among non-exercisers (95% CI: −0.98 to −0.34 mg/L; p = 0.001). Although serum IL-6 levels did not differ statistically between groups (p = 0.072), the interval estimates remained compatible with potentially relevant reductions among exercisers. The estimated between-group difference indicated that exercisers presented median IL-6 concentrations 4.34 pg/mL lower than non-exercisers (95% CI: −9.41 to 0.24 pg/mL). No meaningful differences were observed for TNF-α, IL-8, IL-10, or IL-12. Taken together, these findings suggest that regular physical exercise is associated with a more favorable inflammatory profile in older adults, particularly through lower hsCRP concentrations. The findings for IL-6 remain inconclusive but support the need for future studies with more precise estimates of the magnitude and potential clinical relevance of this association. Full article

During cherry-tomato-bunch harvesting, clustered fruits, thin stems, and ambiguous fruit–stem junctions cause missed detections and errors in picking-point localization. To address these challenges, we propose TSP-Net, a structure-aware and geometry-constrained detection network built on YOLOv11n, together with an ROI heat-map regression module for picking-point localization. TSP-Net integrates the Truss-aware Multi-scale Ghost Cross Stage Partial (TMG-CSP) module into the backbone to strengthen structural features of fruit edges, small stems, and clusters. It introduces the Truss-oriented Axial-Local Attention (TALA) module during feature fusion to capture fruit-arrangement direction and local occlusion boundaries. We also design Physics-informed Truss Consistency (PTC) Loss to regularize detections by enforcing consistency with fruit-cluster morphology through constraints on center distribution, inter-fruit spacing, and scale continuity. For picking-point localization, local ROIs are extracted from detection outputs, Gaussian heat maps are predicted, and continuous coordinates are decoded using soft-argmax. In the controlled evaluation, TSP-Net attains precision 81.81%, recall 73.21%, mAP@50 79.53%, and mAP@50:95 64.83%, which exceed the corresponding YOLOv11n results by 0.83, 0.32, 1.29, and 1.03 percentage points, respectively. The model size is reduced from 5.23 MB to 5.08 MB, the parameter count falls from 2.59 M to 2.49 M, and computational cost declines from 6.4 to 6.0 GFLOPs. On the common valid-ROI test set, the proposed heat-map localization yields a mean localization error of 47.2 px, a median error of 24.2 px, and PCK@20, PCK@50, and PCK@100 of 45.1%, 68.4%, and 85.5%, respectively. Under identical ROI conditions, this heat-map method reduces the mean localization error by 11.3 px and raises PCK@20 by 14.9 percentage points compared with direct coordinate regression. In summary, the proposed approach enhances cherry-tomato-bunch detection and 2D picking-point candidate localization while meeting lightweight constraints, offering a structure-aware visual perception solution for greenhouse cherry-tomato harvesting. Full article

Tomato is a major global crop, yet foliar diseases seriously affect yield and quality. Accurate and efficient disease identification techniques are of great significance for ensuring agricultural production safety. To address the limitations of existing methods in feature extraction capability, model complexity, and dependence on large-scale labeled data, as well as the difficulty of recognizing early-stage diseases whose visual symptoms are not yet fully developed, this paper proposes SAEFormer, a lightweight and robust disease recognition model. The model integrates a Multi-scale Selective Fusion Attention Block to enhance the ability to model multi-scale semantic information in lesion areas. In addition, by leveraging a self-supervised loss derived from dense relative localization as an auxiliary regularization term, the model’s generalization ability under limited training data is notably enhanced. To optimize normalization and improve inference efficiency, the RepBN normalization strategy is further adopted, significantly reducing computational cost while maintaining model performance. Experimental results on Dataset A show that SAEFormer achieves a Top-1 accuracy of 87.86% with 24.14 M parameters and 5.35 GFLOPs, demonstrating a favorable balance between recognition accuracy and model complexity. The training curves further indicate stable convergence during model optimization. Ablation experiments validate the complementary contributions of the proposed modules. Moreover, SAEFormer achieves competitive performance in cross-dataset evaluation on Dataset B, indicating its potential adaptability to different data distributions. Overall, SAEFormer provides an efficient approach to tomato leaf disease recognition and shows potential for deployment in precision agriculture applications. Full article

The precise detection and pose estimation of electric vehicle (EV) charging ports in unstructured outdoor environments remain challenging due to small sizes, variable illumination, and stringent tolerance requirements for robotic plug-in operations. To address these issues, this paper presents a hybrid perception framework that integrates an attention-embedded detection network with geometrically constrained pose optimization. For robust detection, CBAM-YOLOv11 is proposed, which incorporates a sequential channel-spatial attention module into the backbone network to enhance feature representation of texture-less small targets while suppressing background clutter and glare. Then, a topological geometric constraint-based method is developed for accurate pose estimation. Specifically, the 2D-3D correspondences are purified before being fed into an Efficient Perspective-n-Point (EPnP) solver, while a nonlinear refinement with rigid distance priors is applied as regularization. Extensive experiments on the dataset and a physical robotic platform demonstrate that the proposed detector achieves 99.2% mAP@0.5 and a 24.6 percentage point improvement in mAP@0.5:0.95 over the baseline YOLOv11. The pose estimation module reduces positioning standard deviations along the X, Y, and Z axes to 4.72 mm, 5.65 mm, and 5.60 mm, respectively, surpassing conventional EPnP by about 60%. In 30 repeated robotic insertion trials, the system attains a 93.3% success rate with approximately 78 ms, fully satisfying real-time and precision requirements for autonomous EV charging. Full article

The estimation of the uncertainty of random variables or the entropy of stochastic processes has attracted considerable attention in many studies. In this study, we focus on obtaining estimators for the Shannon, Rényi, Tsallis, and Havrda–Charvat entropy measures of the Kumaraswamy distribution. Maximum likelihood and Bayesian estimation methods are employed to obtain entropy estimators under progressive Type-II censoring schemes with binomial removals. The Tierney–Kadane approximation is used to obtain the Bayesian estimators. The consistency and asymptotic normality of the maximum likelihood estimators are also stated under standard regularity conditions, and approximate confidence intervals for the entropy measures are constructed accordingly. The behavior of the proposed estimators under various sample sizes and censoring schemes is investigated through an extensive Monte Carlo simulation study. Finally, the Kumaraswamy distribution is fitted to two real datasets from the fields of economics and agricultural hydrology. In both applications, the Kumaraswamy distribution is shown to provide a better fit than the three competing unit distributions. Under different progressive Type-II censoring schemes, maximum likelihood and TK-based Bayesian estimates of the four entropy measures are obtained, while Markov chain Monte Carlo is additionally used to construct Bayesian credible intervals. The resulting credible intervals are found to be similar to the corresponding maximum likelihood-based confidence intervals, supporting the practical applicability of the proposed estimation procedures for entropy measures under censored data. Full article

Thermal error remains a primary bottleneck restricting the machining accuracy of precision CNC machine tools. As a proactive, source-level countermeasure, thermal design has become increasingly critical for achieving the accuracy targets required by advanced manufacturing sectors. This paper presents a critical review of machine-level thermal design methodologies, categorizing existing approaches into three principal technical routes: temperature control, material improvement, and structural optimization. For each route, we critically examine the underlying theoretical foundations, representative implementations, and reported effectiveness, with particular emphasis on the persistent gap between academic research and industrial practice. Our analysis reveals that the majority of existing thermal design efforts focus on reducing the magnitude of thermal deformation, while paying limited attention to its spatial distribution. This imbalance, we argue, limits the potential synergies between thermal design and thermal compensation, as spatially complex deformation fields are intrinsically more difficult to model and correct than regular patterns. To address this gap, we propose a paradigm shift from “amplitude minimization” to “deformation mode regularization”: actively shaping the spatial distribution and temporal evolution of thermal deformation to render it more predictable, repeatable, linear, and readily compensable. The review concludes by outlining a forward-looking framework that integrates thermal deformation mode regularization, digital twin-based thermal state perception, and design-for-compensation principles, offering both theoretical foundations and practical guidelines for thermal design in high-precision machine tools. Full article

The accuracy and consistency of error-state Kalman filtering for SINS/GNSS integrated navigation depend critically on properly tuned process and measurement noise covariance matrices. In dynamic operation, these covariances can be non-stationary: inertial uncertainty changes with maneuver intensity, vibration, and sensor-bias instability, whereas GNSS measurement quality changes with satellite geometry, multipath, obstruction, and signal loss. Fixed-covariance and classical adaptive filters can therefore become overconfident or insufficiently responsive during abrupt maneuvers and degraded GNSS reception. We propose a physics-informed constrained neural covariance estimation (PC-NCE) framework that augments, rather than replaces, the error-state Kalman filter (ESKF) by estimating bounded process and measurement covariance-scale parameters online. The framework maps IMU-window sequences, GNSS-quality indicators, innovation statistics, and motion-state descriptors through a CNN-BiLSTM-attention network to filter-admissible Q_k and R_k parameterizations injected into a closed-loop ESKF. Training enforces positivity, bounds, temporal smoothness, and innovation–consistency regularization. In a reproducible filter-level MATLAB scenario suite, PC-NCE improved covariance-scale tracking and selected consistency ratios relative to fixed and unconstrained neural baselines, whereas position RMSE gains were scenario-dependent. These results provide a simulation-level proof of concept supplemented by an initial held-out measured-trajectory evaluation; broader validation using a full 15-state SINS/GNSS implementation and additional field datasets remains necessary. By treating neural networks as uncertainty-perception layers rather than black-box state estimators, PC-NCE retains the interpretability and engineering safeguards of classical Kalman filtering. Full article

Continuity and reliability are critical for underwater gravity aided inertial navigation, while variations in gravity field suitability, sensor noise, and environmental disturbances can degrade gravity matching and navigation performance. To address this issue, a data-driven matching error compensation framework is proposed for gravity aided inertial navigation. Within this framework, a Hampel filter identifies unreliable gravity matching outputs based on local temporal consistency, and a CNN–BiLSTM–Attention model predicts compensated position increments for the flagged updates. The model maps INS position increments and measured gravity anomaly sequences to reliable gravity matching increments through local feature extraction, temporal modeling, and attention-based weighting, with offline training and online deployment. Reliable training samples were selected offline using reference trajectories, with synchronized GNSS positions serving only as the reference for sample screening in the marine experiments. Experiments were conducted across five simulated gravity field regions with five gravity matching algorithms and along three measured trajectories acquired using two types of marine gravimeters. In the marine experiments, the proposed method achieved mean APE-O values of 1.60, 1.06, and 1.06 n miles on L6, L7, and L8, respectively. The improvement was most evident on L6 with relatively extended error intervals, while the conventional RBIM method achieved comparable performance on the more regular and localized L8 error interval. Across the evaluated datasets, the proposed framework provided effective compensation for degraded gravity matching updates and improved the continuity of position corrections. Full article