Search Results (22,356)

Background/Objectives: The goal of the study was to identify the peculiarities of attention deficit hyperactivity disorder (ADHD) on the base of the behavioral characteristics and acoustic features of speech of children with ADHD and ADHD with comorbidity—ADHD and autism spectrum disorders (ASD) and ADHD and intellectual disabilities (ID)—within the framework of one test task. Behavioral characteristics were selected using DSM-V criteria; acoustic features of speech were considered by researchers as speech markers of ASD and ID detected for different languages. Methods: The study includes 92 children aged 5–13 years with ADHD, ADHD and ID, ADHD and ASD, and control groups of children diagnosed with ASD, ID and typically developing (TD) children. The children were tested using the test task “co-op play”. Video and audio recordings of children performing the test task were collected. We used a complex approach to study the peculiarities of children with ADHD through expert analysis of children’s behavior and play, acoustic spectrographic analysis of speech and questionnaires about early childhood development filled out by parents. Results: The characteristics of behavior, play, and acoustic features of speech of children with ADHD and ADHD and comorbidity were revealed. Children with ADHD had lower behavior scores in the play situation on the expert assessment than TD children, with the greatest differences for characteristics of play, “Playing for toy”, and of behavior “Displaced activity” and “Losing attention”. The speech of children with ADHD is characterized by low values of the third formant and the difference between the first two formants, compared to the corresponding speech features of children from other groups. The speech of children with ADHD+ASD is characterized by maximal pitch values (high voice), while that of children with ADHD+ID is characterized by low vowel articulation index values. Conclusions: Based on the analysis of behavior and speech of children with TD, ADHD, ADHD and comorbidity performing the “co-op play” test task, the set of characteristics specific to ADHD was identified. The obtained data expand our understanding of the specificity of children with ADHD and may contribute to the development of qualified support for families with children with ADHD. Full article

Cooperative localization is critical for UAV swarm operations in GNSS-denied environments. The backbone-listener scheme, using a small subset of agents as active backbone nodes and others as passive listeners, offers notable advantages in reducing communication overhead and enhancing swarm scalability. Building on this scheme, we propose a formation-constrained cooperative localization method to improve accuracy by integrating known formation geometry into the localization process. First, backbone node selection uses a formation-constrained greedy node activation (GNA) strategy with weighted distance fusion, combining measured and ideal formation distances to enable near-optimal selection aligned with formation structure. Second, listener node localization incorporates formation constraints into Chan’s algorithm, paired with angle-of-arrival (AOA) refinement, to ensure estimated positions match expected inter-agent distances. Third, global optimization uses a gradient descent-based refinement to enforce formation constraints across all agent positions. Our theoretical derivations and simulations are limited to the two-dimensional (2D) case. Simulation results validate the proposed method’s improved success rate, reliability, and stability. Its effectiveness is demonstrated across various formation types, with robust adaptability to asymmetric geometries shown to be a valuable feature for practical deployment. Full article

Severe foliage occlusion and dynamically changing lighting conditions in complex orchard environments pose significant challenges for visual perception systems in automated apple harvesting, including low detection accuracy, poor robustness, and insufficient real-time performance. To address these issues, this study proposes an improved lightweight detection network based on YOLOv11, named YOLO-WBL, along with a precise yield estimation algorithm based on 3D point clouds, termed CLV. The YOLO-WBL network is optimized in three aspects: (1) A C3K2_WT module integrating wavelet transform is introduced into the backbone network to enhance multi-scale feature extraction capability; (2) A weighted bidirectional feature pyramid network (BiFPN) is adopted in the neck network to improve the efficiency of multi-scale feature fusion; (3) A lightweight shared convolution separated batch normalization detection head (Detect-SCGN) is designed to significantly reduce the parameter count while maintaining accuracy. Based on this detection model, the CLV algorithm deeply integrates depth camera point cloud information through 3D coordinate mapping, irregular point cloud reconstruction, and convex hull volume calculation to achieve accurate estimation of individual fruit volume and total yield. Experimental results demonstrate that: (1) The YOLO-WBL model achieves a precision of 93.8%, recall of 79.3%, and mean average precision (mAP@0.5) of 87.2% on the apple test set; (2) The model size is only 3.72 MB, a reduction of 28.87% compared to the baseline model; (3) When deployed on an NVIDIA Jetson Xavier NX edge device, its inference speed reaches 8.7 FPS, meeting real-time requirements; (4) In scenarios with an occlusion rate below 40%, the mean absolute percentage error (MAPE) of yield estimation can be controlled within 8%. Experimental validation was conducted using apple images selected from the dataset under varying lighting intensities and fruit occlusion conditions. The results demonstrate that the CLV algorithm significantly outperforms traditional average-weight-based estimation methods. This study provides an efficient, accurate, and deployable visual solution for intelligent apple harvesting and yield estimation in complex orchard environments, offering practical reference value for advancing smart orchard production. Full article

Detection of metal ions under complex and heterogeneous conditions is crucial for food safety, environmental monitoring, and cellular studies. Fluorescent proteins (FPs) are attractive biosensors due to their ease of expression, strong emission without external cofactors, and fluorescence quenching upon metal binding. tKeima features a large Stokes shift, pH sensitivity, and spectral stability, reducing background interference and enabling metal detection in complex samples. Here, we examined tKeima quenching toward biologically relevant metal ions (Fe²⁺, Fe³⁺, and Cu²⁺). Metal titration fitted to the Langmuir isotherm yielded dissociation constants (K_d) of 2710.7 ± 178.6 μM (Fe²⁺), 3112.0 ± 176.7 μM (Fe³⁺), and 881.9 ± 76.2 μM (Cu²⁺), with maximum quenching capacities (B_max) of 133.8 ± 2.4%, 128.3 ± 2.5%, and 109.2 ± 1.2%, respectively. Limits of detection were 396.0 μM (Fe²⁺), 428.6 μM (Fe³⁺), and 457.7 μM (Cu²⁺), and linear quenching responses were observed up to ~1000, 1500, and 1000 μM, respectively. Sphere-of-action combined with Stern–Volmer analysis indicated primarily dynamic quenching for Fe²⁺ and Cu²⁺, whereas Fe³⁺ showed a stronger static component. tKeima showed partial fluorescence restoration with ethylenediaminetetraacetic acid and moderate selectivity against interfering ions. These findings clarify tKeima’s metal-quenching mechanism and support its use as a platform for metal-responsive biosensors. Full article

A new procedure for diagnosing damage to the fuel injection system of marine engines, along with vibration acceleration signal symptoms, is explored with a related built, developed, and tested measuring system. This work fills an important gap given the current lack of a scientific solution to this problem. A vibration acceleration signal sensor, mounted on a holder elaborated on by the authors, is positioned on the injection pipe between the injection pump and the injector. The output signals from the sensor are sent to an acquisition and analysis system, which is used for processing the signals in the time, amplitude, frequency, and time–frequency domains. Experimental choices, using multiple parameters for a given signal analysis field, are based on the location of the optimal sensor, the direction of the sensor mounting, and the selection of a cumulative diagnostic symptom. The vibration acceleration signals recorded along the injection pipe are found to have the strongest magnitude. This article compares diagnostic values from these signals with previously determined upper and lower limits. As a result, the tested fuel injection system is classified as either able or disabled, using unparalleled tolerance ranges given for both the upper and lower limits. The values of the limits are determined based on the average value for an ability state plus or minus three times the standard error of this mean, which has not been reported in the literature previously. Multiple regression models are developed that relate identified symptoms to the state features of the fuel injection system. In addition, artificial neural networks and machine learning are used to detect developing damage. The probability of correctly classifying the states of the diagnostic parameters is 0.467, alongside a diagnostic accuracy of ≤±4%, with the network correctly classifying the state when the testing accuracy is at least 70.0%. Full article

The leg structure of swine is closely related to their robustness and longevity. Animals with sound legs generally have longer productive lifespans and higher reproductive efficiency, whereas leg defects can markedly impair performance and shorten service life. To address the high subjectivity, low efficiency, and poor consistency of traditional leg-structure evaluation by humans, this study developed an automatic scoring system for swine leg structure based on 3D point clouds. The hardware components of the system include the acquisition channel, a multi-view time-of-flight (ToF) depth camera array, an industrial computer, and a star-type synchronization hub. The core algorithm modules include point cloud preprocessing, leg segmentation, geometric feature extraction, and structure-based scoring. Body orientation was corrected using principal component analysis (PCA). An adaptive limb region segmentation method was proposed that combines iterative cropping with geometric verification. Two point cloud tasks were performed: key structural points were extracted via multi-scale curvature analysis, and angular and symmetry parameters of the fore- and hindlimbs were computed in the sagittal and coronal planes. Following a “classify first, then score” strategy, a nine-level linear scoring model was constructed. Field validation showed that the classification accuracy exceeded 90%, the scores were significantly negatively correlated with the degree of structural deviation, and multi-frame resampling yielded good repeatability. The processing time per animal ranged from 1.6 s to 3.0 s, which met the requirements for real-time applications. These results demonstrated that the proposed method could automatically identify and quantitatively evaluate swine leg structure, providing efficient and reliable technical support for objective selection and smart pig farming. Full article

Spring frosts pose a major threat to tea production, causing severe damage to tender spring buds and substantial economic losses. To support timely frost protection measures, this study develops an interpretable machine learning framework for next-day frost forecasting in a tea plantation in Danyang, eastern China. Leveraging nine years (2008–2016) of multi-source data—including high-resolution on-site meteorological observations and daily records from surrounding regional stations—we engineered a comprehensive set of predictive features capturing local microclimatic, regional synoptic, and short-term temporal dynamics. A two-stage feature selection approach, combining Spearman correlation screening with SHAP-based importance ranking, identified an optimal subset of 14 robust predictors. Among eight benchmarked models, XGBoost achieved the best performance on a chronologically held-out test set, yielding a CSI of 0.736, accuracy of 91.0%, F1-Score of 0.848 and AUC-ROC of 0.968. Ablation experiments demonstrated the added value of data integration: model performance improved from a CSI of 0.617 (using only local data) to 0.736 (with full multi-source inputs). SHAP interpretability analysis further revealed that the model’s predictions align with established frost formation physics, highlighting key drivers such as nocturnal cooling rate and regional humidity. This work demonstrates that integrating multi-scale meteorological data with interpretable machine learning offers a reliable, transparent, and operationally viable tool for frost risk management—providing actionable insights to enhance resilience in precision horticulture for perennial crops like tea. Full article

Background/Objectives: Virtual surgical planning (VSP) allows three-dimensional assessment of complex dentofacial deformities and has become integral to modern orthognathic surgery. However, evidence remains limited regarding how skeletal characteristics and malocclusion patterns translate into surgical movement selection. This study aimed to evaluate demographic features, skeletal malocclusion patterns, and clinical treatment strategies in patients undergoing VSP-guided orthognathic surgery. Methods: This retrospective study included 158 patients who underwent VSP-assisted orthognathic surgery between 2019 and 2025. Sagittal skeletal classification, vertical growth pattern, facial asymmetry, and maxillary crossbite were evaluated together with planned maxillary and mandibular movements. Surgical procedures were analyzed according to skeletal malocclusion classes (Class I, II, and III). Group comparisons were performed using chi-square and Kruskal–Wallis tests. Multivariable logistic regression analysis was conducted to assess factors associated with bimaxillary surgery (p < 0.05). Results: Skeletal Class I malocclusion was most prevalent (46.8%), followed by Class III (29.7%) and Class II (23.4%). Hyperdivergent growth patterns were predominantly observed in Class II patients, whereas normodivergent patterns were most common in Class III cases (p < 0.05). Mandibular advancement and setback generally followed expected class-based trends but were also observed across non-corresponding skeletal classes. Maxillary impaction and mandibular autorotation were frequently incorporated. Bimaxillary surgery was performed in 84.2% of cases. Logistic regression analysis showed no independent predictors of bimaxillary surgery (p > 0.05). Conclusions: VSP-assisted orthognathic surgery demonstrates that surgical planning cannot be reduced to sagittal skeletal classification alone. Treatment decisions are shaped by combined sagittal, vertical, transverse, and patient-specific factors, supporting a multidimensional and individualized planning approach. Full article

Background: Diabetes mellitus is a global health challenge, especially among homeless people. Early prediction of diabetes can reduce treatment costs and improve interventions. This study aimed to identify predictors of diabetes among homeless adults by utilizing artificial intelligence and providing recommendations for diabetes prevention. Methods: A case-control study of 150 homeless adults in Giza, Egypt (99 diabetes cases and 51 controls), analyzed 43 variables collected through interviews and physiological measures, with missing data imputed. Feature selection using recursive feature elimination and univariate and correlation analyses reduced the predictors to 13 variables. The class imbalance was addressed using synthetic minority over-sampling on the training set. Six models and a stacking ensemble with XGBoost as a meta-learner were evaluated using 5-fold cross-validation and performance metrics, including the accuracy, precision, recall, F1-score, and AUC-ROC. Results: The key predictors included BMI, systolic blood pressure, triceps skinfold thickness, waist circumference, lifestyle factors, comorbidities, diastolic blood pressure, age, medication adherence, educational level, marital status, duration of residence, and diabetes knowledge. Individual classifiers achieved a moderate performance (accuracy: 56.7–70.0%, F1-score: 0.686–0.781). The stacking ensemble substantially outperformed individual models, achieving a 95.45% accuracy, a 100% precision, a 93.75% recall, a 0.968 F1-score, and a 0.979 AUC-ROC on the test set. Conclusions: Machine learning models can reliably predict diabetes. The proposed hybrid stacking model outperformed conventional classifiers in terms of the prediction performance, highlighting the benefits of ensemble learning and sophisticated resampling strategies in dealing with imbalanced medical data. It is recommended that healthcare institutions integrate AI-powered diagnostic assistance technology into clinical processes to aid in the early detection and treatment of diabetes. Full article

Background: Plant-rich dietary patterns are widely associated with metabolic and gastrointestinal health benefits. However, individuals consuming predominantly plant-based foods may also experience chronic low-dose exposure to dietary pesticide residues. At the same time, physical activity is recognized as an important lifestyle factor influencing metabolic health and gut microbiome composition. How microbiome features and microbiome-related metabolic profiles vary according to physical activity level in adults consuming plant-rich diets and reporting gastrointestinal symptoms remains insufficiently characterized. Objective: To explore associations between physical activity level, gut microbiome characteristics, and urinary organic acid patterns in adults consuming predominantly plant-rich diets and experiencing gastrointestinal symptoms, within a cohort characterized by comparable estimated dietary pesticide exposure used as a contextual dietary background variable. Methods: This cross-sectional observational study included 93 adults consuming ≥50% plant-based foods for at least six months and reporting persistent gastrointestinal symptoms. Participants were stratified according to physical activity level using WHO-based thresholds (<150 vs. ≥150 min/week of moderate-intensity activity). Stool microbiota were assessed using a targeted quantitative PCR panel, and microbial diversity was summarized using a laboratory-derived Shannon index. A voluntary subgroup (n = 50) underwent targeted urinary organic acid analysis (LC–MS/MS). Dietary pesticide exposure was indirectly estimated using national surveillance data combined with individual dietary records and was applied uniformly across groups. Analyses were primarily descriptive and exploratory; results are presented as associations. Results: Estimated dietary pesticide exposure did not differ between physical activity groups. Participants with lower physical activity were older and exhibited lower microbial diversity and a higher prevalence of reduced abundance in selected commensal taxa. Differences were observed in selected intermediary organic acid markers, while no statistically significant difference was found for the bile acid-related indicator. Several cross-domain correlations were identified between microbial features and metabolite patterns. However, given the cross-sectional design, age imbalance between groups, and subgroup-based metabolomic analyses, the findings should be interpreted as hypothesis-generating rather than indicative of independent effects of physical activity. Conclusions: In adults consuming plant-rich diets and reporting gastrointestinal symptoms, physical activity level was associated with distinct microbiome and microbiome-related metabolic patterns under comparable estimated dietary pesticide exposure. These findings highlight the potential contribution of lifestyle factors to interindividual variability in gut microbial and metabolic profiles, while underscoring the need for age-adjusted, longitudinal, and biomarker-based studies to clarify directionality and mechanisms. Full article

Existing remote sensing change detection methods often struggle to accurately capture the contours of complex change targets and subtle textural differences. This makes it difficult to effectively distinguish between the boundaries of change targets and the background. To address this challenge, we propose a novel method called spatial-frequency decoupling alignment encoding (SDA-Encoding), which is designed to fully leverage information from both the spatial and frequency domains. Specifically, we first use a Transformer encoder to extract bi-temporal features. Next, we apply wavelet transform to decouple these features into low-frequency and high-frequency components. In the multi-scale high-frequency interaction (MHI) module, we combine local spatial enhancement using spatial pyramid pooling with cross-scale dependency supplementation via the dual-domain alignment fusion (DAF) module. Meanwhile, in the position-aware low-frequency enhancement (PLE) module, spatial position sensitivity is restored using coordinate attention, and region-level contextual dependencies are captured through the selective fusion attention (SFA) module. Finally, the two frequency-domain branches are complementarily fused within the spatial domain to achieve unified detection of both fine-grained and structural changes. Experimental results on three benchmark datasets demonstrate the significant performance improvements of SDA-Encoding. Full article

Enhancing building energy performance has become an essential goal, particularly as building energy management systems (BEMSs) increasingly rely on high-quality data and reliable predictive models. Although machine learning (ML) models have been widely applied to building energy prediction, optimisation, and management, their reliability in practice is often constrained by data preprocessing rather than algorithm selection. Existing studies often emphasise algorithmic development while providing limited systematic investigation of preprocessing practices, leading to methodological misconceptions and reduced robustness of ML-driven building energy management. As a novel contribution, this article presents a systematic review of 73 scientific articles published from 2020 to 2025 in the field of preprocessing practices. To this goal, a three-step data preprocessing workflow is organised, comprising data analysis, data preparation, and feature engineering. The strengths, limitations, and recurring misconceptions of preprocessing techniques adopted in the analysed studies are synthesised, with emphasis on their impact on prediction accuracy, interpretability, and model robustness. As a result, this review reframes the data preprocessing stage as a decision-making process in which data analysis and the energy improvement task constrain and inform subsequent data preparation and feature engineering steps to address building energy performance enhancement tasks. Full article

Severe hypercalcemia is a life-threatening condition requiring immediate treatment alongside a systematic evaluation to identify the underlying cause. Although malignancy is a common etiology among hospitalized patients, alternative causes must be considered to guide targeted therapy, as illustrated in these cases. The first case involved a 31-year-old postpartum woman with corrected calcium levels of 14.5 mg/dL and suppressed PTH. Hypercalcemia resolved after tapering and temporary cessation of breastfeeding, consistent with lactation-associated hypercalcemia that is likely PTHrP-mediated. The second case describes a 30-year-old woman who presented with hypotension, hypercalcemia, hyperphosphatemia, and low PTH. A systematic evaluation revealed severe glucocorticoid deficiency consistent with primary adrenal insufficiency (Addison’s disease). The final case featured a 47-year-old man with severe symptomatic hypercalcemia (18.5 mg/dL) and markedly elevated PTH. Imaging revealed a 3 cm parathyroid tumor. Selective parathyroidectomy produced a rapid intraoperative PTH decline, and pathology supported parathyroid adenoma rather than carcinoma. Together, these cases highlight that symptomatic severe hypercalcemia is a medical emergency warranting prompt clinical intervention, followed by an early PTH-based stratification to direct a focused, stepwise diagnostic workup and definitive management. Full article

Bank telemarketing campaigns often experience low subscription rates due to customer heterogeneity and severe class imbalance, which pose challenges for reliable predictive modeling. This study investigates a data-driven approach that integrates synthetic minority oversampling and cost-sensitive learning to improve the prediction of telemarketing outcomes. Experiments are conducted using the Portuguese Bank Marketing dataset, comprising 41,188 instances with a positive response rate of 11.3%. Eight machine learning models are evaluated under a unified preprocessing pipeline and five-fold stratified cross-validation, including Logistic Regression, Decision Tree, Random Forest, and Ensemble methods. The results show that Ensemble models, particularly CatBoost, XGBoost, and LightGBM, achieve improved performance compared with traditional baselines, with notable gains in minority-class recall and overall discrimination ability. The best-performing model attains an F1-score of 0.540, a recall of 0.812 for the positive class, and a ROC–AUC of 0.908. To enhance interpretability, SHAP-based analysis is applied to quantify feature contributions, identifying campaign duration, previous contact outcomes, and selected macroeconomic indicators as key predictors. These findings indicate that combining resampling strategies with cost-sensitive optimization provides a robust and transparent approach for learning from imbalanced telemarketing data, thereby supporting reproducible and data-driven financial decision-making by explicitly addressing difficulty in minority-class identification under imbalance and class imbalance under cross-entropy training in imbalanced banking data. Full article

Graph Neural Networks (GNNs) have emerged as the standard for learning representations from graph-structured data. While traditional architectures relying on message-passing mechanisms excel in homophilic settings, they essentially function as fixed low-pass filters. However, this smoothing operation limits their ability to generalize to heterophilic graphs, where connected nodes often exhibit dissimilar labels and high-frequency signals are crucial for discrimination. Furthermore, existing Mixture-of-Experts (MoE) methods for graphs often suffer from local-view routing, failing to capture global structural context during expert selection. To address these challenges, this paper proposes SS-AdaMoE, a novel Spatio-Spectral Adaptive Mixture of Experts framework designed for robust node classification across diverse graph patterns. Specifically, a Dual-Domain Expert System is constructed, integrating heterogeneous spatial aggregators with learnable spectral filters based on Bernstein polynomials. This allows the model to adaptively capture arbitrary frequency responses—including high-pass and band-pass signals—which are overlooked by standard GNNs. To resolve the locality bias, a Hierarchical Global-Prior Gating Network augmented by a Linear Graph Transformer is introduced, ensuring that expert selection is guided by both local node features and global topological awareness. Extensive experiments are conducted on five benchmark datasets spanning both homophilic and heterophilic networks. The results demonstrate that SS-AdaMoE consistently outperforms baselines, achieving accuracy improvements of up to 2.65% on Chameleon and 1.41% on Roman-empire over the strongest MoE baseline, while surpassing traditional GCN architectures by margins exceeding 28% on heterophilic datasets such as Texas. These findings validate that the synergy of learnable spectral priors and global gating effectively bridges the gap between spatial aggregation and spectral filtering. Full article