Search Results (369)

Background/Objectives: Foot mobility is considered an intrinsic risk factor for lower-limb injury, yet commonly used pronated/neutral/supinated classifications rely on arbitrary cut-points. This study aimed to develop a data-driven framework for characterizing a continuous SSNDT–injury risk gradient and deriving clinically interpretable relative-risk bands that define practical injury risk zones along the sit-to-stand navicular drop test (SSNDT) continuum. Methods: Data from 137 physically active male students (274 feet) were analyzed. Intra-rater reliability of the sit-to-stand navicular drop test (SSNDT) was assessed using ICC(3,1). A quadratic mixed-effects logistic regression model was used to characterize the SSNDT–injury relationship and derive odds-ratio-based risk bands for interpretive and screening purposes. Results: SSNDT demonstrated good intra-rater reliability (ICC(3,1) = 0.82). Model comparison supported a non-linear, U-shaped association between SSNDT and injury risk, with a minimum risk value at approximately 5.5 mm. Bootstrap analysis supported a smooth continuous risk gradient. Four representative OR levels (1.2, 1.5, 1.8, and 2.0) were selected to define SSNDT-based interpretative risk bands. Injury prevalence showed an overall increasing trend across these zones, ranging from 4.2% in the Safe zone to 52.4% in the Extreme zone. Conclusions: SSNDT provides a robust, data-driven basis for quantifying foot-mobility–related injury risk along a continuous non-linear gradient and for deriving clinically interpretable relative-risk bands grounded in a validated model. The proposed framework avoids arbitrary cut-points and supports individualized risk screening. Full article

Research on extracting building from airborne point clouds is abundant, yet discussions regarding scenarios where vegetation and building structures are closely intertwined with similar height in rural areas remain relatively scarce. This thesis adopts a region representative of typical rural building features in China as an experimental site to conduct research on building classification procedures from airborne point clouds. Firstly, the multi-level grid size is dynamically determined through slope analysis to creatively segment and recognize terrain type, then differentiated filtering parameters are applied to various terrains to fully extract ground points, providing a ground reference for building classification. Secondly, the selection of building Region of Interest is conducted by multiple geometric feature differences between building and other objects based on watershed segmentation results, which eliminates interference from non-building points, significantly reducing redundant and unnecessary mathematical computation. Finally, refined building classification is achieved based on multiple morphological differences between buildings and other objects. The experimental results show that the precision, recall, and F1 of both datasets exceeded 93.37%, 97.05%, and 95.17%, respectively. The average precision, recall, and F1 reached 94.02%, 97.20%, and 95.58%, respectively. This method demonstrates successful building classification in rural areas, showing strong adaptability and practicality for the extraction of various building data. Full article

Satellite communication systems experience significant signal degradation during rain events, a phenomenon that can be leveraged for meteorological applications. This study introduces a novel hybrid machine learning framework combining unsupervised clustering with cluster-specific supervised deep learning models to transform satellite signal attenuation into a predictive tool for rainfall prediction. Unlike conventional single-model approaches treating all atmospheric conditions uniformly, our methodology employs K-Means Clustering with the Elbow Method to identify four distinct atmospheric regimes based on Signal-to-Noise Ratio (SNR) patterns from a 12-m Ku-band satellite ground station at King Mongkut’s Institute of Technology Ladkrabang (KMITL), Bangkok, Thailand, combined with absolute pressure and hourly rainfall measurements. The dataset comprises 98,483 observations collected with 30-s temporal resolutions, providing comprehensive coverage of diverse tropical atmospheric conditions. The experimental platform integrates three subsystems: a receiver chain featuring a Low-Noise Block (LNB) converter and Software-Defined Radio (SDR) platform for real-time data acquisition; a control system with two-axis motorized pointing incorporating dual-encoder feedback; and a preprocessing workflow implementing data cleaning, K-Means Clustering (k = 4), Synthetic Minority Over-Sampling Technique (SMOTE) for balanced representation, and standardization. Specialized Long Short-Term Memory (LSTM) networks trained for each identified cluster enable capture of regime-specific temporal dynamics. Experimental validation demonstrates substantial performance improvements, with cluster-specific LSTM models achieving R² values exceeding 0.92 across all atmospheric regimes. Comparative analysis confirms LSTM superiority over RNN and GRU. Classification performance evaluation reveals exceptional detection capabilities with Probability of Detection ranging from 0.75 to 0.99 and False Alarm Ratios below 0.23. This work presents a scalable approach to weather radar systems for tropical regions with limited ground-based infrastructure, particularly during rapid meteorological transitions characteristic of tropical climates. Full article

Early spring frost is a major meteorological hazard during the Apple Flowering period. To improve frost event prediction, this study proposes a hybrid 1D-CNN-BiLSTM-Attention model, with its core novelty lying in the integrated dual attention mechanism (Self-attention and Cross-variable Attention) and hybrid architecture. The 1D-CNN extracts extreme points and mutation features from meteorological factors, while BiLSTM captures long-term patterns such as cold wave accumulation. The dual attention mechanisms dynamically weight key frost precursors (low temperature, high humidity, calm wind), aiming to enhance the model’s focus on critical information. Using 1997–2016 data from Luochuan (four variables: Ground Surface Temperature (GST), Air Temperature (TEM), Wind Speed (WS), Relative Humidity (RH)), a segmented interpolation method increased temporal resolution to 4 h, and an adaptive Savitzky–Golay Filter reduced noise. For frost classification, Recall, Precision, and F1-score were higher than those of baseline models, and the model showed good agreement with the actual frost events in Luochuan on 6, 9, and 10 April 2013. The 4 h lead time could provide growers with timely guidance to take mitigation measures, alleviating potential losses. This research may offer modest technical references for frost prediction during the Apple Flowering period in similar regions. Full article

In urban underground space construction using shield tunnelling, the geological conditions ahead of the tunnel face are often uncertain. Without timely and accurate classification of the ground type, mismatches in operational parameters, uncontrolled costs, and schedule risks are likely to occur. Using observations from an earth pressure balance (EPB) project on an urban railway, a data-driven classification framework is developed that integrates shield tunnelling operating measurements with physically derived quantities to discriminate among soft soil, hard rock, and mixed strata. Principal component analysis (PCA) is performed on the training set, followed by a systematic comparison of tree-based classifiers and hyperparameter optimization strategies to explore the attainable performance. Under unified evaluation criteria, a categorical bosting (CatBoost) model optimized by a Nevergrad combination strategy (NGOpt) attains the highest test accuracy of 0.9625, with macro-averaged precision and macro-averaged recall of 0.9715 and 0.9716, respectively. To mitigate optimism from single-point estimates, stratified bootstrap intervals are reported for the test set. A Monte Carlo experiment applies independent perturbations to the PCA-transformed features, producing low label-flip rates across the three classes, with only minor changes in probability calibration metrics, which suggests consistent decisions under sensor noise and sampling bias. Overall, within the scope of the considered EPB project, the study delivers a compact workflow that demonstrates the feasibility of uncertainty-aware ground-type classification and provides a methodological reference for developing decision-support tools in underground tunnel construction. Full article

The increasing scale and operational complexity of cyberattacks have exposed the limitations of static taxonomies for representing multistage threat scenarios. This study addresses the need for more flexible classification models by proposing a relational taxonomy of cyberattacks grounded in documented incidents. Therefore, the main objective is to propose a relational taxonomy that encodes direct transitions across eight groups in a dependency matrix and a directed graph while preserving traceability to MITRE ATT&CK. The taxonomy was validated by an independent panel of experts who assessed methodological clarity and operational utility. The results reveal consistent transition patterns across groups, delineate reproducible escalation routes, and pinpoint cut-off points linked to specific detection and control activities, providing an operational map of progression and intervention. The conclusions show that the taxonomy clarifies escalation paths, strengthens alignment across security monitoring and incident response functions, threat intelligence workflows and training, and provides an operational structure to manage interdependencies, anticipate escalation and focus monitoring on critical points. Full article

Weeding in melon and watermelon fields requires selective and pinpoint operation because the crop plants are sensitive to herbicides and tend to grow on the ground in all directions. Hyperspectral images have high spectral and spatial resolution, enabling an object’s classification according to its spectral properties. Spectral band selection is a common practice with hyperspectral images, as it reduces the number of bands in use with only a minor effect on the results. This study’s innovative contribution is the development and validation of a practical methodology to simplify complex hyperspectral data for real-world robotic weed management. This includes the introduction of the ‘normalized crop sample index’ (NCSI) to guide band selection and the use of machine learning methods, which revealed a set of four spectral bands—480 nm, 550 nm, 686 nm and 750 nm—that hold sufficient discriminating information between weeds and watermelon crop. This minimal set of bands enables the simulation and future development of a low-cost, high-speed multispectral camera system. An XGBoost model showed the lowest misclassification error level of 2–14%. The selected spectral bands were used to extract single-band images from the hyperspectral cube. In these images, vegetation pixels were separated using a normalized difference vegetation index filter, and each pixel was classified into a crop or weed class. The classified pixels were grouped into segmented objects, and weeding points were selected, suitable for robotic pinpoint operation. Full article

Background: During postoperative recovery, patients and their caregivers often lack crucial information, leading to numerous repetitive inquiries that burden healthcare providers. Traditional discharge materials, including paper handouts and patient portals, are often static, overwhelming, or underutilized, leading to patient overwhelm and contributing to unnecessary ER visits and overall healthcare overutilization. Conversational chatbots offer a solution, but Natural Language Processing (NLP) systems are often inflexible and limited in understanding, while powerful Large Language Models (LLMs) are prone to generating “hallucinations”. Objective: To combine the deterministic framework of traditional NLP with the probabilistic capabilities of LLMs, we developed the AI Virtual Assistant (AIVA) Platform. This system utilizes a retrieval-augmented generation (RAG) architecture, integrating Gemini 2.0 Flash with a medically verified knowledge base via Google Vertex AI, to safely deliver dynamic, patient-facing postoperative guidance grounded in validated clinical content. Methods: The AIVA Platform was evaluated through 750 simulated patient interactions derived from 250 unique postoperative queries across 20 high-frequency recovery domains. Three blinded physician reviewers assessed formal system performance, evaluating classification metrics (accuracy, precision, recall, F1-score), relevance (SSI Index), completeness, and consistency (5-point Likert scale). Safety guardrails were tested with 120 out-of-scope queries and 30 emergency escalation scenarios. Additionally, groundedness, fluency, and readability were assessed using automated LLM metrics. Results: The system achieved 98.4% classification accuracy (precision 1.0, recall 0.98, F1-score 0.9899). Physician reviews showed high completeness (4.83/5), consistency (4.49/5), and relevance (SSI Index 2.68/3). Safety guardrails successfully identified 100% of out-of-scope and escalation scenarios. Groundedness evaluations demonstrated strong context precision (0.951), recall (0.910), and faithfulness (0.956), with 95.6% verification agreement. While fluency and semantic alignment were high (BERTScore F1 0.9013, ROUGE-1 0.8377), readability was 11th-grade level (Flesch–Kincaid 46.34). Conclusion: The simulated testing demonstrated strong technical accuracy, safety, and clinical relevance in simulated postoperative care. Its architecture effectively balances flexibility and safety, addressing key limitations of standalone NLP and LLMs. While readability remains a challenge, these findings establish a solid foundation, demonstrating readiness for clinical trials and real-world testing within surgical care pathways. Full article

Air quality monitoring and forecasting has been a challenging problem for years. In addition to traditional ground-based observational stations, in recent years there have been more geostationary and polar orbiting satellite observations on air quality. However, evaluation of performance of these observations is lacking, especially for the region of southern China, which is rarely affected by severe sand/dust weather. In the spring of 2025, two events of sand/dust weather, one case of sand/dust spreading to southern China in April and another case of sand/dust confining to northern China in May, provide a good opportunity for detailed case study and examination of the performance of the tools. The surface particulate matter (PM) concentration retrieved from a geostationary satellite, Geostationary Korea Multi-Purpose Satellite—2B (GEO-KOMPSAT-2B, or GK2B), is studied by checking consistency with the analysis of two numerical models: the Copernicus Atmosphere Monitoring Service model of the European Centre of Medium Range Weather Forecast (ECMWF-CAMS) and Chinese Unified Atmospheric Chemistry Environment model of the China Meteorological Administration (CMA-CUACE). The former shows comparable PM concentration with satellite observations, while overestimation is found with the latter. It is also found that there may be latitude dependence of the quality of the satellite-based data. To further validate the satellite observation data, it is directly compared with the ground-based station measurements in Hong Kong for the event in mid-April 2025, the performance of satellite data points near Hong Kong is generally satisfactory. For polar orbiting satellite, there is information about the aerosol classification in addition to aerosol optical depth, and the classification result is found to be reasonable by comparison with ground-based observation, though some refinements appear to be necessary. The geostationary satellite images provide high spatial coverage and frequently updated air quality data, which are confirmed to be useful in monitoring the southward spread of sand/dust weather to southern China which is a very rare event. The monitoring can be both qualitative and quantitative. The performance of various monitoring and forecasting tools is examined in details based on the cases. It also forms a reference for the use in operation, and opens up a new era for air quality study for southern China. Full article

The objective of this study is to analyze spatial entropy flows that reveal the directional dynamics of climate change—patterns that remain obscured in traditional statistical analyses. This approach enables the identification of pathways for “climate information transport”, highlights associations with atmospheric circulation types, and allows for the localization of both sources and “informational voids”—regions where entropy is dissipated. The analytical framework is grounded in a quantitative assessment of long-term climate variability across Europe over the period 1901–2010, utilizing Shannon entropy as a measure of atmospheric system uncertainty and variability. The underlying assumption is that the variability of temperature and precipitation reflects the inherently dynamic character of climate as a nonlinear system prone to fluctuations. The study focuses on calculating entropy estimated within a 70-year moving window for each calendar month, using bivariate distributions of temperature and precipitation modeled with copula functions. Marginal distributions were selected based on the Akaike Information Criterion (AIC). To improve the accuracy of the estimation, a block bootstrap resampling technique was applied, along with numerical integration to compute the Shannon entropy values at each of the 4165 grid points with a spatial resolution of 0.5° × 0.5°. The results indicate that entropy and its derivative are complementary indicators of atmospheric system instability—entropy proving effective in long-term diagnostics, while its derivative provides insight into the short-term forecasting of abrupt changes. A lag analysis and Spearman rank correlation between entropy values and their potential supported the investigation of how circulation variability influences the occurrence of extreme precipitation events. Particularly noteworthy is the temporal derivative of entropy, which revealed strong nonlinear relationships between local dynamic conditions and climatic extremes. A spatial analysis of the information entropy field was also conducted, revealing distinct structures with varying degrees of climatic complexity on a continental scale. This field appears to be clearly structured, reflecting not only the directional patterns of change but also the potential sources of meteorological fluctuations. A field-theory-based spatial classification allows for the identification of transitional regions—areas with heightened susceptibility to shifts in local dynamics—as well as entropy source and sink regions. The study is embedded within the Fokker–Planck formalism, wherein the change in the stochastic distribution characterizes the rate of entropy production. In this context, regions of positive divergence are interpreted as active generators of variability, while sink regions function as stabilizing zones that dampen fluctuations. Full article

Classifying games according to their strategic properties provides meaningful insights into the motivations driving the interacting parties, suggests possible future trajectories, and in some cases also points to potential interventions aiming to influence the interactions’ outcomes. Here, we present a new classification that merges two perspectives: (i) a revised version of Rapoport and Guyer’s taxonomy, which extends beyond the original 78 games they describe by classifying all two-by-two games according to fundamental strategic properties, and (ii) a novel classification grounded in the theory of subjective expected relative similarity, which addresses not only the games’ payoffs but also the players’ strategic perceptions of their opponents. While Rapoport and Guyer’s original taxonomy classifies only strictly-ordinal games, the revised classification addresses all two-by-two games. It comprises eleven categories that are further grouped into five super-categories that focus on the game’s expected outcome and its strategic stability. The second, similarity-based, classification comprises four main categories, specifying whether players’ perceptions of their opponents have the potential to influence strategic decision-making. The merged classification comprises 14 game types, offering a holistic account of the strategic interaction, the players’ underlying motivations, and the expected outcome. It combines the fixed strategic properties with the variable social aspects of the interaction. Moreover, the novel classification points to the potential of social interventions that may influence the game’s outcome by altering strategic similarity perceptions. Therefore, the present work is relevant for both theoretical and experimental research, providing insights into actual choices expected inside and outside of the laboratory. Full article

Reliable and representative ground data is fundamental for accurate crop classification using satellite imagery. This study demonstrates a structured approach to ground truth planning in the Bareilly district, Uttar Pradesh, where wheat is the dominant crop. Pre-season spectral clustering of Sentinel-2 Level-2A NDVI time-series data (November–March) was applied to identify ten spectrally distinct zones across the district, capturing phenological and land cover variability. These clusters were used at the village level to guide spatially stratified and optimized field sampling, ensuring coverage of heterogeneous and agriculturally significant areas. A total of 197 ground truth points were collected using the iCrops mobile application, enabling standardized and photo-validated data collection with offline functionality. The collected ground observations formed the basis for random forest supervised classification, enabling clear differentiation between major land use and land cover (LULC) classes with an overall accuracy of 91.6% and a Kappa coefficient of 0.886. The findings highlight that systematic ground data collection significantly enhances the reliability of remote sensing-based crop mapping. The outputs serve as a valuable resource for agricultural planners, policymakers, and local stakeholders by supporting crop monitoring, land use planning, and informed decision-making in the context of sustainable agricultural development. Full article

Addressing the challenge of acquiring high-precision leader Unmanned Ground Vehicle (UGV) pose information in real time for communication-denied leader–follower formations, this study proposed Pillar-Bin, a 3D object detection algorithm based on the PointPillars framework. Pillar-Bin introduced an Interval Discretization Strategy (Bin) within the detection head, mapping critical target parameters (dimensions, center, heading angle) to predefined intervals for joint classification-residual regression optimization. This effectively suppresses environmental noise and enhances localization accuracy. Simulation results on the KITTI dataset demonstrate that the Pillar-Bin algorithm significantly outperforms PointPillars in detection accuracy. In the 3D detection mode, the mean Average Precision (mAP) increased by 2.95%, while in the bird’s eye view (BEV) detection mode, mAP was improved by 0.94%. With a processing rate of 48 frames per second (FPS), the proposed algorithm effectively enhanced detection accuracy while maintaining the high real-time performance of the baseline method. To evaluate Pillar-Bin’s real-vehicle performance, a leader UGV pose extraction scheme was designed. Real-vehicle experiments show absolute X/Y positioning errors below 5 cm and heading angle errors under 5° in Cartesian coordinates, with the pose extraction processing speed reaching 46 FPS. The proposed Pillar-Bin algorithm and its pose extraction scheme provide efficient and accurate leader pose information for formation control, demonstrating practical engineering utility. Full article

Crop canopy height is a key structural indicator that is strongly associated with crop development, biomass accumulation, and crop health. To overcome the limitations of time-consuming and labor-intensive traditional field measurements, Unmanned Aerial Vehicle (UAV)-based Light Detection and Ranging (LiDAR) offers an efficient alternative by capturing three-dimensional point cloud data (PCD). In this study, UAV-LiDAR data were acquired using a DJI Matrice 600 Pro equipped with a 16-channel LiDAR system. Three canopy height estimation methodological approaches were evaluated across three crop types: corn, soybean, and winter wheat. Specifically, this study assessed machine learning regression modeling, ground point classification techniques, percentile-based method and a newly proposed Dual-Range Averaging (DRA) method to identify the most effective method while ensuring practicality and reproducibility. The best-performing method for corn was Support Vector Regression (SVR) with a linear kernel (R² = 0.95, RMSE = 0.137 m). For soybean, the DRA method yielded the highest accuracy (R² = 0.93, RMSE = 0.032 m). For winter wheat, the PointCNN deep learning model demonstrated the best performance (R² = 0.93, RMSE = 0.046 m). These results highlight the effectiveness of integrating UAV-LiDAR data with optimized processing methods for accurate and widely applicable crop height estimation in support of precision agriculture practices. Full article

This article introduces an algorithm that uses a U-Net architecture to determine vertical ground surface displacements from unmanned aerial vehicle (UAV)-photogrammetry point clouds, offering an alternative to traditional ground filtering methods. Unlike conventional ground filters that rely on point cloud classification, the proposed approach employs heteroscedastic regression. The U-Net model predicts the conditional expected values of the elevation corrections, aiming to reduce the impact of vegetation on determined ground surface elevations. Concurrently, it estimates the logarithm of the elevation correction variance, allowing for direct quantification of the uncertainty associated with each elevation correction value. The algorithm was evaluated using three metrics: the root mean square error (RMSE) of vertical displacements, the percentage of nodes with determined displacement values, and the percentage of outliers among those values. Performance was assessed using the technique for order of preference by similarity to ideal solution (TOPSIS) method and compared against several ground-filter-based algorithms across four datasets, each including at least two time intervals. In most cases, the U-Net-based approach demonstrated a slight performance advantage over traditional ground filtering techniques. For example, for the U-Net-based algorithm, for one of the test datasets, the RMSE of the determined subsidences was 6.1 cm, the percentage of nodes with determined subsidences was 80.5%, and the percentage of outliers was 0.2%. For the same case, the algorithm based on the next best model (SMRF) allowed an RMSE of 7.7 cm to be obtained; for 77.3% of nodes, the subsidences were determined; and the percentage of outliers was 0.3%. Full article