Search Results (178)

Reconstructing 3D human motion from monocular video presents challenges when frames contain occlusions or blur, as conventional approaches depend on features extracted within limited temporal windows, resulting in structural distortions. In this paper, we introduce a novel framework that combines temporal probability guidance with graph topology learning to achieve robust 3D human mesh reconstruction from incomplete observations. Our method leverages topology-aware probability distributions spanning entire motion sequences to recover missing anatomical regions. The Graph Topological Modeling (GTM) component captures structural relationships among body parts by learning the inherent connectivity patterns in human anatomy. Building upon GTM, our Temporal-alignable Probability Distribution (TPDist) mechanism predicts missing features through probabilistic inference, establishing temporal coherence across frames. Additionally, we propose a Hierarchical Human Loss (HHLoss) that hierarchically regularizes probability distribution errors for inter-frame features while accounting for topological variations. Experimental validation demonstrates that our approach outperforms state-of-the-art methods on the 3DPW benchmark, particularly excelling in scenarios involving occlusions and motion blur. Full article

This paper presents an Artificial Intelligence (AI)-driven framework for high-precision indoor localization using single-link Wi-Fi channel state information (CSI), targeting real-time deployment in complex multipath environments. To overcome challenges such as signal distortion and environmental dynamics, the proposed system integrates adaptive and unsupervised intelligence modules into the localization pipeline. A refined two-stage time-of-flight (TOF) estimation method is introduced, combining a minimum-norm algorithm with a probability-weighted refinement mechanism that improves ranging accuracy under non-line-of-sight (NLOS) conditions. Simultaneously, an adaptive parameter-tuned DBSCAN algorithm is applied to angle-of-arrival (AOA) sequences, enabling unsupervised spatio-temporal clustering for stable direction estimation without requiring prior labels or environmental calibration. These AI-enabled components allow the system to dynamically suppress multipath interference, eliminate positioning ambiguity, and maintain robustness across diverse indoor layouts. Comprehensive experiments conducted on the Widar2.0 dataset demonstrate that the proposed method achieves decimeter-level accuracy with an average localization error of 0.63 m, outperforming existing methods such as “Widar2.0” and “Dynamic-MUSIC” in both accuracy and efficiency. This intelligent and lightweight architecture is fully compatible with commodity Wi-Fi hardware and offers significant potential for real-time human tracking, smart building navigation, and other location-aware AI applications. Full article

Surface deformation induced by the extraction of natural resources constitutes a non-stationary spatiotemporal process. Modeling surface deformation time series obtained through Interferometric Synthetic Aperture Radar (InSAR) technology using deep learning methods is crucial for disaster prevention and mitigation. However, the complexity of model hyperparameter configuration and the lack of interpretability in the resulting predictions constrain its engineering applications. To enhance the reliability of model outputs and their decision-making value for engineering applications, this study presents a workflow that combines a Tree-structured Parzen Estimator (TPE)-based Bayesian optimization approach with ensemble inference. Using the Rhineland coalfield in Germany as a case study, we systematically evaluated six deep learning architectures in conjunction with various spatiotemporal coding strategies. Pairwise comparisons were conducted using a Welch t-test to evaluate the performance differences across each architecture under two parameter-tuning approaches. The Benjamini–Hochberg method was applied to control the false discovery rate (FDR) at 0.05 for multiple comparisons. The results indicate that TPE-optimized models demonstrate significantly improved performance compared to their manually tuned counterparts, with the ResNet+Transformer architecture yielding the most favorable outcomes. A comprehensive analysis of the spatial residuals further revealed that TPE optimization not only enhances average accuracy, but also mitigates the model’s prediction bias in fault zones and mineralize areas by improving the spatial distribution structure of errors. Based on this optimal architecture, we combined the ten highest-performing models from the optimization stage to generate a quantile-based susceptibility map, using the ensemble median as the central predictor. Uncertainty was quantified from three complementary perspectives: ensemble spread, class ambiguity, and classification confidence. Our analysis revealed spatial collinearity between physical uncertainty and absolute residuals. This suggests that uncertainty is more closely related to the physical complexity of geological discontinuities and human-disturbed zones, rather than statistical noise. In the analysis of super-threshold probability, the threshold sensitivity exhibited by the mining area reflects the widespread yet moderate impact of mining activities. By contrast, the fault zone continues to exhibit distinct high-probability zones, even under extreme thresholds. It suggests that fault-controlled deformation is more physically intense and poses a greater risk of disaster than mining activities. Finally, we propose an engineering decision strategy that combines uncertainty and residual spatial patterns. This approach transforms statistical diagnostics into actionable, tiered control measures, thereby increasing the practical value of susceptibility mapping in the planning of natural resource extraction. Full article

The paper presents a statistical model based on the two-weighted exponential distribution (TWED) to examine censored Human Immunodeficiency Virus (HIV) survival information. Identifying HIV as a disability, the study endorses an inclusive and sustainable health policy framework through some predictive findings. The TWED provides an accurate representation of the inherent hazard patterns and also improves the modelling of survival data. The parameter estimation is achieved in both a classical maximum likelihood estimation (MLE) and a Bayesian approach. Bayesian inference can be carried out under general entropy loss conditions and the symmetric squared error loss function through the Markov Chain Monte Carlo (MCMC) method. Based on the symmetric properties of the inverse of the Fisher information matrix, the asymptotic confidence intervals (ACLs) for the MLEs are constructed. Moreover, two-sided symmetric credible intervals (CRIs) of Bayesian estimates are also constructed based on the MCMC results that are based on symmetric normal proposals. The simulation studies are very important for indicating the correctness and probability of a statistical estimator. Implementing the model on actual HIV data illustrates its usefulness. Altogether, the paper supports the idea that statistics play an essential role in promoting disability-friendly and sustainable research in the field of public health in general. Full article

Background: The intestinal microflora is a population of microorganisms that resides in the human gastrointestinal tract and is important in maintaining metabolic and immune homeostasis in the body. Bacteria residing in the intestine produce short-chain fatty acids (SCFAs), which communicate with, among other things, the brain–gut axis—disorders of which are one of the causes of MS-like pathologies. A particular property of SCFAs is the induction of regulatory T cells, which are finding their way into pioneering therapies for MS patients. The aim of the study is to evaluate SCFA secretion in patients with multiple sclerosis from the West Pomeranian region depending on the genotypes of rs778986 and rs3894326 polymorphisms of the FUT3 gene. Methods: The study group included 47 patients clinically diagnosed with MS. Genotyping was performed by real-time PCR using TaqMan probes. Analysis of short-chain fatty acids in faeces was performed on a quadrupole mass spectrometer coupled to a time-of-flight (QTOF) analyser coupled to an AB Sciex high-performance liquid chromatograph (UHPLC). Results: Statistical analysis did not reveal any statistically significant differences in the prevalence of the studied polymorphisms in MS patients compared to the healthy control group. It was observed that the intestinal microflora and SCFA production in MS patients may be disturbed, while the studied FUT3 gene polymorphisms probably do not have a significant effect on their concentrations. A statistical tendency towards higher caproic acid content in heterozygotes of the rs778986 polymorphism and higher valeric acid secretion in homozygotes of rs3894326 was demonstrated. Conclusions: In summary, the studied FUT3 gene polymorphisms are not overrepresented in patients with MS. The rs778986 FUT3 polymorphism may affect the caproic acid content in the faeces of patients with MS, and the rs3894326 polymorphism may affect valeric acid secretion. Due to the small sample size and sparse genotype groups, the study has limited power and negative findings may reflect Type II error; replication in larger cohorts is warranted. Full article

This study presents the development of a Korean-specific safety checklist for fishing vessels under 10 tons, aiming to strengthen self-safety management in small-scale fisheries. The research first reviewed representative European self-inspection systems and checklists from Norway, Denmark, the United Kingdom, and Ireland, which have established integrated safety management schemes combining self-managed risk assessment with periodic inspection. Following on these systems, three human and system analysis methods were employed: SRK/SLMV for identifying human error types and operational error mechanisms, CREAM for evaluating cognitive performance conditions and failure probabilities, and STPA for analyzing control-loop deficiencies and unsafe interactions within the system. Based on these analyses, a Korean-specific safety checklist was developed and structured into three components: Pre-operation, Post-operation, and Periodic Inspection. Each part was designed to reflect the actual operational characteristics of coastal fishing vessels while maintaining consistency with domestic regulatory requirements. The resulting checklist integrates human, technical, and organizational dimensions, providing a structured tool for evaluating risks and supporting self-assessment-based safety management in daily fishing operations. Full article

Background: Understanding how accident risk escalates during unfolding industrial events is essential for developing intelligent safety systems. This study proposes a large language model (LLM)-based framework that simulates human-like risk reasoning over sequential accident precursors. Methods: Using 100 investigation reports from the U.S. Chemical Safety Board (CSB), two Generative Pre-trained Transformer (GPT) agents were developed: (1) an Accident Precursor Extractor to identify and classify time-ordered events, and (2) a Subjective Probability Estimator to update perceived accident likelihood as precursors unfold. Results: The subjective accident probability increases near-linearly, with an average escalation of 8.0% ± 0.9% per precursor ($p<0.05$). A consistent tipping point occurs at the fourth precursor, marking a perceptual shift to high-risk awareness. Across 90 analyzed cases, Agent 1 achieved 0.88 precision and 0.84 recall, while Agent 2 reproduced human-like probabilistic reasoning within ±0.08 of expert baselines. The magnitude of escalation differed across precursor types. Organizational factors were perceived as the highest risk (median = 0.56), followed by human error (median = 0.47). Technical and environmental factors demonstrated comparatively smaller effects. Conclusions: These findings confirm that LLM agents can emulate Bayesian-like updating in dynamic risk perception, offering a scalable and explainable foundation for adaptive, sequence-aware safety monitoring in safety-critical systems. Full article

Guizhou Province in China exhibits a distinctive agroforestry mosaic landscape with frequent human activity in forested areas. This region experiences recurrent forest fires, characterized by significant difficulties in suppression and high risks. Research on the prediction of forest fire occurrences holds crucial practical significance in terms of enhancing regional forest fire prevention capabilities. However, the current fire risk forecasting methods in the area consider only meteorological factors, neglecting firebrands and fuel conditions, which results in deviations between forecasted and actual fire occurrences. Therefore, this study proposes a novel fire occurrence prediction method that utilizes the ignition component (IC) from the National Fire Danger Rating System (NFDRS) to characterize the weather–fuel complex while integrating the firebrand occurrence probability to construct a predictive model. The applicability and accuracy of this method are also evaluated. The results show that, firstly, the probability of at least one daily forest fire occurrence in the study area can be expressed as a nonlinear function based on the IC. Secondly, as time progresses, the correlation between the forest fire occurrence probability and the IC shows a decreasing trend, although the differences across different time spans are not statistically significant. Thirdly, when a 5-year time span is adopted, the error in calculating the forest fire occurrence probability based on the IC is significantly lower than at other time spans. Finally, a predictive model for the forest fire occurrence probability based on the IC is established, where P = (100*IC)/(4.06 + IC), with a mean absolute error (MAE) of 4.83% and mean relative error (MRE) of 14.87%. Based on this research, the IC enables the calculation of forest fire occurrence probabilities, assessment of fire risk ratings, and guidance for fire preparedness and planning. This work also provides theoretical support and a methodological reference for conducting forest fire probability studies in other regions. Full article

Detailed planning of vessel traffic on the fairway, carried out by Vessel Traffic Service (VTS) operators, is a complicated task, especially when there are restrictions for two-way ship traffic. Such restrictions take place on the dredged Świnoujście–Szczecin fairway in Poland. After the dredging of the fairway to 12.5 m, vessel traffic regulations introduced in a Port Regulations document have changed, which impacted the course of the decision-making process related to planning vessel traffic on the fairway performed by VTS operators. The aim of the article is to assess the probability of making erroneous decisions related to the admission of non-compliant vessels to traffic on the dredged Świnoujście–Szczecin fairway after the introduction of new vessel traffic regulations. In the article, the tasks carried out by VTS operators during vessel traffic planning were described and analyzed using Failure Mode and Effects Analysis (FMEA) method. The probability of making an erroneous decision at each stage of the planning process was calculated using the Human Error Assessment and Reduction Technique (HEART) method. An event tree was developed in relation to VTS operators’ decision-making on vessel traffic planning performed before and after the introduction of a decision support system (DSS). An expert method was used to determine the probability values. Recommendations were proposed to reduce the risk of making erroneous decisions by VTS operators while vessel traffic planning. The research results contributed to the expansion of knowledge on the impact of new regulation implementation on vessel traffic safety and the risk of making erroneous decisions related to the admission of non-compliant vessels to traffic on the dredged Świnoujście–Szczecin fairway, considering the implementation of a DSS. The results of the study may be of interest to VTS operators, port authorities and maritime administrations. Full article

Toxicokinetic (TK) properties are essential in the framework of chemical risk assessment and drug discovery. Specifically, a TK profile provides information about the fate of chemicals in the human body. In this context, Quantitative Structure–Activity Relationship (QSAR) models are convenient computational tools for predicting TK properties. Here, we developed QSAR models to predict two TK properties: oral bioavailability and volume of distribution at steady state (VD_ss). We collected and curated two large sets of 1712 and 1591 chemicals for oral bioavailability and VD_ss, respectively, and compared regression and classification (binary and multiclass) models with the application of several machine learning algorithms. The best predictive performance of the models for regression (R) prediction was characterized by a Q²_F3 of 0.34 with the R-CatBoost model for oral bioavailability and a geometric mean fold error (GMFE) of 2.35 with the R-RF model for VD_ss. The models were then applied to a list of potential endocrine-disrupting chemicals (EDCs), highlighting chemicals with a high probability of posing a risk to human health due to their TK profiles. Based on the results obtained, insights into the structural determinants of TK properties for EDCs are further discussed. Full article

This paper introduces a novel Underclothing Body Shape Perception Network (UBSP-Net) for reconstructing parametric 3D human models from clothed full-body 3D scans, addressing the challenge of estimating body shape and pose beneath clothing. Our approach simultaneously predicts both the internal body point cloud and a reference point cloud for the SMPL model, with point-to-point correspondence, leveraging the external scan as an initial approximation to enhance the model’s stability and computational efficiency. By learning point offsets and incorporating body part label probabilities, the network achieves accurate internal body shape inference, enabling reliable Skinned Multi-Person Linear (SMPL) human body model registration. Furthermore, we optimize the SMPL+D human model parameters to reconstruct the clothed human model, accommodating common clothing types, such as T-shirts, shirts, and pants. Evaluated on the CAPE dataset, our method outperforms mainstream approaches, achieving significantly lower Chamfer distance errors and faster inference times. The proposed automated pipeline ensures accurate and efficient reconstruction, even with sparse or incomplete scans, and demonstrates robustness on real-world Thuman2.0 dataset scans. This work advances parametric human modeling by providing a scalable and privacy-preserving solution for applications to 3D shape analysis, virtual try-ons, and animation. Full article

Due to the challenges in obtaining full-body point clouds and the time-consuming registration of parametric body models, we propose an end-to-end Front Point Cloud Parametric Body Regression Network (FPCR-Net). This network directly regresses the pose and shape parameters of a parametric body model from a single front point cloud of the human body. The network first predicts the label probabilities of corresponding body parts and the back point cloud from the input front point cloud. Then, it extracts equivariant features from both the front and predicted back point clouds, which are concatenated into global point cloud equivariant features. For pose prediction, part-level equivariant feature aggregation is performed using the predicted part label probabilities, and the rotations of each joint in the parametric body model are predicted via a self-attention layer. Shape prediction is achieved by applying mean pooling to part-invariant features and estimating the shape parameters using a self-attention mechanism. Experimental results, both qualitative and quantitative, demonstrate that our method achieves comparable accuracy in reconstructing body models from front point clouds when compared to implicit representation-based methods. Moreover, compared to previous regression-based methods, vertex and joint position errors are reduced by 43.2% and 45.0%, respectively, relative to the baseline. Full article

Civil aviation safety remains a critical concern globally, with continuous efforts aimed at reducing accidents and fatalities. This paper focuses on the comprehensive evaluation of civil aviation safety in the Slovak Republic over the past several years, with the main objective of identifying prevailing trends and key risk factors. A comprehensive analysis of 155 accidents and incidents was conducted based on selected operational parameters. Logistic regression was applied to identify potential causal factors influencing various levels of injury severity in aviation accidents. Moreover, the prediction model can also be used to predict the probability of specific injury severity for accidents with given parameter values. The results indicate a clear declining trend in the annual number of aviation safety events; however, the fatality rate has stagnated or slightly increased in recent years. Human error, particularly mistakes and intentional violations of procedures, was identified as the dominant causal factor across all sectors of civil aviation, including flight operations, airport management, maintenance, and air navigation services. Despite technological advancements and regulatory improvements, human-related failures persist as a major safety challenge. The findings highlight the critical need for targeted strategies to mitigate human error and enhance overall aviation safety in the Slovak Republic. Full article

The construction industry is one of the largest contributors to the world economy. However, the level of automation and digitalization in the construction industry is still at its infancy in comparison with other industries due to the complex nature and the large size of construction projects. Meanwhile, construction projects are prone to cost overruns and schedule delays due to the adoption of traditional progress monitoring techniques to retrieve progress on-site, having indoor activities participating with an accountable ratio of these works. Improvements in deep learning and Computer Vision (CV) algorithms provide promising results in detecting objects in real time. Also, researchers have investigated the probability of using CV as a tool to create a Digital Twin (DT) for construction sites. This paper proposes a model utilizing the state-of-the-art YOLOv8 algorithm to monitor the progress of bricklaying activities, automatically extracting and analyzing real-time data from construction sites. The detected data is then integrated into a 3D Building Information Model (BIM), which serves as a DT, allowing project managers to visualize, track, and compare the actual progress of bricklaying with the planned schedule. By incorporating this technology, the model aims to enhance accuracy in progress monitoring, reduce human error, and enable real-time updates to project timelines, contributing to more efficient project management and timely completion. Full article

Hand gestures are essential for interaction in augmented and virtual reality (AR/VR), allowing users to intuitively manipulate virtual objects and engage with human–machine interfaces (HMIs). Accurate gesture recognition is critical for effective task execution. However, users often encounter difficulties due to the lack of immediate and clear feedback from head-mounted displays (HMDs). Current tracking technologies cannot always guarantee reliable recognition, leaving users uncertain about whether their gestures have been successfully detected. To address this limitation, haptic feedback can play a key role by confirming gesture recognition and compensating for discrepancies between the visual perception of fingertip contact with virtual objects and the actual system recognition. The goal of this paper is to compare a simple vibrotactile ring with a full glove device and identify their possible improvements for a fundamental gesture like pinching and fine moving of objects using Microsoft HoloLens 2. Where the pinch action is considered an essential fine motor skill, augmented reality integrated with haptic feedback can be useful to notify the user of the recognition of the gestures and compensate for misaligned visual perception between the tracked fingertip with respect to virtual objects to determine better performance in terms of spatial precision. In our experiments, the participants’ median distance error using bare hands over all axes was 10.3 mm (interquartile range [IQR] = 13.1 mm) in a median time of 10.0 s (IQR = 4.0 s). While both haptic devices demonstrated improvement in participants precision with respect to the bare-hands case, participants achieved with the full glove median errors of 2.4 mm (IQR = 5.2) in a median time of 8.0 s (IQR = 6.0 s), and with the haptic rings they achieved even better performance with median errors of 2.0 mm (IQR = 2.0 mm) in an even better median time of only 6.0 s (IQR= 5.0 s). Our outcomes suggest that simple devices like the described haptic rings can be better than glove-like devices, offering better performance in terms of accuracy, execution time, and wearability. The haptic glove probably compromises hand and finger tracking with the Microsoft HoloLens 2. Full article