Search Results (5,390)

Emergency Medical Services (EMS) personnel require exceptional spatial awareness and rapid decision-making within the confined environment of an ambulance. While Virtual Reality (VR) offers a safe alternative to traditional training, the lack of high-fidelity, regionally accurate, and VR-optimized 3D ambulance models limits its application. This study presents a scenario-driven methodology for developing a VR-ready 3D ambulance environment prototype tailored for Emergency Medical Technician (EMT) training. Utilizing reality-capture techniques, terrestrial laser scanning was performed to accurately document the interior of a standard Hungarian ambulance simulator. The resulting point cloud underwent systematic processing, manual retopology, PBR shading, and the implementation of a custom dual-rigging animation system to optimize complex mechanical movements—such as stretcher operations—for standalone VR platforms. The workflow successfully reduced the vertex count to 25,373 while maintaining millimeter-level spatial fidelity. Technical evaluation confirmed that geometrical, functional, and material objectives were fulfilled, whereas pedagogical implementation remains incomplete. Structural accuracy and animation readiness were verified through preliminary inspection within Blender’s VR viewport inspector. However, interactive game-engine integration remains future work, and educational effectiveness has not yet been tested with EMT learners. Overall, this workflow delivers a 3D asset foundation that establishes the necessary technical basis for subsequent software implementation and clinical evaluation. Full article

The increasing penetration of variable solar and wind generation requires flexible resources capable of improving energy balancing, reliability, and renewable energy utilization. This review critically assesses biofuel-integrated hybrid energy systems as complementary architectures for renewable energy integration, connecting system configuration, energy conversion efficiency, storage and dispatch, intelligent control, environmental performance, and scalability. A critical narrative and integrative approach was applied using literature retrieved from Scopus and Web of Science, and organized across solar–bioenergy, wind–bioenergy, multi-source, storage-supported, microgrid, and multi-energy configurations. The evidence indicates that biomass-derived fuels can provide dispatchable and storable renewable energy that complements variable generation and supports decentralized and multi-energy applications. However, no architecture is universally superior, and greater hybridization does not inherently result in higher thermodynamic efficiency. Performance depends strongly on resource complementarity, feedstock availability and quality, conversion pathways, storage requirements, and operating strategy. Advanced energy management, model predictive control, machine learning, and digital twins can improve system coordination, although much of the available evidence remains simulation-based or limited in experimental scale. Environmental benefits are likewise pathway- and boundary-dependent, particularly when avoided emissions, coproduct allocation, infrastructure, and feedstock supply chains are considered. Overall, biofuel-integrated hybrid systems represent an application-dependent flexibility option rather than a universally optimal solution; future progress requires dynamic uncertainty-aware modeling, harmonized techno-economic and life-cycle assessment, and greater pilot- and industrial-scale validation. Full article

This paper presents an experimental evaluation of a smart glasses-based cyber-physical system for the recognition of dangerous objects and the detection of dynamic life-threatening events. The proposed system integrates real-time computer vision and sound-based localization mechanisms in order to enhance situational awareness and user safety. The dangerous object recognition module is based on a deep learning model derived from the YOLO architecture and MobileNet classifiers, extended with distance estimation capabilities. The dynamic hazard detection module combines auditory localization using interaural time and level differences with visual confirmation through object detection. The experimental study was conducted using datasets of hazardous objects and simulated dynamic scenarios, including moving threats and sudden acoustic events. The dangerous object recognition module achieved F1-scores of up to 100.00% during training and 99.33% during validation, demonstrating high robustness and reliability. The dynamic hazard detection module achieved 0.95 training accuracy and 0.71 validation accuracy under dynamic environmental conditions. Comparative experiments on two hardware platforms showed that the ASUS ROG Zephyrus M16 reduced training time by up to seven times compared to the GIGABYTE GA-A320M-H platform without affecting recognition accuracy. The obtained results confirm the applicability of the proposed multimodal approach for real-time safety systems and wearable assistive technologies operating in complex environments. Full article

Accurate cross-dataset state-of-health prediction for lithium-ion batteries remains challenging due to distribution shifts arising from diverse cathode chemistries, operating temperatures, and charge–discharge protocols across heterogeneous battery fleets. Drawing upon established machine learning paradigms, this study tailors a Domain-Adaptive Mixture-of-Experts (DA-MoE) framework to the battery prognostic context, automatically selecting the optimal domain adaptation strategy for each target domain through a physics-aware, lightweight linear gating network comprising merely 32 learnable parameters. The framework integrates a shared Transformer-based backbone with four adaptation strategies spanning the full spectrum of target-domain information utilization, namely zero-shot transfer, Test-Time Adaptation, Fine-Tuning, and Model-Agnostic Meta-Learning. A comprehensive evaluation on 564 battery cells from seven publicly available datasets under Leave-One-Domain-Out Cross-Validation protocol demonstrates that the proposed framework achieves an average coefficient of determination of 0.864 with perfect oracle strategy alignment under full domain training and maintains competitive generalization at an average R² of 0.795 when each target domain is held out during gating network training. Hard argmax selection consistently outperforms weighted fusion across all seven domains with an average margin of +0.027 in R², confirming that the four adaptation strategies compete rather than cooperate in this application context. A feature ablation analysis identifies sample count as the dominant determinant of strategy selection with performance degradation of ΔR² = −0.182 upon removal, followed by the early-cycle degradation slope and early-cycle nonlinearity index as secondary signals, all of which are computable at deployment time without future ground-truth SOH information. The proposed framework provides a practically deployable solution for battery management systems operating across heterogeneous fleets with minimal computational overhead and strong cross-dataset generalization capability. Full article

Markerless human-motion assessment has become increasingly relevant in domains such as psychomotor learning, rehabilitation, sports training, and collaborative educational environments. While recent pose-estimation frameworks provide reliable skeletal reconstruction, translating these data into interpretable posture assessment remains challenging, particularly under varying participant-to-sensor distances and in multi-participant settings. This paper presents the technological evolution from KUMITRON, a system originally developed for synchronized multi-participant monitoring and interaction analysis in psychomotor activities, to COLLVIT, a prototype implementing configurable depth-aware joint-angle posture assessment. This evolution encompasses RGB-D integration, configurable angular templates, depth-informed adaptive tolerance mechanisms, temporal stabilization strategies, interpretable posture assessment, and multi-participant processing capabilities. The paper distinguishes between the architectures defined at the patent level, their implementation through the KUMITRON and COLLVIT prototypes, and capabilities that remain targets for future implementation and validation. Rather than reporting a controlled experimental evaluation, the contribution of this work lies in documenting the technological evolution from KUMITRON to COLLVIT, the rationale behind the patent-based design decisions, the implementation of the current prototype, and directions for its future development and validation. The resulting framework provides a flexible foundation for future research on markerless kinematic posture assessment in educational, rehabilitation, and other psychomotor application domains. Full article

Reliable abnormal behavior recognition from surveillance videos is hindered by the high cost of clip-level annotation, the scarcity of abnormal samples, and the context-dependent nature of behavioral semantics. Although vision–language models offer strong semantic transferability, their application under limited supervision remains susceptible to noisy pseudo-labels and confirmation bias. We propose confidence-aware semi-supervised vision–language contrastive learning (CA-VLC), which jointly exploits limited labeled videos and abundant unlabeled videos. Building on an existing CLIP-initialized temporal backbone, CA-VLC combines behavior-only and context-enriched text prototypes through confidence- and agreement-guided semantic fusion. For unlabeled videos, the model generates predictions from weakly augmented views and selects reliable pseudo-labels using entropy-based confidence estimation and class-adaptive thresholds. Detached weak-view targets then supervise strongly augmented views through confidence-weighted self-training without requiring an additional teacher network. Furthermore, cross-view consistency regularization and confidence-aware contextual alignment suppress unreliable semantic cues and improve robustness to contextual noise. Experiments on CABR50 demonstrate consistent improvements across multiple labeled-data ratios, while evaluations on CABRZ6 and UCF-101 assess prompt-based transfer to predefined target label sets without target-domain fine-tuning. With 10% labeled videos, CA-VLC achieves 84.06% Top-1 accuracy and 83.51% Macro-F1, retaining 95.47% of its fully supervised Top-1 accuracy of 88.05%, thereby demonstrating its effectiveness for label-efficient abnormal behavior recognition. Full article

This paper presents a novel fault-tolerant model predictive control (FTMPC) framework for fuel cell hybrid electric vehicles (FCHEVs) used for postal delivery applications. The main contribution of the proposed FTMPC is the adaptive adjustment of the model predictive control cost function weights based on fault severity. The proposed reformulation incorporates fault characterization across the diverse degradation mechanisms while maintaining reliable vehicle operation. The FTMPC approach dynamically adapts cost function weights and system constraints based on the fault severity index. The resulting control strategy provides fault-aware power allocation between the fuel cell and battery while accounting for the specified operating and safety constraints. To isolate the contribution of the proposed health-dependent adaptation mechanism, a controlled ablation study was performed against a structurally identical fixed-MPC controller under the same vehicle model, driving cycle, initial conditions, prediction and control horizons, solver configuration, and fault scenarios. The adaptive FTMPC achieved a 10.6956% reduction in direct hydrogen consumption relative to the fixed-MPC baseline. Because differences in terminal battery state of charge (SoC) can influence comparisons based solely on hydrogen consumption, a charge-corrected hydrogen-equivalent metric was also evaluated; using this more conservative metric, the adaptive FTMPC retained a 2.7276% improvement. The final quadratic programming implementation achieved a 100% successful optimization rate in the validation run with no fallback-controller activation, while the maximum soft-constraint slack remained on the order of 10−9. Additional sensitivity analyses were conducted to evaluate the influence of relevant vehicle and operating conditions on energy consumption and battery utilization. These results provide direct quantitative evidence of the contribution of the proposed fault-adaptive mechanism and demonstrate its numerical feasibility for FCHEV energy management, while the limitations of the present simulation-based validation are explicitly acknowledged. Full article

Ultrasonic pulse-echo imaging is one of the most widely used non-destructive evaluation (NDE) modalities for monitoring the structural integrity of reinforced-concrete civil infrastructure such as bridge decks, tunnel linings, and dam walls. In this acquisition geometry, a single low-frequency transducer is mechanically raster-scanned over the accessible top surface of the specimen and records one A-scan per scan position, simultaneously serving as transmitter and receiver. However, commonly used reconstruction algorithms such as the Synthetic Aperture Focusing Technique (SAFT) and Reverse Time Migration (RTM) tend to produce reconstructions of limited quality on this class of data because they do not adequately model the round-trip propagation kernel that is specific to the monostatic geometry, they do not separate the strong near-surface direct-arrival reflection from the bulk image, and they do not account for the persistent aggregate-induced clutter that contaminates every A-scan in concrete media. In this paper, we propose a clutter-aware reconstruction method for monostatic ultrasound acquisition (CARMA), whose main innovation is the joint integration of a monostatic-specific round-trip propagation model, a dedicated near-surface direct-arrival subspace, and a data-adaptive low-rank clutter subspace within a unified model-based reconstruction framework. Unlike existing reconstruction approaches, CARMA explicitly accounts for the co-located transmit–receive geometry through a squared-cosine round-trip directivity model while simultaneously separating scan-dependent direct-arrival contributions and aggregate-induced clutter from the desired reflectivity image. To verify the method under fully controlled and repeatable conditions, we generate intensive, physically realistic full-wave simulations with the k-Wave pseudo-spectral acoustic solver that reproduce a representative civil-infrastructure inspection scenario: three reinforced-concrete specimens with a stepped back wall of varying thickness, ten embedded ground-truth defects spanning steel tendon ducts and low-impedance polystyrene inclusions, a monostatic raster-scanned pulse-echo acquisition, and randomly distributed aggregate scatterers that reproduce the clutter of real concrete. Results on these intensive k-Wave simulations indicate that CARMA reconstruction yields approximately $2\times$ lower localization error than RTM and approximately $4\times$ lower localization error than SAFT, while recovering the deepest embedded defect with substantially better localization and contrast than the comparison methods. Full article

Generative AI’s application in hands-on engineering systems has gained substantial attention, particularly in complex hardware–software configurations that involve physical operational risks. Traditional configuration tools often lack real-time contextual awareness, limiting the diagnostic capabilities of novice users. To overcome such limitations, we developed an AI-driven system configuration and diagnostics engine by integrating a deterministic rule-validation layer with a probabilistic generative large language model, balancing factual reliability with adaptive conversational debugging. Using task–technology fit (TTF) theory, the engine’s functional alignment was evaluated through an experimental study involving 100 participants. Structural equation modeling results showed that TTF significantly enhances user learning satisfaction and overall diagnostic learning outcomes. Accounting for 86.3% of the variance in diagnostic performance (R² = 0.863), the developed engine presents high effectiveness in supporting real-time, interactive engineering diagnostics. Full article

Background/Objective: Activated coagulation factor XII (FXIIa) is a component of the contact activation pathway and a pharmacologically relevant target in contact-system-associated processes. In this study, scaffold-aware and interpretable machine-learning QSAR models were developed for human FXIIa activity. Methods: Bioactivity records for the human single protein target CHEMBL2821 were retrieved from ChEMBL release 37. Modeling was restricted to exact IC50 measurements from assays explicitly referring to FXIIa, Factor XIIa, or activated Factor XII. Median-consolidated pIC50 values and two-dimensional Mordred descriptors were evaluated using leakage-safe preprocessing, scaffold-disjoint validation, Y-randomization, applicability domain analysis, structural similarity auditing, and SHAP interpretation. Results: The regression dataset comprised 424 compounds and 166 Bemis–Murcko scaffolds in this study. The Gradient Boosting regressor achieved R² = 0.7560, RMSE = 0.6924, and MAE = 0.4965 on the locked scaffold-disjoint test set (n = 85); across 50 repeated scaffold partitions, the mean R² was 0.6892 ± 0.1515. The classification model achieved ROC-AUC = 0.9453, PR-AUC = 0.9807, balanced accuracy = 0.7561, and MCC = 0.5972 (n = 73). Y-randomization supported nonrandom predictive signals (empirical p = 0.0099). Conclusions: The models support computational prioritization within the represented FXIIa chemical domain, while prospective evaluation of independently generated compounds remains necessary. Full article

This paper follows an increasingly expressed awareness that while systems thinking and system dynamics can be taught without involving sustainability, the reverse is not the case. Systems thinking is characterised by concepts such as interconnectedness, feedback loops, emergent properties, dynamic complexity, leverage points, and so on. A purpose here is to put flesh on these theoretical bones in terms of applying systems concepts to problems prioritizing sustainability, rather than talking about them in generalities. Because system dynamics is the methodology used in the Limits to Growth study, a substantial part of the literature review focuses on specific aspects of that study and controversies that have surrounded it since its first publication. Its 50th anniversary in 2022 generated a spate of publications, supporting both the substantive value of its outcomes and its methodological approach. The second part of this paper introduces and applies concepts and procedures of system dynamics to problems that can be understood without specialist disciplinary knowledge. The purpose is to provide access to processes at a level that enables application of systemic insights and methods in addressing the plethora of different problems associated with the challenge of achieving sustainable development in our interconnected world. Full article

Artificial intelligence can extend the functional capabilities of embedded sensors by extracting application-level information from physical measurements. This study investigates whether footstep-induced floor vibrations acquired with a single triaxial MEMS accelerometer contain sufficient information to characterize pedestrian path orientation and travel sense. A custom sensing platform based on an ADXL355 accelerometer and an ESP32 microcontroller was developed to acquire the structural vibration response at 4 kSPS. Lightweight temporal features were processed using a Random Forest classifier. The primary assessment used leakage-aware event-level cross-validation, with complete footsteps as the data-partitioning units. Under this more conservative protocol, discrimination of the complete A–K movement-label set was poor, whereas a compact 12-dimensional descriptor representation achieved 73.18% accuracy, 71.52% balanced accuracy, and 70.98% macro-F1 for X/Y path-orientation classification. Reliable positive/negative travel-sense discrimination could not be demonstrated from isolated footsteps. For historical comparison, the original sample-level procedure yielded 97.09% accuracy, but this value is retained only as a within-sequence reference because densely sampled observations contain strongly overlapping information. The findings provide proof-of-concept evidence that a single floor-mounted MEMS accelerometer can capture coarse pedestrian path-orientation information without cameras or spatially distributed vibration-sensor networks. Feature extraction and classifier inference were performed offline; broader validation across participants, sessions, floor structures, and realistic disturbances is required before deployment as an embedded edge AI sensing node. Full article

Reliable clinical decision support systems require not only high predictive accuracy but also trustworthy probability estimates and robust uncertainty quantification. However, most medical artificial intelligence (AI) studies primarily emphasize discrimination performance while overlooking systematic reliability evaluation. This study proposes a reliability-aware evaluation framework for Alzheimer’s disease detection that integrates discrimination analysis, statistical validation, probability calibration, uncertainty quantification, robustness assessment, and clinical decision analysis within a unified pipeline. Multiple machine learning classifiers and ensemble configurations were evaluated using repeated stratified cross-validation and assessed through discrimination and calibration metrics. Support Vector Machine achieved the highest ROC-AUC (0.955 ± 0.046), while Extra Trees obtained the highest Accuracy (0.878) and F1-score (0.887). Friedman analysis confirmed statistically significant differences among classifiers ($p<0.001$). Platt scaling consistently improved probabilistic reliability, whereas Beta calibration demonstrated stable performance under noise, feature perturbation, and reduced-data scenarios. Uncertainty-aware selective prediction increased high-confidence diagnostic accuracy by up to 8.1%, and decision curve analysis demonstrated improved clinical utility. The reliability analysis identified calibration-aware stacking as the most reliable ensemble configuration. An independent cross-dataset evaluation on a heterogeneous Alzheimer’s disease clinical dataset with a substantially different feature space yielded stable discrimination (ROC-AUC = 0.858 ± 0.025) and calibration (ECE = 0.132 ± 0.019) after the STACK_CAL architecture was independently retrained from scratch. These findings provide evidence of the cross-dataset applicability of the proposed reliability-aware strategy across different clinical data modalities, while further prospective and independent validation remains necessary before real-world clinical deployment. Full article

Hyperspectral retrieval of nitrogen-related vegetation variables has undergone rapid methodological advances driven by the emergence of protein-sensitive radiative transfer models (RTMs), modern machine learning (ML), and operational imaging spectroscopy. This review synthesizes recent developments in hyperspectral retrieval of nitrogen-related vegetation variables across leaf and canopy scales, with particular emphasis on advances reported between 2020 and 2026. We examine the evolution from classical parametric regression and nonlinear ML approaches towards physically based RTM inversion and hybrid RTM–ML frameworks that integrate the complementary strengths of physical modeling and statistical learning. Particular attention is given to protein-sensitive RTMs, advanced ML approaches, and uncertainty-aware retrieval. Recent developments highlight the potential of hybrid RTM–ML frameworks to combine physical consistency with computationally efficient statistical learning, while probabilistic methods such as Gaussian Process Regression provide additional capabilities for uncertainty characterization. The review further discusses the transition from experimental studies to operational applications enabled by airborne and satellite imaging spectroscopy, including PRISMA, EnMAP, and forthcoming missions such as CHIME. Remaining challenges include the inherently ill-posed nature of nitrogen retrieval, limited and insufficiently representative calibration data, uncertainty characterization, and generalization across sensors, species, and ecosystems. Overall, the reviewed evidence points towards increasingly integrated retrieval frameworks, while emphasizing that robust transferability and operational implementation remain dependent on representative data, physical realism, and rigorous uncertainty assessment. Full article

This study proposes a source-study-aware validation framework to estimate the shear capacity of stirrup-free steel-fiber-reinforced concrete corbels and assess the reliability and generalizability of machine-learning models in structural engineering. A database of 108 specimens, compiled from seven independent studies, was analyzed using linear regression, ridge regression, and hyperparameter-optimized XGBoost. The evaluation combined standard specimen-level five-fold cross-validation, predefined source-study holdout evaluation, exhaustive partition-sensitivity analysis, and specimen-level out-of-bag bootstrap uncertainty analysis. In the predefined source-study hold-out evaluation, with hyperparameters selected exclusively from the training portion via an inner group-aware search, the models achieved test R² values of 0.842, 0.866, and 0.912, respectively, with XGBoost providing the highest point estimate of performance. However, an exhaustive sensitivity analysis of source-study partitions, in which hyperparameters were re-selected independently within the training portion of each partition, indicated that this ranking was not maintained: Linear Regression achieved the highest mean and median R² and the narrowest interquartile range, whereas XGBoost exhibited the lowest mean and median R², the widest interquartile range, and the highest incidence of negative R² values and large prediction errors among the three models; this reflects instability introduced by re-tuning under limited, group-diverse training data. The specimen-level out-of-bag bootstrap uncertainty analysis also favored the linear models in terms of mean performance and confidence-interval width. Standardized coefficients and SHAP analyses consistently identified the shear span-to-effective-depth ratio, the longitudinal reinforcement ratio, and the fiber ratio as the dominant predictors. This study provides a transparent and uncertainty-aware framework for determining when predictive performance is transferable across independent experimental studies and when caution is required in engineering applications. Full article