Search Results (2,678)

Panoptic maps enable robots to reason about both geometry and semantics. However, open-vocabulary models repeatedly produce closely related labels that split panoptic entities and degrade volumetric consistency. The proposed UPPM advances open-world scene understanding by leveraging foundation models to introduce a panoptic Dynamic Descriptor that reconciles open-vocabulary labels with unified category structure and geometric size priors. The fusion for such dynamic descriptors is performed within a multi-resolution multi-TSDF map using language-guided open-vocabulary panoptic segmentation and semantic retrieval, resulting in a persistent and promptable panoptic map without additional model training. Based on our evaluation experiments, UPPM shows the best overall performance in terms of the map reconstruction accuracy and the panoptic segmentation quality. The ablation study investigates the contribution for each component of UPPM (custom NMS, blurry-frame filtering, and unified semantics) to the overall system performance. Consequently, UPPM preserves open-vocabulary interpretability while delivering strong geometric and panoptic accuracy. Full article

Background/Objectives: Federated learning (FL) offers a way for healthcare institutions to collaboratively train machine learning models without sharing sensitive patient data. This systematic review aims to comprehensively synthesize the ethical dimensions of FL in healthcare, integrating privacy preservation, algorithmic fairness, governance, and equitable access into a unified analytical framework. The application of FL in healthcare between January 2020 and December 2024 is examined, with a focus on ethical issues such as algorithmic fairness, privacy preservation, governance, and equitable access. Methods: Following PRISMA guidelines, six databases (PubMed, IEEE Xplore, Web of Science, Scopus, ACM Digital Library, and arXiv) were searched. The PROSPERO registration is CRD420251274110. Studies were selected if they described FL implementations in healthcare settings and explicitly discussed ethical considerations. Key data extracted included FL architectures, privacy-preserving mechanisms, such as differential privacy, secure multiparty computation, and encryption, as well as fairness metrics, governance models, and clinical application domains. Results: Out of 3047 records, 38 met the inclusion criteria. The most popular applications were found in medical imaging and electronic health records, especially in radiology and oncology. Through thematic analysis, four key ethical themes emerged: algorithmic fairness, which addresses differences between clients and attributes; privacy protection through formal guarantees and cryptographic techniques; governance models, which emphasize accountability, transparency, and stakeholder engagement; and equitable distribution of computing resources for institutions with limited resources. Considerable variation was observed in how fairness and privacy trade-offs were evaluated, and only a few studies reported real-world clinical deployment. Conclusions: FL has significant potential to promote ethical AI in healthcare, but advancement will require the development of common fairness standards, workable governance plans, and systems to guarantee fair benefit sharing. Future studies should develop standardized fairness metrics, implement multi-stakeholder governance frameworks, and prioritize real-world clinical validation beyond proof-of-concept implementations. Full article

Ensuring sustained driver attention is critical for intelligent transportation safety systems; however, the performance of data-driven driver distraction detection models is often limited by the high cost of large-scale manual annotation. To address this challenge, this paper proposes an adaptive semi-supervised driver distraction detection framework based on teacher–student learning and deformable pyramid feature fusion. The framework leverages a limited amount of labeled data together with abundant unlabeled samples to achieve robust and scalable distraction detection. An adaptive pseudo-label optimization strategy is introduced, incorporating category-aware pseudo-label thresholding, delayed pseudo-label scheduling, and a confidence-weighted pseudo-label loss to dynamically balance pseudo-label quality and training stability. To enhance fine-grained perception of subtle driver behaviors, a Deformable Pyramid Sparse Transformer (DPST) module is integrated into a lightweight YOLOv11 detector, enabling precise multi-scale feature alignment and efficient cross-scale semantic fusion. Furthermore, a teacher-guided feature consistency distillation mechanism is employed to promote semantic alignment between teacher and student models at the feature level, mitigating the adverse effects of noisy pseudo-labels. Extensive experiments conducted on the Roboflow Distracted Driving Dataset demonstrate that the proposed method outperforms representative fully supervised baselines in terms of mAP@0.5 and mAP@0.5:0.95 while maintaining a balanced trade-off between precision and recall. These results indicate that the proposed framework provides an effective and practical solution for real-world driver monitoring systems under limited annotation conditions. Full article

Acid mine drainage (AMD) and acid-generating mine wastes exhibit low pH, high sulfate levels, and complex multi-metal loads that strain conventional treatment. Thermoacidophilic red algae of the order Cyanidiales, particularly Galdieria sulphuraria (G. sulphuraria), have attracted interest as a biological option because they tolerate extreme acidity and elevated temperatures, grow under low light in mixotrophic or heterotrophic modes, and display rapid metal binding at the cell surface. This review synthesizes about two decades of peer-reviewed work to clarify how G. sulphuraria can be deployed as a practical module within mine water treatment trains. We examine the mechanisms of biosorption and bioaccumulation and show how they map onto two distinct configurations. Processed freeze-dried biomass functions as a regenerable sorbent for rare earth elements (REEs) and selected transition metals in packed beds with acid elution for recovery. Living cultures serve as polishing units for divalent metals and, when present, nutrients or dissolved organics under low light. We define realistic operating windows centered on pH 2–5 and temperatures of approximately 25–45 °C, and we identify matrix effects that govern success, including competition from ferric iron and aluminum, turbidity and fouling risks, ionic strength from sulfate, and suppression of REE uptake by phosphate in living systems. Building on laboratory studies, industrial leachate tests, and ecosystem observations, we propose placing G. sulphuraria upstream of bulk neutralization and outline reporting practices that enable cross-site comparison. The goal is an actionable framework that reduces reagent use and sludge generation while enabling metal capture and potential recovery of valuable metals from mine-influenced waters. Full article

Parametric tiered-seating design can be framed as a constrained multi-objective optimization problem in which a low-dimensional decision vector is evaluated by a deterministic operator with sequential feasibility rejection and visibility constraints. This study introduces an oracle-preserving, learning-assisted screening workflow, where a multi-output multilayer perceptron (MLP) is used only to prioritize candidates for evaluation. Here, multi-output denotes a single network trained to predict the full objective vector jointly. Candidates are sampled within bounded decision ranges and evaluated by an operator that propagates section-coupled geometric state and enforces hard clearance thresholds through a Vertical Sightline System (VSS), i.e., a deterministic row-wise sightline/clearance evaluator that enforces hard clearance thresholds. The oracle-evaluated set is reduced to its mixed-direction Pareto-efficient subset and filtered by feature-space proximity to a fixed validation reference using nearest-neighbor distances in standardized 11-dimensional features, yielding a robustness-oriented pool. A compact shortlist is derived via TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution; used here strictly as a post-Pareto decision-support ranking rule), and preference uncertainty is assessed by Monte Carlo weight sampling from a symmetric Dirichlet distribution. In an archived run under a fixed oracle budget, 1235 feasible designs are evaluated, producing 934 evaluated Pareto solutions; proximity filtering retains 187 robust candidates and TOPSIS reports a traceable top-30 shortlist. Stability is supported by concentrated top-k frequencies under weight perturbations and by audits under single-feature-drop ablations and tested rounding precisions. Overall, the workflow enables reproducible multi-objective screening and reporting for feasibility-dominated seating design. Full article

In mineral processing, visual-based online particle size analysis systems depend on high-precision image segmentation to accurately quantify ore particle size distribution, thereby optimizing crushing and sorting operations. However, due to multi-scale variations, severe adhesion, and occlusion within ore particle clusters, existing segmentation models often exhibit undersegmentation and misclassification, leading to blurred boundaries and limited generalization. To address these challenges, this paper proposes a novel semantic segmentation model named VTC-Net. The model employs VGG16 as the backbone encoder, integrates Transformer modules in deeper layers to capture global contextual dependencies, and incorporates a Convolutional Block Attention Module (CBAM) at the fourth stage to enhance focus on critical regions such as adhesion edges. BatchNorm layers are used to stabilize training. Experiments on ore image datasets show that VTC-Net outperforms mainstream models such as UNet and DeepLabV3 in key metrics, including MIoU (89.90%) and pixel accuracy (96.80%). Ablation studies confirm the effectiveness and complementary role of each module. Visual analysis further demonstrates that the model identifies ore contours and adhesion areas more accurately, significantly improving segmentation robustness and precision under complex operational conditions. Full article

There is a lack of focus on psychological support for fathers in Neonatal Intensive Care Units (NICUs), both in research and practice, with fathers receiving far less support from NICU providers as compared with mothers. This article aims to discuss the current literature and limitations related to providing psychological support to fathers in the NICU and proposes short- and long-term efforts for improving psychological care for NICU fathers. We conducted a narrative literature review to summarize interventions for supporting fathers in the NICU, including emotional support, educational support, social support, family-integrated care, and multi-component interventions. While initial work is promising, there are major limitations. Very few studies have examined interventions specific to providing support to fathers in the NICU, and little work has investigated differences in the support needs and responses to interventions for NICU fathers as compared with mothers. Fathers have historically been overlooked in the NICU. Given the growing recognition of paternal mental health challenges and their impact on infant development, there is a pressing need for efforts aimed at supporting fathers in the NICU. Efforts must consider system structure, policy, multidisciplinary training, and implementation protocols to improve the quality of care provided to NICU fathers. Full article

The state of charge (SoC) is one of the critical parameters in battery management systems, as it directly determines the operational safety and reliability of batteries. To accurately predict the SoC of an electric forklift under varying operating conditions, two surrogate models, an improved Transformer and an improved Transformer 2, are developed. The experimental data obtained through real-vehicle tests are multi-dimensional and contain multiple sources of noise, resulting in poor prediction accuracy when only a single preprocessing algorithm is used. Therefore, this paper first discusses the effect of the preprocessing algorithms on SoC estimation. Compared with the original experimental data and the Kalman filter algorithm, the Kalman filter–principal component analysis (PCA) method is more suitable for preprocessing the original electric forklift data. The mean absolute error (MAE) and root mean square error (RMSE) of the improved Transformer model obtained using the Kalman filter – PCA method are reduced by 26.32% and 27.73% respectively, compared to the single Kalman method. Then, this study investigates the impact of data with different dimensions on the prediction performance of the improved Transformer mode. The results show that five-dimensional data can more effectively train the improved Transformer model, since the MAE decreases by 14.63% and 19.54%, and the RMSE decreases by 14.85% and 20.37% compared to three-dimensional and seven-dimensional data. Through the analysis of the improved Transformer model, an improved Transformer 2 model with higher prediction accuracy is obtained. Then, the improved Transformer 2 model is compared with the LSTM and CNN algorithms. The results indicate that the improved Transformer 2 model can predict SoC more stably and accurately than the single LSTM and CNN algorithms. Specifically, compared with the LSTM model, the proposed Transformer 2 model reduces the MAE by 77.16% and the RMSE by 91.75%. In comparison with the CNN model, the MAE is reduced by 71.81% and the RMSE by 80%. Full article

Engineering is suffering a significant change driven by the integration of artificial intelligence (AI) into engineering optimization in design, analysis, and operational efficiency across numerous disciplines. This review synthesizes the current landscape of AI-driven optimization methodologies and their impacts on engineering applications. In the literature, several frameworks for AI-based engineering optimization have been identified: (1) machine learning models are trained as objective and constraint functions for optimization problems; (2) machine learning techniques are used to improve the efficiency of optimization algorithms; (3) neural networks approximate complex simulation models such as finite element analysis (FEA) and computational fluid dynamics (CFD) and this makes it possible to optimize complex engineering systems; and (4) machine learning predicts design parameters/initial solutions that are subsequently optimized. Fundamental AI technologies, such as artificial neural networks and deep learning, are examined in this paper, along with commonly used AI-assisted optimization strategies. Representative applications of AI-driven engineering optimization have been surveyed in this paper across multiple fields, including mechanical and aerospace engineering, civil engineering, electrical and computer engineering, chemical and materials engineering, energy and management. These studies demonstrate how AI enables significant improvements in computational modelling, predictive analytics, and generative design while effectively handling complex multi-objective constraints. Despite these advancements, challenges remain in areas such as data quality, model interpretability, and computational cost, particularly in real-time environments. Through a systematic analysis of recent case studies and emerging trends, this paper provides a critical assessment of the state of the art and identifies promising research directions, including physics-informed neural networks, digital twins, and human–AI collaborative optimization frameworks. The findings highlight AI’s potential to redefine engineering optimization paradigms, while emphasizing the need for robust, scalable, and ethically aligned implementations. Full article

Hyperdimensional Computing (HDC) offers a robust and energy-efficient paradigm for edge intelligence; however, current hardware accelerators are often proprietary, tailored to the target learning task and tightly coupled to specific CPU microarchitectures, limiting portability and adoption. To address this, and democratize the deployment of HDC hardware, we present a general-purpose, plug-and-play accelerator IP that implements the Binary Spatter Code framework as a standalone, host-agnostic module. The design is compliant with the AMBA AXI4 standard and provides an AXI4-Lite control plane and DMA-driven AXI4-Stream datapaths coupled to a banked scratchpad memory. The architecture supports synthesis-time scalability, enabling high-throughput transfers independently of the host processor, while employing microarchitectural optimizations to minimize silicon area. A multi-layer C++ software (GitHub repository commit 3ae3b46) stack running in Linux userspace provides a unified programming model, abstracting low-level hardware interactions and enabling the composition of complex HDC pipelines. Implemented on a Xilinx Zynq XC7Z020 SoC, the accelerator achieves substantial gains over an ARM Cortex-A9 baseline, with primitive-level speedups of up to $431\times$. On end-to-end classification benchmarks, the system delivers average speedups of $68.45\times$ for training and $93.34\times$ for inference. The complete RTL and software stack are released as open-source hardware to support reproducible research and rapid adoption on heterogeneous SoCs. Full article

Extended Reality (XR) technologies have matured into powerful tools for training in high-stakes domains, from emergency response to search and rescue. Yet current systems often struggle to balance real-time AI-driven personalisation with the need for human oversight and calibrated trust. This article synthesizes the programmatic contributions of a multi-study doctoral project to advance a design-and-evaluation framework for trustworthy adaptive XR training. Across six studies, we explored (i) recommender-driven scenario adaptation based on multimodal performance and physiological signals, (ii) persuasive dashboards for trainers, (iii) architectures for AI-supported XR training in medical mass-casualty contexts, (iv) theoretical and practical integration of Human-in-the-Loop (HITL) supervision, (v) user trust and over-reliance in the face of misleading AI suggestions, and (vi) the role of interaction modality in shaping workload, explainability, and trust in human–robot collaboration. Together, these investigations show how adaptive policies, transparent explanation, and adjustable autonomy can be orchestrated into a single adaptation loop that maintains trainee engagement, improves learning outcomes, and preserves trainer agency. We conclude with design guidelines and a research agenda for extending trustworthy XR training into safety-critical environments. Full article

Efficient resource allocation is critical for transportation hub operations, yet current scheduling systems require substantial domain-specific customization when deployed across different facilities. This paper presents a domain-adaptive deep reinforcement learning (DADRL) framework that learns transferable optimization policies for dynamic resource allocation across structurally similar transportation scheduling problems. The framework integrates dual-level heterogeneous graph attention networks for separating constraint topology from domain-specific features, hypergraph-based constraint modeling for capturing high-order dependencies, and hierarchical policy decomposition that reduces computational complexity from $O\left(mnT\right)$ to $O(m+n+T)$. Evaluated on realistic simulators modeling airport gate assignment (Singapore Changi: 50 gates, 300–400 daily flights) and seaport berth allocation (Singapore Port: 40 berths, 80–120 daily vessels), DADRL achieves 87.3% resource utilization in airport operations and 86.3% in port operations, outperforming commercial solvers under strict real-time constraints (Gurobi-MIP with 300 s time limit: 85.1%) while operating 270 times faster (1.1 s versus 298 s per instance). Given unlimited time, Gurobi achieves provably optimal solutions, but DADRL reaches 98.7% of this optimum in 1.1 s, making it suitable for time-critical operational scenarios where exact solvers are computationally infeasible. Critically, policies trained exclusively on airport scenarios retain 92.4% performance when applied to ports without retraining, requiring only 800 adaptation steps compared to 13,200 for domain-specific training. The framework maintains 86.2% performance under operational disruptions and scales to problems three times larger than training instances with only 7% degradation. These results demonstrate that learned optimization principles can generalize across transportation scheduling problems sharing common constraint structures, enabling rapid deployment of AI-based scheduling systems across multi-modal transportation networks with minimal customization and reduced implementation costs. Full article

Soil organic matter (SOM) is a key indicator for evaluating soil fertility and ecological functions, and hyperspectral technology provides an effective means for its rapid and non-destructive estimation. However, in practical soil systems, the spectral response of SOM is often highly covariant with mineral composition, moisture conditions, and soil structural characteristics. Under small-sample conditions, hyperspectral SOM modeling results are usually highly sensitive to spectral preprocessing methods, sample perturbations, and model architecture and parameter configurations, leading to fluctuations in predictive performance across independent runs and thereby limiting model stability and practical applicability. To address these issues, this study proposes a multi-strategy collaborative deep learning modeling framework for small-sample conditions (SE-EDCNN-DA-LWGPSO). Under unified data partitioning and evaluation settings, the framework integrates spectral preprocessing, data augmentation based on sensor perturbation simulation, multi-scale dilated convolution feature extraction, an SE channel attention mechanism, and a linearly weighted generalized particle swarm optimization algorithm. Subtropical red soil samples from Guangxi were used as the study object. Samples were partitioned using the SPXY method, and multiple independent repeated experiments were conducted to evaluate the predictive performance and training consistency of the model under fixed validation conditions. The results indicate that the combination of Savitzky–Golay filtering and first-derivative transformation (SG–1DR) exhibits superior overall stability among various preprocessing schemes. In model structure comparison and ablation analysis, as dilated convolution, data augmentation, and channel attention mechanisms were progressively introduced, the fluctuations of prediction errors on the validation set gradually converged, and the performance dispersion among different independent runs was significantly reduced. Under ten independent repeated experiments, the final model achieved R² = 0.938 ± 0.010, RMSE = 2.256 ± 0.176 g·kg⁻¹, and RPD = 4.050 ± 0.305 on the validation set, demonstrating that the proposed framework has good modeling consistency and numerical stability under small-sample conditions. Full article

The use of physical vehicles and environments during vehicle research and development is highly resource-intensive, particularly for autonomous vehicles. Recently, digital models are therefore increasingly used instead, which require high levels of fidelity and validity. While the two aforementioned qualities are often lacking, an absence of versatility for multi-purpose use is even more prevalent in current digital models. In response to these challenges, this work presents a novel real-time multi-physics digital twin of an offroad vehicle with high levels of fidelity and validity, both regarding the vehicle dynamics and hydraulics, as well as regarding the visual representation of the environment and the exteroceptive sensor emulation. The versatility of the digital twin enables its usage for vehicle development tasks concerning mechanical components and driveline, as well as for visual machine learning tasks, such as generation of auto-annotated visual training data. Development of control algorithms leveraging both visual input and mechanical systems is also enabled. Furthermore, the real-time capability allows for Hardware-in-the-Loop and Vehicle-in-the-Loop simulation. The modeling, calibration, and real-world validation of the digital twin is presented, with an emphasis on the vehicle dynamics and hydraulics. The shown validity enables advancements in the development of autonomous offroad vehicles. Full article

Building cracks are significant indicators of structural integrity. Conventional fracture detection methodologies, however, are characterized by extended durations, significant labor requirements, and limitations in both precision and operational effectiveness. Findings are also subject to subjective and technical constraints inherent in manual assessments. To overcome these challenges, this paper introduces an enhanced YOLOv8-based methodology for developing a building crack detection system, thereby achieving high precision, operational efficiency, and cost-effectiveness. Initially, classified and segmented datasets of building fractures were obtained from field photography, online image aggregation, and open-source databases, thereby providing the basis for training the experimental model. Subsequently, the Swin Transformer window multi-head self-attention mechanism was implemented to augment small-object recognition capabilities and reduce computational demands, thereby enabling the development of an enhanced image segmentation module. Utilizing the U-Net’s segmentation capabilities, a rotated split method was implemented to quantify fracture width and derive geometric parameters from the segmented crack regions. In order to evaluate the effectiveness of the model, two experiments were conducted: one to demonstrate the performance of the classification category and the other to show the capabilities of the segmentation category. The result is that the proposed model has high accuracy and efficiency in the frac detection task. This approach effectively enhances fracture detection in structural safety evaluations of these buildings, providing technical support for relevant management decisions. Full article