Search Results (8,211)

Modeling thermal environments across scales is crucial for climate-adaptive design and energy management. Traditional numerical methods (e.g., CFD) offer high accuracy and physical consistency, but they are computationally expensive. In contrast, purely data-driven models, though efficient, lack physical consistency and generalization capability. This review systematically examines Physics-Informed Neural Networks (PINNs), a hybrid paradigm in which physical prior knowledge is embedded directly into the neural network training process. A structured keyword search of the Web of Science Core Collection was performed, and 94 peer-reviewed journal articles were analyzed. The evolution from numerical simulations and data-driven surrogate models to PINNs is outlined. PINN methods are classified according to the stage at which physical prior information is integrated (i.e., dataset development, model construction, or loss function formulation). Current research remains heavily focused on loss function constraints, whereas systematic integration into data augmentation and model construction remains limited. Application domains span indoor environments, outdoor environments, and building systems, with each domain exhibiting unique prior integration strategies tailored to specific problems. Future PINN modeling should evolve toward multi-physics coupling, adaptive loss balancing, cross-scenario transfer learning, and unified evaluation benchmarks. PINNs in this field are promising but remain at an early stage, especially for complex urban-scale deployment. This review synthesizes existing research around the three stages of dataset development, model construction, and loss function formulation, summarizes the prior integration strategies adopted in the domain of building thermal environments, and provides a practical workflow for embedding physical prior knowledge at different stages of model development. Full article

Selecting superior families at the seedling stage is crucial for accelerating genetic gain in sugarcane, yet systematic comparisons of selection methods remain limited. This study evaluated seven selection strategies: phenotypic check-based selection (Pheno), a three-trait combined index (CI3), Best Linear Unbiased Prediction (BLUP), Best Linear Unbiased Estimation (BLUE), tiered family selection (Tiered), logistic regression (LASSO), and the Multi-Trait Family Ideotype Distance Index (MFIDI). The experiment followed an augmented block design with four blocks, two check varieties, and included 125 test families comprising 10,955 seedlings. Using a combined index of standardized cane and sugar yields, families were classified as elite (top 20%), moderate (60%), and weak (bottom 20%). BLUP and BLUE rankings were consistent (Spearman’s ρ > 0.95, TCI = 88%, Jaccard = 0.79). Elite families showed median index values of 0.90 (BLUP) and 0.88 (BLUE) with wide interquartile ranges, whereas weak families had medians of −0.70 with narrow ranges. LASSO achieved excellent predictive performance: AUC = 0.95, accuracy = 0.92, sensitivity = 0.90, specificity = 0.94, identifying cane yield, sugar yield, and millable cane as key drivers. Agreement for inferior families was lower across methods (BCI ≤ 68%). BLUP with a multi-trait index proved most effective for discriminating elite families. Families F31 and F71 consistently ranked top. Combining selection approaches with agreement indices improves early-stage decisions for family selection in sugarcane breeding. Full article

Wireless-power mobile edge computing, SWIPT-MEC, priority-aware WPT scheduling and swarm resource allocation already solve important parts of the energy-management problem. The novelty of WPT-JCCO is not any one of those elements; it is a single swarm-supervisory feasible set that couples decisions which the three adjacent method classes normally separate. Each epoch-level action jointly selects the robot to charge and one of three physically distinct WPT modalities: far-field radio-frequency, resonant near-field and directional lightwave transfer, together with the SWIPT split, local/edge task placement, CPU frequency, bandwidth and transmit power. Relative to SWIPT-MEC, the formulation adds discrete recipient–modality selection with pose, alignment, blockage and dwell-dependent feasibility. Relative to conventional WPT scheduling, charging is not a separate priority or routing stage but is solved jointly with computation and radio allocation. Relative to swarm resource-allocation methods, energy replenishment is endogenous and an individual minimum-battery constraint protects the weakest robot. A fourth coupling makes the centrally generated resource vector admissible only when the complete sense–compute–actuate age fits the one-second supervisory epoch; otherwise a previously feasible or local-safe action is applied. Nonlinear harvesting, partial offloading, priority scoring and augmented-Lagrangian primal–dual updates are treated as established techniques. This paper derives the continuous block updates, keeps the WPT variables binary through candidate screening, and declares convergence only when stationarity, feasibility, merit-change and binary-hold tests are jointly satisfied. Normalised primal steps are safeguarded by backtracking, dual and penalty updates are bounded, and a local tracking bound plus divergence monitor delimit real-time operation without claiming global mixed-integer optimality or closed-loop motion stability. Numerical evaluation over a 20-robot swarm and 30 Monte Carlo runs shows that WPT-JCCO reduces net energy depletion by 23.8% relative to communication–computation optimisation with static WPT and by 49.7% relative to local-only execution, while increasing task success from 93.5% to 97.3%. A released common-trace comparison shows normalised-cost reductions of 11.1%, 11.3% and 5.8% relative to two-stage WPT+CCO, fixed-SWIPT dynamic offloading and an offline Q-learning scheduler. Convergence and one-factor-at-a-time sensitivity studies further examine swarm size, task load, WPT budget, bandwidth, edge capacity, mobility and channel margin. The headline values remain scoped to the nominal independent-task case; mode-specific RF, near-field and lightwave operating envelopes, robust pose/CSI, WPT-safety and task-DAG extensions are formulated but not presented as hardware-validated results. Full article

Background: Costal cartilage is the preferred structural material for augmentation rhinoplasty when robust and durable tip support is required. However, conventional full-thickness harvest is associated with significant donor-site morbidity, and commonly employed rigid fixation strategies—such as the septal extension graft—substantially restrict postoperative nasal tip compliance. The present study introduces a novel two-component technique combining a half-harvest costal cartilage procurement method with a pyramidal-shaped columellar strut graft anchored on the floating-tip principle, with the objective of maintaining postoperative nasal tip flexibility while providing structural support following augmentation rhinoplasty. Methods: A retrospective review was performed of consecutive patients who underwent primary or revision augmentation rhinoplasty using the pyramidal costal cartilage columellar strut graft technique by a single surgeon between June 2018 and February 2026. The medial half of the conjoined costal cartilage at the seventh, eighth, or ninth rib was procured via a half-harvest approach, preserving the lateral cortex and perichondrium to minimize donor-site morbidity and potential cartilage regeneration was considered a theoretical benefit. The harvested cartilage was carved into a pyramidal columellar strut and secured to the anterior nasal spine using a floating fixation construct; the inferior base of the strut was rigidly fixed to the nasal septum and anterior nasal spine with a minimum of three PDS 5-0 sutures, while the superior portion remained free to preserve physiologic nasal tip mobility. Adjunctive cap and shield grafts, perichondrial wrapping, and dermal fat grafts were employed as indicated. Primary outcomes included nasal tip projection, postoperative tip mobility, donor-site morbidity, and surgical complication rates. Results: Favorable clinical observations of maintained tip projection were noted throughout follow-up. Manual postoperative examination suggested preservation of tip flexibility in most patients; however, no validated objective mobility assessment tool was available. The revision rate for clinically significant tip deviation was low. No major donor-site adverse events—including pneumothorax or rib fracture—were encountered. Postoperative chest wall pain was minimal and transient, with most patients resuming daily activities within one week of surgery. Conclusions: The pyramidal-shaped costal cartilage columellar strut graft with half-harvest technique is a novel, biomechanically informed, and technically reproducible approach to augmentation rhinoplasty that was developed to address donor-site morbidity and postoperative tip rigidity, two commonly recognized limitations of conventional costal cartilage rhinoplasty: donor-site morbidity and postoperative nasal tip rigidity. Preservation of the lateral cortex and perichondrium during procurement may contribute to reduced postoperative donor-site discomfort, accelerates functional recovery, and may promote endogenous cartilage regeneration over time. The anatomically derived pyramidal strut geometry, combined with floating fixation to the anterior nasal spine, was designed to approximate the native columellar architecture, enabling consistent preservation of physiologic nasal tip mobility. The present series demonstrated a favorable safety profile with a low overall complication rate and an absence of major donor-site adverse events. Prospective studies with validated objective outcome measures are required to confirm these findings, to delineate the optimal patient selection criteria, and to establish evidence-based long-term outcome benchmarks for this technique. Full article

Lysine lactylation (Kla) is a recently discovered post-translational modification implicated in energy metabolism, cellular reprogramming, and disease progression. Here, we train the existing ProteinBERT-based predictor PBertKla on an integrated multi-source dataset and augment it with a lightweight machine-learning (ML) layer over sequence-derived features to predict Kla sites; on a common blind test set, the resulting model (PBertKla + ML) reaches an area under the receiver operating characteristic curve (AUROC) of 0.9126 on the integrated set and is statistically indistinguishable from the strongest available tool (Auto-Kla, DeLong p = 0.74) while significantly exceeding a recent ProtBert-based method (PCBert-Kla, p = 4 × 10⁻¹⁵). Two elements support this result. First, to train and benchmark the model, we assembled and released the largest curated Kla dataset to date, Multi (26,034 samples compiled from nine published sources through a 9-step quality-control pipeline), as a community resource. Second, we validated the model under a leakage-controlled protocol: re-training the complete pipeline under protein-level, 40%-identity homology, and leave-one-study-out splits—each verified to have zero train–test overlap—maintained ≈0.90 AUROC, only 0.6–1.5 percentage points (pp) below the random-split value, confirming genuine generalization rather than memorization. Ablation and SHapley Additive exPlanations (SHAP) analyses locate the predictive signal primarily in the ProteinBERT metafeature, with the ML layer adding a modest but real increment (+0.63 pp over PBertKla alone on Multi; no significant gain on the smaller hepatocellular carcinoma (HCC) set). Finally, an exploratory AlphaFold-based structural case study of FAM210A illustrates how predicted Kla sites distribute across ordered and disordered regions, without claiming a quantitative structure–probability relationship. All trained weights and code are publicly available. Full article

Human-Centered AI (HCAI) has emerged as a guiding paradigm for designing AI systems that align with human values, needs, and well-being, yet the field lacks consensus on what constitutes human-centeredness. This study addresses that gap through a four-phase sequential mixed-methods design: (1) thematic analysis of 81 HCAI definitions from academic, institutional, and industry sources, yielding 78 keywords; (2) frequency-based statistical categorization; (3) expert evaluation producing a final inventory of 26 attributes; and (4) a cross-sectional survey (N = 145), predominantly drawn from the Asia-Pacific region (77.2%, with Myanmar, Singapore, and Thailand most represented), in which practitioners, academics, and students rated each attribute on a 7-point Likert scale, complemented by a reflexive thematic analysis of open-ended responses. The 26-item scale demonstrated excellent internal consistency. Trust, values, benefits, needs, and usability were rated most highly, while affective and cognitive attributes—emotions, behaviours, and empathy—were consistently rated lower, a pattern the qualitative data suggest reflects perceived intractability rather than indifference. Inter-attribute correlations revealed interpretable substructures, including an experience/usability cluster, an emotion/empathy cluster, and a participatory engagement cluster, while human control operated as a conceptually independent dimension. Five qualitative themes provided interpretive context: user needs and augmentation as design drivers, ethical foundations and value alignment, trust as a relational outcome contingent on transparency, the complexity of human experience as a design challenge, and structural barriers including corporate incentives, regulatory gaps, and resource constraints. In this predominantly Southeast Asian sample, all three stakeholder groups showed substantial agreement on which attributes matter most and least. The primary divergence ran between academics and students: academics assigned higher importance to participatory and process-oriented attributes, while students emphasized tangible outcomes. Practitioners occupied an intermediate position, with a distinctive emphasis on ethical values. These findings offer an empirically grounded vocabulary for human-centeredness, positioned as an exploratory foundation for future psychometric refinement, with implications for HCAI design practice, education, and cross-stakeholder dialogue. Full article

The sea urchin embryo represents a well-established model organism widely applied in embryo toxicity assays, ecotoxicological investigations, and biomonitoring studies. These analyses are primarily based on the morphological evaluation of embryos, which is conventionally carried out by experts through light microscopy. However, this approach is both time-intensive and inherently subjective, as the outcomes strongly depend on the evaluator’s expertise and experience. With the increasing adoption of machine learning techniques in image classification tasks, this study investigates the applicability of machine-learning-based approaches for the classification of sea urchin embryo images. The dataset used in this work originates from a previous study examining the effects of nickel exposure on Paracentrotus lividus embryos, with concentrations ranging from 0.01 to 3.0 mM. Given the limited size of the available dataset, data augmentation techniques were applied to artificially expand the number of training samples. Subsequently, a convolutional neural network classification model was developed using both original and augmented images, and its performance was assessed using multiple evaluation metrics. The proposed model demonstrated strong performance, achieving a maximum F1 score of 0.976 and an accuracy of 0.988. These results indicate that machine-learning-based approaches can effectively support the classification of sea urchin embryo images even in data-constrained scenarios. Overall, this work contributes to the development of automated and objective methods for morphological assessment, with the potential to enhance both the reliability and efficiency of traditional evaluation procedures. Full article

Background: The emergence of generative adversarial networks has laid the groundwork for data augmentation, addressing challenges of missing training data in various research scenarios. However, simulating functional magnetic resonance imaging (fMRI) data remains particularly challenging, especially for populations with varying degrees of mild cognitive impairment (MCI). Effectively characterizing and capturing the mechanisms of brain function variations poses a critical issue in cognitive neuroscience. This study aims to simulate and analyze synthetic fMRI blood-oxygen-level-dependent (BOLD) signals across four cognitive stages: healthy control (HC), early MCI (EMCI), late MCI (LMCI), and Alzheimer’s disease (AD). Methods: We propose WGTMM, an innovative method that integrates the Vision Transformer for fMRI (VTFF) into a generative adversarial network architecture. Crucially, WGTMM directly generates fMRI time-series data from pink noise rather than modeling in a latent space, thereby preserving rich temporal dynamics. The framework incorporates a Wasserstein GAN (WGAN) with feature matching to enhance generation quality and mitigate mode collapse. Results: demonstrate that WGTMM-generated fMRI data exhibit lower Kullback-Leibler (KL) divergence compared to traditional GAN and WGAN models, indicating a closer resemblance to real datasets from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Furthermore, when applied to data augmentation, the synthetic data substantially improve multi-class classification performance. Conclusions: WGTMM not only enriches training datasets but also provides new insights into spatial biomarkers of cognitive decline. By leveraging VTFF to investigate class token attention patterns across 360 brain regions, this study reveals monotonic weight variations along disease stages in key cortical areas, including the rostral Area 6, the primary sensory cortex, and PFm near Wernicke’s area, offering a fine-grained exploration of disease progression. Full article

Background/Objectives: Aromatic L-amino acid decarboxylase deficiency (AADC-D; OMIM #608643) is a rare autosomal recessive neurometabolic disorder caused by pathogenic variants in the DDC gene, leading to impaired of monoamine neurotransmitter biosynthesis. AADC, a pyridoxal-5′-phosphate (PLP)-dependent enzyme, catalyzes the conversion of L-dopa and 5-hydroxytryptophan (5-HTP) to dopamine and serotonin, respectively. Early diagnosis remains challenging due to the limited specificity of current biochemical approaches. This study aimed to evaluate plasma AADC enzyme activity using these physiological substrates by High-Performance Liquid Chromatography (HPLC)-based method and assess its potential utility in the biochemical diagnosis of AADC deficiency. Methods: Plasma AADC activity was quantified using physiological substrates (L-dopa and 5-HTP) by HPLC with electrochemical and fluorescence detection. Sanger sequencing of the DDC gene was performed in two suspected patients to identify pathogenic variants. Results: Two genetically confirmed AADC-D patients demonstrated reduced enzyme activity. Using L-dopa as substrate, enzyme activity in patients was 12.4 and 26.1 pmol/min/mL, both below the published reference interval (36–129 pmol/min/mL). Using 5-HTP as substrate, enzyme activity was 1.5 and 5.1 pmol/min/mL; Patient 1 showed activity below the reference interval (2.0–7.1 pmol/min/mL), while Patient 2 demonstrated activity within the lower range of reported values. Reduced enzyme activity was consistent with the clinical features and molecular findings with identification of pathogenic variants in the DDC gene (c.175G>A and c.714+4A>T). Conclusions: Plasma AADC activity measurement demonstrates potential as a functional biochemical biomarker that augments molecular genetic testing in the biochemical evaluation of AADC deficiency. Further studies involving larger patient cohorts are required to further evaluate its diagnostic performance and broader clinical applicability. Full article

As a next-generation automotive display technology, Augmented Reality Head-Up Display (AR-HUD) has demonstrated immense potential in reshaping driving safety and enhancing the human–computer interaction experience. To address the challenges of barrel distortion and perspective distortion inherent in HUD systems, we propose a joint-learning-based dual-path pre-correction method. This approach employs a shared encoder to extract image features, which are then decoupled into two parallel branches: a classification branch and a distortion flow prediction branch. Building upon this architecture, a model-fitting method is introduced to estimate the distortion model parameters in the parameter space using the predicted distortion types and flows, thereby reconstructing a refined distortion flow. Finally, image rectification is achieved through a resampling method. On the ARHDD dataset, the proposed method achieves a PSNR of 24.617 dB (barrel) and 25.062 dB (perspective), an SSIM of 0.845 and 0.873, and an NRMSE of 0.163 and 0.157, respectively. On the Places 365 dataset, it achieves a PSNR of 23.914 dB (barrel) and 21.870 dB (perspective), an SSIM of 0.812 and 0.748, and an NRMSE of 0.174 and 0.211, respectively. Both quantitative and qualitative comparative experiments against other state-of-the-art methods demonstrate that the proposed approach achieves superior correction performance for both types of distortion. Finally, the simulation verification of the HUD system proved that this correction method demonstrated excellent potential, but further verification is still needed in a real or semi-real environment. Full article

Diagnosing tilapia diseases in complex aquaculture environments is severely hindered by noisy backgrounds and limited high-quality pathological data. To overcome these bottlenecks, this study presents a two-stage diagnostic framework integrating an enhanced Segment Anything Model (SAM) with an Adaptive Neuro-Fuzzy Inference System (ANFIS). In the first stage, SAM is augmented with a Convolutional Block Attention Module (CBAM) feature adapter and a Region Proposal Network (RPN)-based prompt encoder. This design enables the automated and precise extraction of irregular disease lesions by self-generating spatial prompts, thereby isolating water background noise. In the second stage, clinical color features extracted from the lesion masks are classified using ANFIS. To optimize performance on small-scale datasets, ANFIS parameters are trained via Particle Swarm Optimization (PSO) under a numerically stable One-vs-Rest (OvR) binary cross-entropy loss. Validated on the public dataset “Enhancing Disease Detection in Nile Tilapia”, our method delivers an average segmentation Dice coefficient of 86.2% and a classification accuracy of 93.5%. This hybrid approach demonstrates strong potential as a foundational baseline for the automated monitoring of aquaculture diseases. Full article

Global economic policy uncertainty has emerged as a significant challenge for developing regions, with Sub-Saharan Africa particularly vulnerable due to its fragile economies and social systems that rely on external support. This study examines the effect of global economic policy uncertainty on social sustainability and how this relationship is moderated by governance effectiveness and natural resource rents. These relationships were examined using 27 years of panel data from 45 Sub-Saharan African countries, spanning 1997 to 2023. The Augmented Mean Group (AMG), Common Correlated Effects Mean Group (CCMG), and the two-step difference Generalized Method of Moments (GMM) estimators are advanced methods for analyzing data and estimating relationships among variables. The study found that global economic policy uncertainty had a significant negative effect on social sustainability. Furthermore, the study revealed that governance effectiveness and natural resource rents positively and significantly moderate the relationship between global economic policy uncertainty and social sustainability. These findings have significant implications for policy and governance, highlighting the critical need for governments, especially in developing and resource-dependent regions, to strengthen institutional capacity and fiscal frameworks in order to manage the adverse effects of global economic policy uncertainty. They underscore the importance of developing responsive, transparent, and accountable governance structures that can effectively allocate resources toward social priorities even during periods of external economic volatility. Full article

Background/Aims: While pathogenic germline variants play a critical role in pediatric cancer susceptibility, traditional clinical genetics primarily focuses on single-gene interpretations. Transitioning to a systems-level analysis of inherited variation can uncover shared biological vulnerabilities, informing genetic counseling, surveillance, and targeted therapeutics. This study aims to implement an unsupervised machine learning framework to identify and characterize Germline Mutation Signatures (GMS) across diverse pediatric malignancies, elucidating latent genomic patterns that reveal shared oncogenic mechanisms. Methods: We analyzed germline whole-exome and whole-genome sequencing (WES/WGS) data from a retrospective cohort of 420 pediatric cancer patients and matched non-cancer controls. Variants were deeply annotated to capture multi-dimensional features, including predicted pathogenicity, splice-site disruption, regulatory impact, population frequency, and sequence context. To enable robust modeling, we integrated an augmented feature set encompassing evolutionary constraint, loss-of-function intolerance, and compositionally normalized substitution spectra. These high-dimensional annotations were processed using a deep autoencoder for non-linear representation learning, followed by Gaussian Mixture Modeling (GMM) of the latent space. Results: The framework delineated 13 signatures (GMS1–GMS13), yielding an optimal Davies–Bouldin index of 1.051. These signatures map to fundamental biological processes, including DNA repair deficiencies, transcription-coupled damage, replication stress, and aberrant RNA regulation. Crucially, these GMSs transcend traditional tissue-of-origin classifications, manifesting across multiple distinct cancer types. This observation indicates convergent germline etiologies and suggests potential shared susceptibilities to pathway-directed therapies. Conclusions: The discovery of these cross-cancer signatures provides a scalable, biologically interpretable framework for decoding inherited pediatric cancer risk. While the therapeutic mapping networks identified are currently exploratory and serve as a hypothesis-generating foundation, this deep learning-driven paradigm establishes a robust basis for stratified precision medicine. Pending prospective clinical validation, this approach holds significant translational potential to move beyond single-gene paradigms toward unified, systems-level precision oncology strategies. Full article

Rotating machinery is a key component in modern industry, and its operating condition directly affects equipment safety and production reliability. However, discrepancies among different machines cause source–target distribution shifts, while fault annotation for target machines is costly, limiting the performance of deep learning-based diagnosis under cross-machine scenarios with limited labels. To address these issues, this paper proposes a multi-scale time–frequency semantic consistency model based on self-supervised transferable representation learning, termed MTFSC. First, augmented waveform views and multi-scale frequency-domain views are constructed from unlabeled source-domain vibration signals for self-supervised pre-training without source labels. Then, a time-domain impulse-aware feature extractor and a time–frequency decoupled spectral feature extractor are designed to enhance local impulsive responses and emphasize fault-sensitive time–frequency patterns. Furthermore, a semantic-aware soft contrastive loss is developed to mine potential semantic neighbors from multi-scale frequency-domain structural similarity, reducing false-negative effects in conventional hard-label contrastive learning. Finally, the pre-trained time-domain extractor is transferred to the target machine and fine-tuned with limited labeled samples. Experimental results show that MTFSC outperforms comparison methods under different labeled sample ratios and achieves an average accuracy of 97.5% across four cross-machine diagnostic tasks. Full article

The limited augmented Zarankiewicz number provides a combinatorial lower bound for the maximum SOS rank of biquadratic forms and refines the classical Zarankiewicz number by allowing admissible augmented edges. In this paper, new lower bounds for this number are established by using incidence graphs of complete graphs. An infinite family of constructions based on complete graphs is presented, showing that the gap between the limited augmented Zarankiewicz number and the classical Zarankiewicz number can grow linearly with the size of the graph. Several small cases are also studied in detail. In particular, exact values are obtained for the cases $6\times 4$, $5\times 3$, and $5\times 4$, and an improved lower bound is given for the $5\times 5$ case. In addition, a lifting method is introduced to construct admissible limited augmented graphs on larger parameter pairs from suitable smaller ones, leading to further lower bounds. These results strengthen the connection between extremal bipartite graph theory and SOS-rank lower bounds for biquadratic forms. Full article