Search Results (608)

Massive MIMO systems can substantially enhance spectral efficiency, but such gains rely on the availability of accurate channel state information (CSI). However, the increase in the number of antennas leads to a significant growth in feedback overhead, while conventional deep-learning-based CSI feedback methods also impose a substantial computational burden on the user equipment (UE). To address these challenges, this paper proposes LLM4FB, a one-sided CSI feedback framework that leverages a pre-trained large language model (LLM). In this framework, the UE performs only low-complexity linear projections to compress CSI. In contrast, the BS leverages a pre-trained LLM to accurately reconstruct and predict CSI. By utilizing the powerful modeling capabilities of the pre-trained LLM, only a small portion of the parameters needs to be fine-tuned to improve CSI recovery accuracy with low training cost. Furthermore, a multiobjective loss function is designed to simultaneously optimize normalized mean square error (NMSE) and spectral efficiency (SE). Simulation results show that LLM4FB outperforms existing methods across various compression ratios and mobility levels, achieving high-precision CSI feedback with minimal computational capability from terminal devices. Therefore, LLM4FB presents a highly promising solution for next-generation wireless sensor networks and industrial IoT applications, where terminal devices are often strictly constrained by energy and hardware resources. Full article

Integrated Sensing and Communication (ISAC) has emerged as a cornerstone technology for next-generation wireless networks, where accurate performance evaluation is essential. In such systems, the capacity–distortion function provides a fundamental measure of the trade-off between communication and sensing performance, making its computation a problem of significant interest. However, the associated optimization problem is often constrained by non-convexity, which poses considerable challenges for deriving effective solutions. In this paper, we propose extended Arimoto–Blahut (AB) algorithms to solve the non-convex optimization problem associated with the capacity–distortion trade-off in bistatic ISAC systems. Specifically, we introduce auxiliary variables to transform non-convex distortion constraints in the optimization problem into linear constraints, prove that the reformulated linearly constrained optimization problem maintains the same optimal solution as the original problem, and develop extended AB algorithms for both squared error distortion and logarithmic loss distortion. The numerical results validate the effectiveness of the proposed algorithms. Full article

Water quality prediction serves as a crucial basis for water environment supervision and is of great significance for water resource protection. This study utilized meteorological and water quality data from 40 monitoring stations in the Tuojiang River Basin, Sichuan Province, China. A Gated Recurrent Unit (GRU) model and a Graph Attention Network–Gated Recurrent Unit (GAT-GRU) model were constructed. Furthermore, based on the GAT-GRU framework, an Enhanced Spatio-Temporal Relation-Guided Gated Recurrent Unit (ESRG-GRU) model was developed by incorporating an explicit river network topology and a loss function that is sensitive to extreme values to strengthen spatio-temporal relationships. Water quality predictions were made for all 40 stations, and the performance of the three models was compared. The results show that, during the 7-day forecasting period, the training time of both the ESRG-GRU and the GAT-GRU models was only about 1/40 of that required for the GRU model. In terms of prediction accuracy, the average Nash–Sutcliffe efficiency (NSE) values over the 7-day forecast period were ESRG-GRU (0.7904) > GAT-GRU (0.7557) > GRU (0.6870), while the average root mean square error (RMSE) values were ESRG-GRU (0.0156) < GAT-GRU (0.0168) < GRU (0.0185). Regarding accuracy across different regions and seasons within the river basin, the ESRG-GRU model, guided by enhanced spatio-temporal deep learning, consistently outperformed both the GRU and the GAT-GRU models. This method can effectively enhance both the efficiency and accuracy of water quality prediction, thereby providing support for water environment supervision and regional water quality improvement. Full article

Bounding box regression (BBR) loss plays a critical role in object detection within computer vision. Existing BBR loss functions are typically based on the Intersection over Union (IoU) between predicted and ground truth boxes. However, these methods neither account for the effect of predicted box scale on regression nor effectively address the drift problem inherent in BBR. To overcome these limitations, this paper introduces a novel BBR loss function, termed Gaussian Adaptive Ochiai BBR loss (GAOC), which combines the Ochiai Coefficient (OC) with a Gaussian Adaptive (GA) distribution. The OC component normalizes by the square root of the product of bounding box dimensions, ensuring scale invariance. Meanwhile, the GA distribution models the distance between the top-left and bottom-right corners (TL/BR) coordinates of predicted and ground truth boxes, enabling a similarity measure that reduces sensitivity to positional deviations. This design enhances detection robustness and accuracy. GAOC was integrated into YOLOv5 and RT-DETR and evaluated on the PASCAL VOC and MS COCO 2017 benchmarks. Experimental results demonstrate that GAOC consistently outperforms existing BBR loss functions, offering a more effective solution. Full article

Predicting core loss under high-frequency non-sinusoidal excitation is crucial for power electronics equipment design. Temperature significantly affects core loss, and traditional core loss prediction models typically incorporate temperature corrections to enable accurate loss estimation across varying temperatures. Based on the Modified Steinmetz Equation (nonT-MSE) model, this study considers the temperature effect by employing a combination of the Tanh function and a linear term to modify the three empirical parameters, with the Tanh function capturing the nonlinear saturation of the loss coefficient k with increasing temperature. This leads to the establishment of the temperature-corrected non-TMSE (T-MSE) model for predicting magnetic core loss under high-frequency non-sinusoidal excitation. During model derivation, training data undergo logarithmic transformation processing. Subsequently, with T-MSE empirical parameters as variables and the minimum mean squared error between T-MSE predicted values and experimental values as the objective function, a single-objective optimization model is established. Finally, the empirical parameters of T-MSE are calculated using the training data and the single-objective optimization model. Comparing the core loss experimental results of the four materials, the average MSE values for the T-MSE model, the nonT-MSE model, and the square-root temperature-corrected non-TMSE model proposed by Zeng et al. (Zeng) are 0.0082, 0.0459, and 0.0110, respectively; with average MAPE of 1.57%, 1.87%, and 2.17%, respectively; and average R² of 0.9862, 0.9807, and 0.9731. Compared to the nonT-MSE model and the Zeng model, the T-MSE model demonstrated higher prediction accuracy. 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: Genetic mutations have proven to be the epicenters of cancer and disease progression. Traditional WXS sequencing and BLOSUM scoring can be used to infer the evolutionary conservation of amino acid substitutions, though these approaches are not informed by probable base pair sequence changes. Within gene mutation analysis, most tools focus on amino acid conservation or codon switching independently, limiting their ability to contextualize observed mutations against stochastic mutational processes. In the clinical setting, variants of unspecified significance remain difficult to interpret, as clinicians are often unable to determine whether observed mutations arise from oncogenic selection or from stochastic mutational degradation. Methods: We analyzed mutation sequences from the TCGA BRCA cohort for TP53 and PIK3CA and developed a model that integrates BLOSUM scoring with statistical modeling of base pair changes to evaluate deviation from codon-aware neutral expectations. Observed mutational distributions were compared against a stochastic neutral model to assess statistical significance. Results: Within the TCGA BRCA cohort, TP53 mutations were significantly more evolutionarily radical than expected under the codon-aware neutral model, while PIK3CA mutations were significantly more evolutionarily conservative, as determined using chi-square testing. These opposing patterns are consistent with the distinct functional roles of TP53 and PIK3CA in oncogenesis, where TP53 is inhibited through disruptive loss-of-function mutations, whereas PIK3CA is recurrently mutated in a manner that preserves protein structure and promotes constitutive pathway activation. This contrast reflects selective pressure toward disabling tumor suppressor function while maintaining persistent oncogenic signaling. Conclusions: Codon-aware neutral modeling provides a statistical framework for distinguishing mutations that deviate from stochastic expectations and may aid in the interpretation of variants of unspecified significance. By contextualizing mutational severity relative to neutral processes, this approach offers insight into tumor evolution and may support prognostic assessment without relying on predefined gene-level neutrality. Full article

Retrieval-augmented generation (RAG) has emerged as an effective approach for analyzing massive and diverse data. It offers promising avenues for energy management and intelligent decision support amid the accelerating digital transformation of the power industry. However, when applied to this specialized domain, traditional RAG systems face two key challenges: (1) poor comprehension of domain-specific terminology, leading to irrelevant retrieval, and (2) limited precision in re-ranking the retrieved results. To address these limitations, this paper presents an innovative integrated optimization framework. The framework enhances RAG performance in the electric power domain through two key strategies. First, we adapt a base embedding model to the domain using contrastive learning and iteratively refine hard negative samples to improve retrieval quality. Second, we employ a large language model (LLM) as a teacher to distill re-ranking knowledge into a lightweight bidirectional encoder representations from transformers (BERT) model, using a hybrid loss function that combines mean squared error (MSE) loss and margin ranking loss. The framework aims to simultaneously improve the model’s understanding of domain-specific terminology and the re-ranking accuracy of critical information. Experimental results on both a private power-domain dataset and the public DuReader_robust benchmark demonstrate that the proposed framework achieves significant performance gains. Comprehensive ablation studies confirm the necessity of each component and reveal their synergistic effects within the framework. Furthermore, sensitivity analyses of key hyperparameters confirm the effectiveness of our hybrid loss and identify optimal configurations that enhance both retrieval and generation performance. This work not only introduces an effective optimization framework tailored for domain-specific RAG applications but also advances industrial intelligence by enhancing the accuracy and reliability of information services. Full article

This paper presents an Artificial Neural Network (ANN) approach for estimating total real and reactive power losses in electrical power systems. Three network architectures were explored: the Multilayer Perceptron (MLP), the Radial Basis Function (RBF) network, and the Generalized Regression Neural Network (GRNN). The main advantage of the proposed methodology lies in its ability to rapidly compute power loss values throughout the system. ANN models are especially effective due to their capacity to capture the nonlinear characteristics of power systems, thus eliminating the need for iterative procedures. The applicability and effectiveness of the approach were evaluated using the IEEE 14-bus test system and compared with the continuation power flow method, which estimates losses using conventional numerical techniques. The results indicate that the ANN-based models performed well, achieving mean squared error (MSE) values below the predefined threshold during both training and validation (0.001). Notably, the networks accurately estimated the total power losses within the expected range, with residuals on the order of 10⁻⁴. Among the models tested, the RBF network showed slightly superior performance in terms of error metrics, requiring fewer centers to meet the established criteria compared to the MLP and GRNN models (11 centers). However, the GRNN achieved the shortest processing time; even so, all three networks produced satisfactory and consistent results, particularly in identifying the critical points of electrical power systems, which is of fundamental importance for ensuring system stability and operational reliability. Full article

Background: Duchenne muscular dystrophy (DMD) results from pathogenic variants in the DMD gene, one of the most significant and most mutation-prone genes in the human genome. Although global mutation registries are well developed, genetic data from Central Asian populations remain extremely limited, leaving essential gaps in regional epidemiology and in the understanding of genotype–phenotype patterns. Methods: We conducted a retrospective analysis of patients with genetically confirmed dystrophinopathy in Kazakhstan. Variants were identified using multiplex ligation-dependent probe amplification (MLPA) for exon-level copy number alterations and next-generation sequencing (NGS) with Sanger confirmation for sequence-level changes. All variants were classified under ACMG guidelines. Statistical modelling incorporated mutation-class grouping, exon-hotspot mapping, reading-frame status, CPK stratification, chi-squared association testing, Spearman correlations, Kaplan–Meier ambulation survival curves, and multivariable logistic and Cox regression. Results: multi-exon deletions were the predominant mutation class, with a marked concentration within the canonical hotspot spanning exons 44–55. Recurrent deletions affecting exons 46–50 and 45–50 appeared in several unrelated patients. NGS confirmed severe protein-truncating variants, including p. Lys1049* and p. Ser861Ilefs*7. Phenotypic severity followed a consistent hierarchy: hotspot-associated deletions and early truncating variants showed the earliest loss of ambulation, whereas splice-site variants and duplications demonstrated the mildest courses. CPK levels correlated with the extent of genomic involvement, though extreme elevations did not consistently predict early functional decline. Regression models identified hotspot localization and out-of-frame effect as independent predictors of ambulation loss. Conclusions: This study provides the first statistically modelled characterisation of DMD gene mutations in Kazakhstan. While the mutational landscape largely mirrors global patterns, notable variability in clinical severity suggests the presence of population-specific modifiers. Integrating comprehensive molecular diagnostics with statistical-genetics approaches enhances prognostic accuracy and supports the development of mutation-targeted therapeutic strategies in Central Asia. Full article

Frequent cloud cover severely limits the use of optical remote sensing for continuous ecological monitoring. Synthetic aperture radar (SAR) offers an all-weather alternative, but translating SAR data to optical equivalents is challenging, particularly in cloudy regions where paired training data are scarce. To address this, we developed an enhanced CycleGAN (denoted by SA-CycleGAN) to derive a high-fidelity, temporally continuous normalized difference vegetation index (NDVI) from SAR imagery. The SA-CycleGAN introduces a novel spatiotemporal attention generator that dynamically computes global and local feature relationships to capture long-range spatial dependencies across diverse landscapes. Furthermore, a structural similarity (SSIM) loss function is integrated into the SA-CycleGAN to preserve the structural and textural integrity of the synthesized images. The performance of the SA-CycleGAN and three unsupervised models (DualGAN, GP-UNIT, and DCLGAN) was evaluated by deriving NDVI time series from Sentinel-1 SAR images across four sites with different vegetation types. Ablation experiments were conducted to verify the contributions of the key components in the SA-CycleGAN model. The results demonstrate that the SA-CycleGAN significantly outperformed the comparison models across all four sites. Quantitatively, the proposed method achieved the lowest Root Mean Square Error (RMSE) of 0.0502 and the highest Coefficient of Determination (R²) of 0.88 at the Zhangbei and Xishuangbanna sites, respectively. The ablation experiments confirmed that the attention mechanism and SSIM loss function were crucial for capturing long-range features and maintaining spatial structure. The SA-CycleGAN proves to be a robust and effective solution for overcoming data gaps in optical time series. Full article

Background/Objectives: Hydroxyapatite (HAp)-based implants and HAp–titanium (HApTi) composites are widely used in orthopedic and dental applications, but their long-term success is limited by peri-implant bone loss. Local delivery of osteoactive molecules from implant surfaces may enhance osseointegration and reduce periprosthetic osteolysis. This study combined in silico modeling and experimental assays to compare calcium fructoborate (CaFb), sodium alendronate, and calcium alendronate as functionalization agents for HAp and HApTi implants. Methods: Molecular docking (AutoDock 4.2.6) and 100 ns molecular dynamics (MD) simulations (AMBER14 force field, SPC water model) were performed to characterize ligand–substrate interactions and to calculate binding free energies (ΔG_binding) and root mean square deviation (RMSD) values for ligand–HAp/HApTi complexes. HAp and HApTi discs obtained by powder metallurgy were subsequently functionalized by surface adsorption with CaFb or alendronate salts. The amount of adsorbed ligand was determined gravimetrically, and in vitro release profiles were quantified by HPTLC–MS for CaFb and by HPLC after FMOC derivatization for alendronates. Results: CaFb–HAp and CaFb–HApTi complexes showed the lowest binding free energies (−1.31 and −1.63 kcal/mol, respectively), indicating spontaneous and stable interactions. For HAp-based complexes, the mean ligand RMSD values over 100 ns were 0.27 ± 0.17 nm for sodium alendronate, 0.72 ± 0.28 nm for calcium alendronate (range 0.35–1.10 nm), and 0.21 ± 0.19 nm for CaFb (range 0.15–0.40 nm). For HApTi-based complexes, the corresponding RMSD values were 0.30 ± 0.15 nm for sodium alendronate, 0.72 ± 0.38 nm for calcium alendronate and 0.26 ± 0.14 nm for CaFb. These distributions indicate that CaFb and sodium alendronate maintain relatively stable binding poses, whereas calcium alendronate shows larger conformational fluctuations, consistent with its less favorable binding energies. Experimentally, CaFb exhibited the greatest chemisorbed amount and percentage on both HAp and HApTi, followed by sodium and calcium alendronate. HApTi supported higher loadings than HAp for all ligands. Release studies demonstrated a pronounced burst and rapid plateau for both alendronate salts, whereas CaFb displayed a slower initial release followed by a prolonged, quasi-linear liberation over 14 days. Conclusions: The convergence between in silico and adsorption–release data highlights CaFb as the most promising candidate among the tested ligands for long-term functionalization of HAp and HApTi surfaces. Its stronger and more stable binding, higher loading capacity and more sustained release profile suggest that CaFb-coated HApTi implants may provide a favorable basis for future in vitro and in vivo studies aimed at improving osseointegration and mitigating periprosthetic osteolysis, although direct evidence for osteolysis prevention was not obtained in the present work. Full article

All-medium metamaterial absorbers (MMAs) have attracted considerable attention for ultra-broadband electromagnetic wave (EMW) absorption. Herein, a lightweight graphene aerogel (GA) was synthesized through a low-temperature, atmospheric-pressure reduction route. Benefiting from its 3D porous network, enriched oxygen-containing functional groups, and improved graphitization, the GA offers diverse intrinsic attenuation pathways and a limited effective absorption bandwidth (EAB) of only 6.46 GHz (11.54–18.00 GHz at 1.95 mm). To clarify its attenuation mechanism, nonlinear least-squares fitting was used to quantitatively separate electrical loss contributions. Compared with graphene, the GA shows markedly superior attenuation capability, making it a more suitable medium for MMA design. Guided by equivalent circuit modeling, a stacked frustum-configured GA-based MMA (GA-MMA) was developed, where structure-induced resonances compensate for the intrinsic absence of magnetic components in the GA, thereby substantially broadening its absorption range. The GA-MMA achieves an EAB of 40.7 GHz (9.1–49.8 GHz, reflection loss < −10 dB) and maintains stable absorption under incident angles up to ± 70°. Radar cross-section simulations further indicate its potential in electromagnetic interference mitigation, human health protection, and defense information security. This work provides a feasible route for constructing ultralight and broadband MMAs by coupling electrical loss with structural effects. Full article

High-resolution Digital Terrain Models (DTMs) are essential for precise terrain analysis, yet their production remains constrained by the high cost and limited coverage of LiDAR surveys. This study introduces a deep learning framework based on a modified Residual Channel Attention Network (RCAN) to super-resolve 10 m DTMs to 1 m resolution. The model was trained and validated on a 568 km² LiDAR-derived dataset using custom elevation-aware loss functions that integrate elevation accuracy (L1), slope gradients, and multi-scale structural components to preserve terrain realism and vertical precision. Performance was evaluated across 257 independent test tiles representing flat, hilly, and mountainous terrains. A balanced loss configuration (α = 0.5, γ = 0.5) achieved the best results, yielding Mean Absolute Error (MAE) as low as 0.83 m and Root Mean Square Error (RMSE) of 1.14–1.15 m, with near-zero bias (−0.04 m). Errors increased moderately in mountainous areas (MAE = 1.29–1.41 m, RMSE = 1.84 m), confirming the greater difficulty of rugged terrain. Overall, the approach demonstrates strong potential for operational applications in geomorphology, hydrology, and landscape monitoring, offering an effective solution for high-resolution DTM generation where LiDAR data are unavailable. Full article

Accurate state estimation is essential for the real-time operation and control of modern distribution systems characterized by high renewable energy penetration, bidirectional power flows, and volatile loads. Conventional model-driven approaches such as the Weighted Least Squares (WLS) exhibit limited robustness under noisy and sparse measurements, while existing data-driven methods often neglect critical physical constraints inherent to power systems. To address these limitations, this paper proposes a physics-constrained Graph Attention Network (GAT) framework for distribution system state estimation (DSSE) that synergistically integrates data-driven learning with physical domain knowledge. The proposed method comprises three key components: (1) a Gaussian Mixture Model (GMM)-based data augmentation strategy that captures the stochastic characteristics of loads and distributed generation to generate synthetic samples consistent with actual operating distributions; (2) a GAT-based feature extractor with topology-aware admittance matrix embedding that effectively learns spatial dependencies and structural relationships among network nodes; and (3) a physics-constrained loss function that incorporates nodal power and voltage limit penalties to enforce operational feasibility. Comprehensive evaluations on the real-world 141-bus test system demonstrate that the proposed method achieves mean absolute error (MAE) reductions of 52.4% and 45.5% for voltage magnitude and angle estimation, respectively, compared to conventional Graph Convolutional Network (GCN)-based approaches. These results validate the superior accuracy, robustness, and adaptability of the proposed framework under challenging measurement conditions. Full article