Chronic Kidney Disease (CKD) is a chronic disease with a continuously increasing prevalence rate and requires early detection to prevent disease progression. This study aims to optimize the performance of the K-Nearest Neighbor (K-NN) algorithm in the classification of chronic kidney disease through the application of the Random Forest method. The dataset used comes from Kaggle and consists of 400 patient data with 26 clinical attributes. The research stages include data pre-processing in the form of handling missing values, categorical data transformation, feature normalization, and data division into training data and test data with a ratio of 80:20. Random Forest is used as a comparison method and optimization approach, while K-NN is used as the main classification algorithm. Model performance evaluation is carried out using accuracy, precision, recall, F1-score, and confusion matrix metrics. The test results show that the Random Forest algorithm obtains an accuracy value of 98.75%, while the K-NN algorithm produces an accuracy of 96.25%. These results prove that the application of Random Forest is able to optimize the performance of K-NN in the classification of chronic kidney disease effectively.

Continuous-time causal distribution learning with identifiability for brain dynamic effective connectivity inference.

Despite the digital transformation of society, handwritten documents continue to be collected in various investigations, such as fraud investigations and drug trafficking. Recent research highlighted that handwriting offers not only comparative value (i.e. helping address a source question), but it also has the potential to infer a writer's background profile (i.e. helping address other questions than source). This study compared binary logistic regression (BLR) and classification & regression tree (CRT) models to infer a writer's cultural background based on handwriting features. An experimental two-step modelling approach was employed to distinguish Australian, Korean, and Vietnamese writers (N = 196) using categorical handwriting features coded from scanned handwritten texts. The first step was classifying Australian from non-Australian writers, and the second step was further specifically classifying non-Australians into Korean and Vietnamese. The results demonstrated how a two-step modelling framework could be operationalised for early-stage writer classification and highlighted its practical strengths and limitations. The BLR model provided statistical depths for detailed interpretation, and it achieved higher classification accuracy, 93.4% and 97.8% in each step. The CRT model also achieved a high accuracy rate, but lower than BLR with 86.7% and 94.2%. Furthermore, blind test results reflected the practical challenges and strengths of each model. The CRT model correctly classified six out of seven blind specimens while the BLR correctly classified three out of seven blind specimens. Each model presented distinct strengths as the BLR model provided rich detailed statistical outputs, such as odds ratios and significance levels, while the CRT model offered greater accessibility and usability for non-statistical experts. These findings suggest that model selection should balance interpretability, robustness and accuracy. Although more work is required until such models can be applied in practice, this study highlights the potential to extract operational insights from handwriting beyond traditional comparison methods, supporting intelligence-led workflows even when no comparison material is available.

Patient with pluripathology-centered care: The patients' voice and the professionals' vision

High-quality 4D dynamic PET imaging is often compromised by noise, especially in low-count frames, which limits clinical utility and quantitative accuracy. This study proposes a novel spatiotemporal denoising method (SPRINTER) that integrates anatomical priors, self-supervised adaptive principal component analysis (aPCA), and deep learning to enhance image quality and preserve time activity fidelity without relying on ground-truth data. The method combines anatomically guided aPCA-based temporal smoothing with a supervised 3D ResUNet for spatial denoising. The resulting high signal-to-noise ratio, spatially denoised images are iteratively refined using a temporal regularization strategy to enhance contrast. The model was trained using brain scan datasets from 220 participants who were administered one of the following PET/MRI radiotracers: 18F-AV45, 18F-FDG, 15O-HO, 15O-OO, and 11C-PiB for generalizability testing. Evaluations were performed on synthetic simulations with known ground-truth data and real acquired brain scan data. We compared the proposed method against multiple baseline approaches, including conventional reconstruction (OSEM), spatial-only and temporal-only denoising strategies, and two unsupervised reference methods: Non-Local Means (NLM) filtering, a classical denoising approach, and Noise2Void (N2V). These baselines were selected to reflect both conventional and recent unsupervised deep learning denoising paradigms applicable to PET imaging. Performance was assessed using both synthetic simulations with known ground truth and real acquired PET data. In addition to voxel-level image quality metrics, the impact of denoising on downstream quantitative analysis was evaluated using Ki parametric imaging derived from simulation data. This enabled direct assessment of tracer kinetic estimation accuracy across different denoising strategies. We compared SPRINTER with OSEM, spatial-only, temporal-only, and two existing unsupervised denoising approaches, including NLM and Noise2Void. Across both simulation and acquired datasets, SPRINTER significantly outperformed all comparison methods (p < 0.05, ANOVA with Bonferroni multiple comparison corrections). The largest gains were observed for the noisiest data using 15O-HO and 15O-OO tracers, where SPRINTER achieved marked SNR improvements in acquired data (e.g., 15O-HO: 3.92 ± 1.28 vs. 2.68 ± 1.24; p = 0.096; 15O-OO: 3.71 ± 1.79 vs. 2.53 ± 1.15 for NLM; p = 0.082). These improvements were consistently superior to those obtained with NLM and Noise2Void, which showed either spatial blurring or limited performance in low-count frames. In simulation studies, SPRINTER significantly reduced voxel-wise reconstruction error compared to all baselines (NRMSE: 0.07 ± 0.04 and 0.09 ± 0.05 vs. 0.33 ± 0.08 to 0.07 and 0.37 ± 0.31 for NLM; p < 0.0001), while also outperforming NLM and Noise2Void, which exhibited higher residual error and reduced temporal consistency. Importantly, contrast was preserved and enhanced, with improved CNR particularly in 1⁸F-FDG and 11C-PiB (e.g., 1⁸F-FDG: 0.37 ± 0.33 vs. 0.18 ± 0.19; p < 0.0001; 11C-PiB: 0.54 ± 0.08 vs. 0.41 ± 0.12; p < 0.001), indicating effective denoising without loss of biologically relevant signal. While NLM and spatial-only methods achieved comparable SNR improvements, this was largely driven by oversmoothing. In contrast, with a similar level of SNR enhancement, the incorporation of temporal information further improved structural fidelity, as reflected by higher SSIM values across all tracers in simulation data (e.g., 1⁸F-AV45: 0.73 ± 0.14 vs. 0.17 ± 0.08 for NLM; p < 0.0001). This study introduces a robust, self-supervised spatiotemporal denoising method for 4D dynamic PET imaging of the brain. SPRINTER spatiotemporal denoising leverages anatomical guidance and temporal dynamics to enhance spatial clarity and temporal consistency. Its radiotracer-agnostic design and rigorous self-supervision make it well-suited for clinical applications where high-quality reference data are unavailable.

Modern business operations take place under conditions of intense globalisation, increased competition, and constant changes in international financial markets. In such an environment, business financing is one of the key factors for sustainable growth and long-term stability. Aligning financial decisions with internationally accepted accounting principles, particularly with the International Financial Reporting Standards (IFRS), is of special importance, as they ensure the transparency, comparability, and reliability of financial information. The subject of this paper is the analysis of business financing in the international economic environment, with a special focus on the application of accounting principles in the financial decision-making process. The aim of the paper is to determine the role of accounting standards in securing quality sources of financing, reducing financial risks, and strengthening the trust of investors and creditors. The paper is based on an analysis of relevant domestic and foreign literature, as well as the application of scientific methods of analysis, synthesis, and comparison. The research findings indicate that the consistent application of international accounting principles positively impacts the efficiency of business financing and a company's competitive position in the global market.

BackgroundFew pregnant women meet activity guidelines, and about half experience pelvic girdle pain (PGP), with 10% developing chronic symptoms. PGP is multifactorial and tailored physical activity and exercise can reduce pain. A web-based self-care program, Women-In-Motion (WIM), was developed to support physical activity during pregnancy and help prevent and manage PGP.AimThe study aim was to explore pregnant women’s experiences with and perceptions of WIM for managing physical activity and PGP to optimize quality of life during pregnancy. A second aim was to use the results for improvements of WIM.MethodA qualitative approach was employed using focus groups, conducted digitally or in hybrid formats. Pregnant women, gestational weeks <30, were invited. The participants had access to the program one to five weeks prior to focus groups. All sessions were recorded, transcribed, and analysed using a combination of Krueger and Casey’s constant comparison method and Graneheim and Lundman’s inductive content analysis.ResultsFour focus groups were conducted with pregnant women (n=17), representing variation in parity, exercise habits, and experiences of PGP. The analysis resulted in an overarching theme: “Moving confidently through pregnancy”. WIM was seen as helping reduce barriers to physical activity while providing biopsychosocial pain insights. Varying support needs indicate more individualized approaches.ConclusionOverall, participants experienced the WIM program to enhance their confidence, and their shared perceptions of diverse needs will inform program revisions.

Scientifically understanding the trade-off and synergy relationship among ecosystem services of cultivated land is of great significance for cultivated land protection and the refined management of ecosystem services. This study quantified four typical cultivated land ecosystem services in the Yangtze River Delta from 2000 to 2020 through models such as InVEST and MaxEnt. The difference comparison method was adopted to identify the trade-off and synergy relationships among ecosystem services， and the geographical weighted logistic regression was used to reveal the influence of different influencing factors on the trade-off and synergy relationships. Finally， the cultivated land in the study area was zoned and optimized with the aid of the production-possibility frontiers. The results showed that： ① During the research period， grain production presented a spatial distribution pattern of "high in the north and low in the south，" while the spatial distribution of carbon sequestration and habitat quality was opposite to that of grain production. The high-value areas of recreation service gradually shifted from the northern part of the Yangtze River Delta to the central and southern parts. Between 2000 and 2020， grain production increased significantly by 33.97%， while other ecosystem services declined slightly to varying degrees. ② Overall， carbon sequestration-grain production and habitat quality-recreation service showed a synergistic relationship， while other ecosystem services showed a trade-off relationship. The trade-off and synergy relationship among ecosystem services had obvious spatial heterogeneity. ③ The synergy relationship of ecosystem service trade-off mainly showed a significant negative response to precipitation and mainly showed a significant positive response to the urbanization rate and population density. ④ Based on the trade-off intensity of ecosystem services， the cultivated land in the study area was divided into the vulnerable area， the single dominant trade-off area， the balanced development area， and the coordinated development area. Among them， the overall trade-off intensity of the vulnerable area was relatively high， accounting for 24.92% of the study area， and it is a key area for future ecological restoration and optimization improvement. This article aims to provide a scientific basis for the refined management of cultivated land in the Yangtze River Delta and offer a reference for the optimization of the spatial pattern.

ABSTRACT A construction progress prediction model based on BIM and ABC-SVM is proposed to predict and control the construction progress. Firstly, a construction progress influencing factor index system consisting of 24 secondary indicators was constructed from 7 dimensions including personnel, machinery, management, and environment; Furthermore, by integrating heterogeneous data from multiple sources through BIM technology, effective extraction and fusion of construction information can be achieved based on information entropy theory; Finally, the artificial bee colony (ABC) algorithm was employed to automatically optimize the key parameters of the SVM, and an ABC-SVM prediction model was constructed. The experimental results show that the average absolute percentage error (MAPE) of the model is 5.82% (95% CI: [5.08%, 6.56%]), and the coefficient of determination reaches 0.82, which is significantly better than the comparison method; Sensitivity analysis identified 8 highly sensitive factors, including mechanical equipment failure (MAPE change rate +2.5%) and worker proficiency (+2.3%); The ablation experiment verified the key role of BIM data fusion and ABC parameter optimization in improving prediction accuracy. This model provides a reliable progress prediction tool for project managers and has important practical value in improving the level of construction progress management.

Deep learning (DL) methods have demonstrated promising performance in online motor unit (MU) identification from high-density surface electromyogram (HD-sEMG). However, its dependency on larger amounts of data limits practicability. To address this issue, a novel few-shot learning method enhanced by sample reconstruction strategy is presented for online MU identification. In this method, a spatio-temporal neural network was first pre-trained based on the simulated HD-sEMG data and MU spike trains, endowing it with initial representational capabilities for MU features. Then, an innovative sample reconstruction strategy was employed to generate physiologically interpretable synthetic samples for model fine-tuning with minimal experimental data. These samples were intended to enhance the model's ability to characterize the spatiotemporal features of MUAP waveforms, thereby improving the online MU identification performance. Experimental HD-sEMG signals were collected from the abductor pollicis brevis muscles of ten subjects using an 8 × 8 electrode array. The results demonstrated that the proposed method can achieve a matching rate of approximately 93% in online MU identification stage, with only 6s of experimental data for offline model fine-tuning, significantly outperforming the comparison methods. This work provides a novel solution for efficient real-time MU identification, and the findings are expected to advance the widespread application of DL-based real-time HD-sEMG decomposition in developing advanced neural-machine interfaces towards robotic motor control and rehabilitation medicine.

Can we normalize surface electromyography in patients with spasticity of the upper limb?

Neutron-gamma discrimination based on STFT-DFF model and FPGA implementation.

A Rényi divergence-oriented multi-attributive border approximation area comparison method within a circular intuitionistic fuzzy framework for enhanced decision analytics

The Transportation Problem (TP) is an optimization model that distributes goods from multiple supply points to various demand points at minimal cost. A crucial step in solving TP is generating an Initial Basic Feasible Solution (IBFS), which affects the efficiency of reaching the optimal solution. However, existing IBFS methods such as Supply Selection Method (SSM), Vogel's Approximation Method (VAM), Bilqis-Chastine-Erma (BCE). Juman-Hoque Method (JHM), and Total Opportunity Cost Matrix-Minimal Total (TOCM-MT) are not always reliable in producing low-cost solutions. This study proposes the Rihan-Bilqis-Saikhu Method (RBSM). This heuristic modifies SSM by considering the total cost-supply of each cell and adjusting how surplus allocations are shifted to rows with shortages. The method was evaluated using 42 test cases, including 32 published test cases, 5 randomly generated test cases, and 5 real test cases from XYZ company. Results show that RBSM outperformed all comparison methods, achieving the optimal solution in 36 out of 42 cases (85.71 % accuracy) and producing the lowest average deviation (0.58 %) from the optimal cost. The contributions of RBSM are:•Integration of total cost-supply into allocation decisions.•Refined reallocation rules between surplus rows and rows with shortages.•Consistent accuracy and efficiency across diverse test cases.

ABSTRACT Multispectral and panchromatic image fusion (also known as pansharpening) is widely used in various fields such as vegetation coverage assessment and land cover classification. Existing pansharpening networks typically extract global and local features through parallel dual-branch architectures and achieve feature interaction via symmetric stage-wise fusion. However, this paradigm lacks a causal order between global context and local details, often leading to feature redundancy and spectral-spatial distortion. To address this issue, this paper proposes a novel Global – Local Feature Alternation Pansharpening Network (GLFAPNet). The network adopts a single-stream architecture composed of multiple sequentially stacked Global–Local Feature Alternation (GLFA) modules, strictly following a ‘global first, local later’ execution order. Each GLFA module mainly consists of a Swin Transformer (ST) module and a multi-scale parallel convolution (MPC) module, where the global context prior guides the refinement of local details, effectively suppressing spectral distortion while preserving the integrity of ground objects. The network adaptively determines the optimal number of stacked GLFA modules for different satellite datasets based on validation loss, and through quantitative trade-off analysis of parameter count, FLOPs and inference time, it is verified that this depth selection strategy achieves an optimal balance between efficiency and performance. Qualitative and quantitative experiments on GF-1, WorldView-4 and QuickBird datasets demonstrate that the proposed method outperforms comparison methods in both visual image quality and six quantitative evaluation metrics. Finally, in the normalized difference vegetation index (NDVI) application experiment, the proposed method achieves the lowest RMSE (0.0267) and MAE (0.0182), which are 12.7% and 14.2% lower than those of the second-best method, respectively. This improvement effectively enhances the accuracy of vegetation coverage retrieval, demonstrating strong competitiveness and broad application prospects. The code link is available at https://github.com/RSIDEA-ECUT/GLFAPNet.

Muda and Yangxuan recommended a ridge-calibrated test statistic for controlling Type I error inflation in confirmatory factor analysis under non-normality. Although improving finite-sample inference is an important goal, their empirical evaluation is undermined by incorrectly implemented benchmark statistics, misattributed comparison methods, and a simulation design restricted to asymptotically robust conditions. Using corrected code, we reanalyze the original conditions and replace the misattributed benchmarks with the penalized eigenvalue procedures pEBA 4 RLS and pOLS 2 RLS . Under the original conditions, the best-performing procedures are the ridge-calibrated TCsFCr statistic and the penalized eigenvalue methods. However, under additional non-asymptotically robust conditions, including high-dimensional models, pEBA 4 RLS provides the most reliable Type I error control and outperforms the ridge-calibrated competitors.

Dynapenia, defined as reduced muscle strength despite preserved muscle mass, is increasingly being recognized alongside sarcopenia in older adults. Clinical differences between dynapenia and sarcopenia in hospitalized cardiovascular disease (CVD) patients remain unclear. This study aimed to compare the clinical characteristics among Normal, Dynapenia, and Sarcopenia phenotypes.This prospective, single-center cohort study included patients admitted to the cardiology ward at Seirei Hamamatsu General Hospital (July 2024-September 2025) who received physical therapy and completed body composition assessment at discharge. The patients were divided into Normal, Dynapenia, and Sarcopenia groups classified using a previously reported flowchart and cutoff values for grip strength and skeletal muscle mass index (SMI) based on the Asian Working Group for Sarcopenia 2025 criteria. Three-group comparisons were conducted using multiple comparison methods, and no adjustment was made due to the exploratory nature of the analyses. Adjusted comparisons were conducted using analysis of covariance controlling for age, sex, B-type natriuretic peptide, and SMI.Among the 316 patients, 133 (42.1%) were Normal, 31 (9.8%) Dynapenia, and 152 (48.1%) Sarcopenia. Unadjusted comparisons showed graded differences across the 3 groups for physical function, cognitive function, and activities of daily living, with the decreasing order being Normal > Dynapenia > Sarcopenia. After adjustment, differences between the Dynapenia and Sarcopenia groups were no longer significant, whereas Dynapenia remained lower than Normal for grip strength, walking speed, and phase angle.Dynapenia may represent a distinct phenotype with preserved muscle mass but reduced strength, influenced by comorbidities and systemic CVD effects. Identifying dynapenia could support phenotype-specific rehabilitation strategies, although further studies are needed to clarify the underlying mechanisms.

The article examines theoretical and methodological foundations of integrating cost management into the enterprise Balanced Scorecard system. The subject of the research is the development of a strategically oriented cost management system based on the use of financial statements and management reporting indicators. The study addresses the need to improve the effectiveness of cost management under conditions of limited information support, instability of the external environment, and the increasing role of strategic management tools in ensuring enterprise performance. The purpose of the study is to develop a methodological approach to integrating cost management into the Balanced Scorecard of an enterprise. The methodology includes a systemic approach, methods of economic analysis, comparison, generalization, and logical modeling. The analysis is based on financial statements and management reports of JSC “Ukrainian Energy Machines”. The study proposes a methodological approach to integrating cost management into the Balanced Scorecard system. This approach involves structuring cost indicators according to four perspectives: financial, customer, internal business processes, and learning and growth. A model of integrating cost management into the system of strategic performance indicators of the enterprise has been developed, which makes it possible to establish cause-and-effect relationships between resource use, costs and performance outcomes. The findings can be applied in the practical activities of enterprises in forming a strategically oriented cost management system based on financial and managerial data. The study shows that the proposed approach allows transforming financial reporting data into a system of strategic cost management indicators and improving decision-making quality. The results contribute to aligning the enterprise cost policy with its strategic development objectives and improving the efficiency of resource utilization.

While family health is widely recognized as fundamental to college students' psychological development, the specific associative patterns through which different family health dimensions relate to humanistic care ability-and how these patterns differ by gender-remain incompletely mapped. This study employed cross-sectional network analysis and network comparison methods to examine 2,357 Chinese college students (ages 17-23; 1,325 females) who completed the Family Health Scale-Short Form and Humanistic Care Ability Questionnaire. Gaussian Graphical Models with LASSO regularization (EBIC, γ = 0.5) revealed three key findings. First, family external social support emerged as the node with the highest bridge expected influence in the observed network, statistically connecting family health to humanistic care dimensions, particularly trust and hope. This pattern is consistent with predictions derived from social capital theory but should not be interpreted as evidence of a developmental mechanism given the cross-sectional design. Second, a small negative association was observed between family health resources and trust (edge weight = -0.07), the interpretation of which is constrained by the operational content of the resource subscale (which assesses access to practical and healthcare resources rather than affluence) and by the small effect size. Third, patience and humility exhibited the highest network centrality, functioning as the most centrally connected nodes in the observed network; following recent methodological cautions, we do not interpret centrality as evidence of causal leverage. Network comparison tests revealed substantial overall gender invariance: global network structure, global expected influence, and node centrality did not differ significantly between male and female networks. Network comparison tests revealed only two small local edge differences and one bridge-centrality difference (all small in magnitude); these local differences are reported as exploratory. These cross-sectional associative patterns generate hypotheses regarding family-care linkages that future longitudinal and experimental research should test before being translated into intervention design.

This study evaluated the real-world effectiveness of trastuzumab deruxtecan (T-DXd) in patients with breast cancer brain metastases (BCBM), generating data from populations underrepresented in clinical trials. Patients with BCBM treated with T-DXd across seven U.S. health systems from 2019 to 2023 were retrospectively identified. HER2 status was classified as HER2-positive (IHC 3 + or IHC 2+/FISH+) or HER2-low (IHC 1 + or IHC 2+/FISH-). Overall survival (OS) was the primary outcome and was evaluated using Kaplan-Meier and log-rank methods for unadjusted comparisons followed by multivariable Cox regression. A total of 111 patients were included (HER2-positive, n = 77; HER2-low, n = 34). HER2-low tumors were more often ER-positive than HER2-positive tumors (79.4% vs. 56.6%, respectively). Overall, 46.8%of patients had received ≥ 6 prior systemic therapy lines. In unadjusted analyses, greater prior chemotherapy exposure was associated with shorter OS (median OS not reached for 0 lines, 35.2 months for 1-2 lines, and 22.1 months for ≥ 3 lines). Median OS was longer in HER2-positive than HER2-low disease (35.2 vs. 12.8 months, respectively). In multivariable analysis, receipt of ≥ 3 prior chemotherapy lines was associated with shorter OS (aHR 9.95, 95% CI 1.20-82.53; p = 0.033), although this finding should be interpreted cautiously given the small sample size, wide confidence interval, and pooled analysis across HER2 subgroups. In this real-world cohort of patients with BCBM treated with T-DXd, HER2-positive disease was associated with longer unadjusted survival than HER2-low disease.Greater prior chemotherapy exposure may reflect poorer underlying prognosis and more heavily pretreated disease.