Search Results (327)

The Kolmogorov–Arnold representation theorem states that any continuous multivariable function can be exactly represented as a finite superposition of continuous single-variable functions. Subsequent simplifications of this representation involve expressing these functions as parameterized sums of a smaller number of unique monotonic functions. Kolmogorov–Arnold Networks (KANs) have been recently proposed as an alternative to multilayer perceptrons. KANs feature learnable nonlinear activations applied directly to input values, modeled as weighted sums of basis spline functions. This approach replaces the linear transformations and sigmoidal post-activations used in traditional perceptrons. In this work, we propose a novel KAN variant by replacing both the inner and outer functions in the Kolmogorov–Arnold representation with weighted sinusoidal functions of learnable frequencies. We particularly fix the phases of the sinusoidal activations to linearly spaced constant values and provide a proof of their theoretical validity. We also conduct numerical experiments to evaluate its performance on a range of multivariable functions, comparing it with fixed-frequency Fourier transform methods, basis spline KANs (B-SplineKANs), and multilayer perceptrons (MLPs). We show that it outperforms the fixed-frequency Fourier transform B-SplineKAN and achieves comparable performance to MLP. Full article

Background and Objectives: This study aimed to evaluate the predictive value of systemic inflammatory response markers—namely, the Systemic Inflammatory Response Index (SIRI), Aggregate Index of Systemic Inflammation (AISI), and Monocyte-to-Lymphocyte Ratio (MLR)—in determining the occurrence of major complications following radical cystectomy. Materials and Methods: A retrospective analysis was conducted on 200 patients who underwent open radical cystectomy with ileal conduit diversion. Demographic, clinical, and laboratory variables, including albumin, creatinine, eGFR, smoking, and ASA score, were collected. SIRI, AISI, and MLR were calculated from preoperative blood counts. Major complications and their subtypes (infectious, wound, cardiopulmonary, thrombotic, and anastomotic) were adjudicated independently. Statistical analyses included multivariable logistic regression, ROC curves, calibration (Hosmer–Lemeshow, intercept, slope, and plots), bootstrap resampling (B = 2000), linearity checks (restricted cubic splines and Box–Tidwell), incremental value metrics (ΔAUC, IDI, and NRI), and decision-curve analysis (DCA). Results: Major complications occurred in 57 patients (28.5%). SIRI values were significantly higher in patients with major complications (median 2.12 vs. 1.63, p = 0.006), whereas AISI and MLR did not differ. SIRI remained an independent predictor in multivariable analysis (OR 1.37, 95% CI 1.01–1.86, p = 0.045). An AUC of 0.624 (95% CI 0.538–0.709) with a negative predictive value of 83.3% was observed for SIRI. The baseline clinical model yielded an AUC of 0.648, and an AUC of 0.672 was obtained when SIRI was added (ΔAUC = +0.024, 95% CI −0.022–0.071, p = 0.16). Calibration was excellent (intercept = 0.07, slope = 1.08), and superior net benefit was demonstrated for the SIRI-augmented model within threshold probabilities of 0.15–0.45 in DCA. A statistically significant improvement in IDI (0.024, p = 0.024) was identified, while NRI was positive but not significant. Subtype analyses indicated that the strongest associations of SIRI were with infectious and wound complications. Conclusions: SIRI was found to be an independent predictor of major complications after open radical cystectomy. Although gains in discrimination were modest, incremental analyses demonstrated improved calibration and net clinical benefit when SIRI was incorporated into a clinical model. External validation is required before translation into clinical practice. Full article

This study presents a comparative analysis of wave buoy analogy models for sea state estimation. A nonparametric, response amplitude operator-based model is introduced as a physics-based approach, while a convolutional neural network is adopted as a machine learning approach. Using time-domain simulation data of wave-induced ship motions under various operating conditions, the accuracy and reliability of each model’s estimation are evaluated. The sensitivity of the physics-based model to operating conditions is examined, along with optimization strategies such as hyperparameter tuning. In particular, regularization techniques based on bilinear and B-spline surface fitting are applied to the nonparametric model, and the effects of interpolation techniques on model performance are assessed. For the machine learning model, a parametric study is conducted to determine input data types and formats, including time series and spectral representations, as well as the required length of the time window and dataset volume. Finally, the feasibility of the proposed neural network in estimating not only sea state parameters but also loading and navigational information, such as ship speed and GM, is discussed. Full article

Accurate identification of mechanical excitation forces is of great significance for the control of ship radiated noise and structural design. Currently, the identification of excitation forces mostly relies on indirect calculations, which suffer from ill-conditioned problems. Regularization correction is one of the main means to solve this problem. Although regularization methods have been widely developed, their application in the field of ships is relatively rare. Currently, the commonly used methods are truncation singular values and Givonov regularization methods. This paper starts from the practical application of ships and addresses the problem of poor correction effect of traditional regularization methods. Two optimized regularization methods, quasi-optimal discriminant criterion and B-spline interpolation function method, are proposed. These methods are verified through simulations and experiments. The results of the scaled model experiments show that compared with using the L-curve alone, the Q-O method reduces the regularization error by 29%, while the BL curve improves the robustness by 38% under a 15 dB noise condition. Full article

This study presents a morphing Non-Uniform Rational B-Spline (NURBS) optimization method for enhancing sports car aerodynamics, with performance evaluation conducted in the vehicle’s symmetry plane. The morphing approach enables precise, smooth deformations of rear-end and spoiler geometries while preserving shape continuity, allowing controlled aerodynamic modifications suitable for comparative analysis. Flow simulations were carried out in ANSYS Fluent 2022 using the Reynolds-Averaged Navier–Stokes (RANS) equations with the standard k-ε turbulence model, selected for its stability and accuracy in predicting boundary-layer evolution, wake behavior, and flow separation in external automotive flows. Three configurations were assessed: the baseline model, a spoiler-equipped version, and two NURBS-morphed designs. The symmetry-plane evaluation ensured bilateral balance across all variants, enabling direct comparison of drag and lift performance. The results show that the proposed morphing strategy achieved notable lift reduction and favorable drag-to-lift ratios while maintaining manufacturability. The findings demonstrate that combining NURBS-based morphing with symmetry-plane aerodynamic assessment offers an efficient, reliable framework for vehicle aerodynamic optimization, bridging geometric flexibility with robust computational evaluation. Full article

Power amplifier behavioral modeling is an important technique for efficient and accurate digital predistortion, but conventional models fail to generalize when applied across varying carrier frequencies. This work addresses the carrier-frequency generalization by proposing a parameterized memory polynomial (PMP) modeling approach. The method involves extracting memory polynomial models at multiple carrier frequencies and interpolating their coefficients using spline interpolation, resulting in a single model capable of operating across a wide carrier-frequency band. Experimental validation was conducted using measured input–output PA responses over the 3.3–3.8 GHz range. Results obtained show that PMP built on three carrier frequencies achieves up to 9 dB average NMSE improvement compared to the fixed-coefficient MP model. The proposed model nearly matches the accuracy of the MP model at the entire measured range. The overall accuracy depends on the combination of the introduced interpolation error and the discrepancy between the initial MP model fitting errors. The proposed method offers a practical solution for PA modeling in systems requiring fast frequency agility, such as carrier aggregation and dynamic spectrum access, eliminating the need for model retraining at each operating frequency. Full article

Micro-expressions, characterized by brief and subtle facial muscle movements, are essential for conveying nuanced emotions in digital humans, yet existing rendering techniques often produce rigid or emotionally monotonous animations due to the inadequate modeling of temporal dynamics and action unit interdependencies. This paper proposes a graph-driven framework for micro-expression rendering that generates emotionally diverse and lifelike expressions. We employ a 3D-ResNet-18 backbone network to perform joint spatio-temporal feature extraction from facial video sequences, enhancing sensitivity to transient motion cues. Action units (AUs) are modeled as nodes in a symmetric graph, with edge weights derived from empirical co-occurrence probabilities and processed via a graph convolutional network to capture structural dependencies and symmetric interactions. This symmetry is justified by the inherent bilateral nature of human facial anatomy, where AU relationships are based on co-occurrence and facial anatomy analysis (as per the FACS), which are typically undirected and symmetric. Human faces are symmetric, and such relationships align with the design of classic spectral GCNs for undirected graphs, assuming that adjacency matrices are symmetric to model non-directional co-occurrences effectively. Predicted AU activations and timestamps are interpolated into continuous motion curves using B-spline functions and mapped to skeletal controls within a real-time animation pipeline (Unreal Engine). Experiments on the CASME II dataset demonstrate superior performance, achieving an F1-score of 77.93% and an accuracy of 84.80% (k-fold cross-validation, k = 5), outperforming baselines in temporal segmentation. Subjective evaluations confirm that the rendered digital human exhibits improvements in perceptual clarity, naturalness, and realism. This approach bridges micro-expression recognition and high-fidelity facial animation, enabling more expressive virtual interactions through curve extraction from AU values and timestamps. Full article

This work presents a generative design algorithm for the semi-automatic reconstruction of sweepable surfaces from point clouds obtained through three-dimensional scanning. The proposed algorithm enables, starting from a 3D acquisition dataset, the correct automatic orientation of the mesh, the selection of a suitable cutting edge, and the specification of the number of transversal sections for an effective 3D model reconstruction. Additionally, it suggests a maximum number of points to be used for reconstructing the sectional curves. The mesh reconstruction is performed through a lofting operation, resulting in a non-uniform rational B-spline (NURBS) surface. The algorithm has been applied to a case study involving the front wing surface of a foil from the Olympic class iQFoil, which has recently garnered significant attention from researchers in the field of performance analysis. The obtained reconstructed surface exhibits very low deviation values when compared to the original mesh. This demonstrates the reliability of the results obtained with the proposed approach, which provides sufficient accuracy and is obtained in a considerably shorter time compared to the traditional manual reconstruction approach, enabling the reconstruction of a 3D model in just a few semi-automatic steps, ready for subsequent numerical analyses if needed. Full article

Generative Artificial Intelligence (GenAI) is widely recognized for its profound impact on labor market demand, supply, and skill dynamics. However, due to its transformative nature, GenAI increasingly overlaps with traditional AI roles, blurring boundaries and intensifying the need to reassess workforce competencies. To address this challenge, this paper introduces KANVAS (Kolmogorov–Arnold Network Versatile Algorithmic Solution)—a framework based on Kolmogorov–Arnold Networks (KANs), which utilize B-spline-based, compact, and interpretable neural units—to distinguish between traditional AI roles and emerging GenAI-related positions. The aim of the study is to develop a reliable and interpretable labor market classification system that differentiates these roles using explainable machine learning. Unlike prior studies that emphasize predictive performance, our work is the first to employ KANs as an explanatory tool for labor classification, to reveal how GenAI-related and European Skills, Competences, Qualifications, and Occupations (ESCO)-aligned skills differentially contribute to distinguishing modern from traditional AI job roles. Using raw job vacancy data from two labor market platforms, KANVAS implements a hybrid pipeline combining a state-of-the-art Large Language Model (LLM) with Explainable AI (XAI) techniques, including Shapley Additive Explanations (SHAP), to enhance model transparency. The framework achieves approximately 80% classification consistency between traditional and GenAI-aligned roles, while also identifying the most influential skills contributing to each category. Our findings indicate that GenAI positions prioritize competencies such as prompt engineering and LLM integration, whereas traditional roles emphasize statistical modeling and legacy toolkits. By surfacing these distinctions, the framework offers actionable insights for curriculum design, targeted reskilling programs, and workforce policy development. Overall, KANVAS contributes a novel, interpretable approach to understanding how GenAI reshapes job roles and skill requirements in a rapidly evolving labor market. Finally, the open-source implementation of KANVAS is flexible and well-suited for HR managers and relevant stakeholders. Full article

Background: Medically unexplained oral symptoms/syndromes (MUOS), such as Burning Mouth Syndrome and Persistent Idiopathic Facial Pain, present significant management challenges due to the lack of standardized treatments and high-level evidence. While pharmacotherapy is often employed, real-world data on treatment adherence—a pragmatic proxy for effectiveness and tolerability—remain sparse, especially in Japan. This study aimed to describe the real-world prescribing patterns of antidepressants and dopamine receptor partial agonists (DPAs) for MUOS and retrospectively investigate their association with treatment continuation. Methods: This retrospective observational study analyzed data from patients initiating pharmacotherapy for MUOS at a specialized clinic in Japan (April 2021–March 2023). We used Cox proportional hazards models to evaluate treatment continuation for amitriptyline monotherapy and antidepressant–aripiprazole adjunctive therapy. The primary outcome was the time to discontinuation. Dosage effects were modeled using B-splines to capture nonlinearity. Results: Among 702 MUOS patients who started pharmacotherapy, 493 received amitriptyline as the first prescription, and 108 received aripiprazole as an adjunctive therapy. For amitriptyline monotherapy, a nonlinear relationship was observed between dosage and discontinuation risk, with a relatively lower hazard around 25 mg/day across age groups. In the antidepressant–aripiprazole adjunctive group, the overall hazard ratio for discontinuation was higher (HR = 4.75, p < 0.0005) compared to non-adjunctive therapy, likely due to indication bias reflecting more treatment-resistant cases. However, within the aripiprazole adjunctive group, a U-shaped relationship was identified between maximum aripiprazole dosage and discontinuation risk, with the lowest hazard (HR ≈ 0.30) observed at approximately 1.7–1.8 mg/day. Mild side effects such as drowsiness, dry mouth, constipation, tremor, insomnia, and weight gain were noted, but no severe adverse events occurred. Conclusions: This real-world data analysis suggests specific dosage ranges (amitriptyline ≈ 25 mg/day; aripiprazole augmentation ≈ 1.7–1.8 mg/day) are associated with longer treatment continuation in MUOS patients. Treatment continuation reflects a crucial balance between symptom relief and tolerability, essential for managing these chronic conditions. It is critical to emphasize that these findings are descriptive and observational, derived from a specialized setting, and do not constitute prescriptive recommendations. They highlight the importance of individualized dosing. Definitive evidence-based strategies require validation through prospective randomized controlled trials. Full article

To improve the dynamic performance of parallel robots in multi-dimensional space, a novel trajectory planning method of space discretization for parallel robots is proposed. First, the kinematic model of the 5PUS-RPUR parallel robot is established. Then, the normalized Jacobian condition number is obtained via the variable weighting matrix method, and is used as the performance metric of path optimization. The weighted sum method is utilized to construct a composite objective function for the trajectory that incorporates travel time and acceleration fluctuations. Next, the position space between the start and end points is discretized, and the robot pose space based on the position points is analyzed via the search method. The discrete pose point weights are assigned according to the condition number. Dijkstra’s algorithm is used to find the path with the minimum condition number. The trajectory optimization model is established by fitting the discrete path with a B-spline curve and optimized via genetic algorithm. Finally, comparative numerical simulations validate the proposed method, which reduces actuator RMS displacement difference by up to 32.9% and acceleration fluctuation by up to 25.6% against state-of-the-art techniques, yielding superior motion smoothness and dynamic stability. Full article

High-precision Sea Surface Temperature (SST) prediction is critical for understanding ocean–atmosphere interactions and climate anomaly monitoring. We propose GRU_EKAN, a novel hybrid model where Gated Recurrent Units (GRUs) capture temporal dependencies and the Enhanced Kolmogorov–Arnold Network (EKAN) models complex feature interactions between SST and multivariate ocean predictors. This study integrates GRU with EKAN, using B-spline-parameterized activation functions to model high-dimensional nonlinear relationships between multiple ocean variables (including sea water potential temperature at the sea floor, ocean mixed layer thickness defined by sigma theta, sea water salinity, current velocities, and sea surface height) and SST. L2 regularization addresses multicollinearity among predictors. Experiments were conducted at 25 South China Sea sites using 2011–2021 CMEMS data. The results show that GRU_EKAN achieves a superior mean R² of 0.85, outperforming LSTM_EKAN, GRU, and LSTM by 5%, 25%, and 23%, respectively. Its average RMSE (0.90 °C), MAE (0.76 °C), and MSE (0.80 °C²) represent reductions of 31.3%, 27.0%, and 53.2% compared to GRU. The model also exhibits exceptional stability and minimal Weighted Quality Evaluation Index (WQE) fluctuation. During the 2019–2020 temperature anomaly events, GRU_EKAN predictions aligned closest with observations and captured abrupt trend shifts earliest. This model provides a robust tool for high-precision SST forecasting in the South China Sea, supporting marine heatwave warnings. Full article

In many practical applications, data collected over time often exhibit autocorrelation, which, if unaccounted for, can lead to biased or misleading statistical inferences. To address this issue, we propose a varying-coefficient additive model for density-valued responses, incorporating a functional auto-regressive (FAR) error process to capture serial dependence. Our estimation procedure consists of three main steps, utilizing spline-based methods after mapping density functions into a linear space via the log-quantile density transformation. First, we obtain initial estimates of the bivariate varying-coefficient functions using a B-spline series approximation. Second, we estimate the error process from the residuals using spline smoothing techniques. Finally, we refine the estimates of the additive components by adjusting for the estimated error process. We establish theoretical properties of the proposed method, including convergence rates and asymptotic behavior. The effectiveness of our approach is further demonstrated through simulation studies and applications to real-world data. Full article

Accurate estimation of tree diameter at breast height (DBH) from LiDAR point clouds is essential for forest inventory, biomass assessment, and ecological monitoring. This paper presents a perimeter-based DBH estimation framework that achieves competitive accuracy against geometric fitting methods across three datasets. The proposed approach partitions the trunk cross-section into angular sectors and employs Gaussian Mixture Models (GMMs) to identify representative boundary points in each sector, weighted by radial proximity and statistical confidence. To handle occlusion and partial scans, missing sectors are reconstructed using symmetry-aware proxy generation. The final perimeter is modeled via either convex hull or B-spline interpolation, from which DBH is derived. Extensive experiments were conducted on two public TreeScope datasets and a custom mobile LiDAR dataset. Compared to the Density-Based Clustering Ring Extraction (DBCRE) baseline, our method reduced RMSE by 22.7% on UCM-0523M (from 2.60 to 2.01 cm), 34.3% on VAT-0723M (from 3.50 to 2.30 cm), and 29.6% on the Custom Dataset (from 2.16 to 1.52 cm). Ablation studies confirmed the individual and synergistic contributions of GMM clustering, radial consistency filtering, and proxy synthesis. Overall, the method provides a flexible alternative that reduces dependence on strict geometric assumptions, offering improved DBH estimation performance with moderate occlusion and incomplete, uneven boundary coverage. Full article

We propose a novel deep learning framework for counterfactual inference on the COMPAS dataset, utilizing a multi-task CNN-LSTM architecture. The model jointly predicts multiple outcome types: (i) count outcomes with zero inflation, modeled using zero-inflated Poisson (ZIP), zero-inflated negative binomial (ZINB), and negative binomial (NB) distributions; (ii) time-to-event outcomes, modeled via the Cox proportional hazards model. To effectively leverage the structure in high-dimensional tabular data, we integrate functional data analysis (FDA) techniques by transforming covariates into smooth functional representations using B-spline basis expansions. Specifically, we construct a pseudo-temporal index over predictor variables and fit basis expansions to each subject’s feature vector, yielding a low-dimensional set of coefficients that preserve smooth variation while reducing noise. This functional representation enables the CNN-LSTM model to capture both local and global temporal patterns in the data, including treatment-covariate interactions. Our approach estimates both population-average and individual-level treatment effects (ATE and CATE) for each outcome and evaluates predictive performance using metrics such as Poisson deviance, root mean squared error (RMSE), and the concordance index (C-index). Statistical inference on treatment effects is supported via bootstrap-based confidence intervals and hypothesis testing. Overall, this comprehensive framework facilitates flexible modeling of heterogeneous treatment effects in structured, high-dimensional data, advancing causal inference methodologies in criminal justice and related domains. Full article