1663 papers
This study proposes an explainable flood prediction framework that integrates GIS, a hybrid LSTM-XGBoost deep learning model, and XAI techniques (SHAP and LIME) to deliver accurate, transparent, and policy-oriented decision support for climate-resilient disaster management.
This study demonstrates that a cost-effective, rule-based Digital Twin architecture using discrete-event simulation can robustly predict RoRo vessel service times with high accuracy, proving that significant decision-making value can be achieved without the need for expensive, high-fidelity sensor infrastructure.
This study establishes a comprehensive statistical benchmarking framework to evaluate eight metaheuristic algorithms for calibrating three nonlinear soil constitutive models, revealing that algorithm performance varies significantly with model complexity and that low objective-function values do not guarantee accurate parameter recovery due to equifinality.
This study numerically investigates the impact of intermediate tie configurations, hoop spacing, and hook anchorage angles on the lateral load capacity and ductility of reinforced concrete columns, revealing that optimized tie designs significantly enhance structural performance through improved confinement and buckling restraint.
This review analyzes 105 plasma-etch virtual metrology studies to propose a two-stage framework that addresses the challenge of constructing compact, robust, and physically meaningful representations from high-dimensional process data to overcome the limitations of sparse and delayed physical metrology in semiconductor manufacturing.
This study presents a five-axis in situ bioprinting system utilizing conformal slicing to enable multi-angle, orientation-adaptive deposition on complex curved surfaces, thereby overcoming the limitations of traditional 3-axis planar printing to achieve superior structural fidelity, mechanical integrity, and clinical applicability for patient-specific tissue reconstruction.
This paper presents a robust, automated methodology for assessing urban electric pole inclination using Terrestrial Laser Scanning and a multi-algorithmic pipeline that integrates RANSAC, PCA, and geometric fitting to achieve higher accuracy and stability than conventional visual inspections, particularly in noisy or occluded environments.
This paper proposes a low-complexity, phase-only transmit beampattern optimization method for Frequency Diverse Array (FDA) radar that minimizes radiated power at hostile interception locations while maximizing echo signal energy, thereby significantly enhancing the system's low probability of intercept (LPI) performance.
This paper proposes a fully data-driven framework that combines compressed sensing, adaptive Dynamic Mode Decomposition with control (DMDc) calibrated via DCC-GARCH, and reduced-order Kalman filtering to accurately reconstruct full-field states of nonlinear dynamical systems from sparse and noisy point-sensor measurements without relying on first-principles models.
This study analyzes seepage and water level fluctuations in the alluvial Kattakurgan reservoir through field monitoring and geophysical assessments to identify hazardous dam sections and formulate an efficient, seasonally adaptive operating mode.