1616 papers
This paper proposes CC-DeePC, a safe data-enabled predictive control framework that leverages Adaptive Conformal Inference to dynamically calibrate output constraints based on predictor residuals, thereby significantly increasing the rate of certified, slack-free safety under non-stationary dynamics compared to existing robust and static baselines.
This study demonstrates that machine learning models can successfully infer contemporaneous wind speeds and boundary-layer heights from single atmospheric composition snapshots, proving that such static scenes retain recoverable information about the underlying dynamical state.
This paper presents a comprehensive mathematical and systems analysis of a consistency-aware visual-inertial estimation architecture for GPS-denied drone swarms, demonstrating through reproducible simulations that low image residuals alone are insufficient for reliable localization and highlighting the critical importance of geometric observability and rigorous software validation.
This paper presents a fail-closed, trust-aware command authorization framework for autonomous UAV swarms operating in GPS-denied environments that integrates cryptographic authentication with runtime safety and trust assessments to deterministically gate commands based on a nine-state cyber-resilience supervisor.
This paper presents a deep learning framework using Detectron2 and a COCO-formatted dataset generated via OpendTect and Label Studio to achieve superior instance segmentation of chaotic seismic reflections compared to U-Net, demonstrating that a ResNet101 backbone yields the highest bounding box accuracy.
This study proposes an Environment-Aware Adaptive Multi-Objective Ant Colony Optimization (EA-MOACO) algorithm that integrates coupled wind–wave–current conditions and dynamic parameter adjustments to outperform existing methods in minimizing both route length and energy consumption for ship navigation in complex marine environments.
This paper presents a high-fidelity distributed statevector quantum circuit simulator that partitions the full state vector across four Xilinx Alveo U55C FPGAs using a specialized gate execution strategy to eliminate cross-card traffic for diagonal gates, thereby enabling exact simulations of up to 28 qubits with verified perfect fidelity.
This paper proposes a Work Breakdown Structure–Integrated Technology Classification (WBS–ITC) framework to map dispersed lunar in-situ resource utilization (ISRU) space-construction patents by construction capability rather than traditional classification, revealing distinct technology concentrations and functional adjacencies that conventional patent mapping overlooks.
This study employs Fuzzy C-Means clustering within a GIS framework to assess the seismic vulnerability and accessibility of 184 healthcare facilities in Cox's Bazar, Bangladesh, revealing that while hazard levels are low in the most critical areas, a multi-criteria analysis uncovers a significant capacity mismatch for facilities serving the Rohingya refugee population that would be overlooked by hazard-only assessments.
This study develops a data-driven framework integrating machine learning models, explainable AI, and multi-objective optimization to predict and optimize the thermo-hydraulic performance of tubular heat exchangers equipped with co- and counter-swirl V-winglet double perforated twisted tape inserts.