Preprints — Entidade

engrxiv.org·há 2 dias

Faithful but Not Plausible? A Comparative Evaluation of Explainable AI Methods for Bridge Deck Crack Detection

Objectives: Automated crack detection using deep learning is increasingly proposed for bridge deck inspection, but transportation agencies hesitate to adopt models whose decisions cannot be examined.

engrxiv.org·há 2 dias

Threat Aware Task Offloading and Caching for Secure UAV Assisted Vehicular Consumer Electronics

Vehicular consumer electronics increasingly support computation-intensive and latency-sensitive services, imposing stringent efficiency, reliability, and security requirements on vehicular edge comput

engrxiv.org·há 2 dias

A Hierarchical YOLO-Based Pipeline for Document Analysis in Natural Images

Extracting structured information from documents embedded in natural images remains challenging due to diverse layouts and environmental noise. We propose a hierarchical three-stage deep learning pipe

engrxiv.org·há 3 dias

Hyperspectral Visual SLAM for Autonomous UAV Crop Stress Detection: A Reinforcement Learning Approach to Precision Agriculture

Localized soil-moisture deficits, that is, irregular sub-field patches where crops experience water stress well before visible wilting, are a leading cause of yield variability in row-crop agriculture

engrxiv.org·há 3 dias

On the Local Convergence of the Third-Order Newton Iteration

We present a local convergence analysis of the third-order Newton iteration for unconstrained optimization recently proposed by Ahmadi, Chaudhry, and Zhang. For the single-variable case, we derive the

engrxiv.org·há 3 dias

Physics-guided neural network with an asymmetric safety loss for fire resistance prediction of insulated FRP-strengthened RC beams

Machine-learned surrogates predict fire resistance (FR) of insulated FRP-strengthened RC beams accurately but violate basic physics, extrapolate unpredictably, and treat unsafe over-predictions the sa

engrxiv.org·há 3 dias

Artificial Intelligence Is Not an Intern: Authoritative Prompt Parenting for the Supervision of Generative AI by Engineers, Scientists, and Health Professionals

Generative artificial intelligence does not hold professional responsibility, and it may not reliably preserve user instructions over extended interactions. In response, we present “authoritative prom

engrxiv.org·há 3 dias

TopoContour-Mamba

Visual state-space models need a sequence before selective scanning, so the route decides which evidence is read early and which remains close to the final output. Most visual routes are fixed across