Driver Behavior Modeling with Subjective Risk‐Driven Inverse Reinforcement Learning
A subjective risk‐driven inverse reinforcement learning framework is proposed to model driver decision‐making. It infers drivers' risk perception and risk tolerance from driving data. A learnable risk threshold is used to regulate decisions, enabling interpretable and human‐like driving behavior decisions.
Yang Liang +6 more
wiley +1 more source
Unbiased Structure Prediction of Sophisticated Cage Structures
We introduce the software and workflow for automated, unbiased exploration of all possible connectivities of a given set of building blocks and their stoichiometry to predict stable cage structures. ABSTRACT Cage structure prediction has made significant strides by generating structures based on what the community has seen before.
Andrew Tarzia, Giovanni M. Pavan
wiley +2 more sources
Acceleration of ray tracing method using predictive evaluation and GPGPU technology
Sobota Branislav +3 more
doaj +1 more source
Cloud-to-Edge Deployment of Optimized nnU-Net for Ischemic Stroke Lesion Segmentation on Resource-Constrained Embedded Devices. [PDF]
Alcaraz-Ortiz D +2 more
europepmc +1 more source
Xstainer: A Novel Virtual Staining Tool Powered by Advanced Deep Learning Techniques
Xstainer is a deep learning–based virtual staining framework that converts hematoxylin and eosin‐stained whole slide images into multiple histochemical stains, including Masson's trichrome, Periodic acid‐Schiff, Jones methenamine silver, and Toluidine blue.
Fatma Nur Kinali +15 more
wiley +1 more source
Single‐cell Spatial Transcriptomics Analysis and Denoising Engine is introduced as a unified deep learning framework that jointly performs denoising, clustering, and gene prioritization in spatial transcriptomics. By integrating linear and nonlinear representations within a dual‐channel architecture, it improves robustness and accuracy, uncovers ...
Yaxuan Cui +11 more
wiley +1 more source
A Pragmatic Framework for Federated Learning Risk and Governance in Academic Medical Centers. [PDF]
Bottomly D +6 more
europepmc +1 more source
Exploiting Ferroelectric and Spintronic Dynamics for Neural Network Computation
Ferroelectric and spintronic devices, relying on the control of polarization and magnetization, offer intrinsically fast, durable, energy‐efficient, and low‐latency building blocks for analog in‐memory computing. The hysteretic dynamics of an order parameter are leveraged to provide nonvolatile, multistate memory and nonlinear switching. Brain‐inspired
Dashiell Harrison +4 more
wiley +1 more source
A lightweight monocular perception framework generates high‐fidelity depth maps and integrates YOLOv8 detection to estimate object‐wise distances from a single RGB image. Evaluated on KITTI and the proposed D‐Far250 dataset, the system demonstrates accurate long‐range perception up to 250 m while maintaining real‐time performance, enabling scalable ...
Faseeh Muhammad +5 more
wiley +1 more source
UAV-based RGB and multispectral mango leaf disease detection with benchmarking of YOLOv5 to YOLOv10 and SeqOpt-optimised YOLOv8 for real-time edge deployment. [PDF]
Karthik RP +3 more
europepmc +1 more source

