Results 21 to 30 of about 37,104 (149)
Ensemble learning for the partial label ranking problem
Mathematical Methods in the Applied Sciences, Volume 46, Issue 1, Page 7-27, 15 January 2023., 2023 The partial label ranking problem is a general interpretation of the preference learning scenario known as the label ranking problem, the goal of which is to learn preference classifiers able to predict a complete ranking with ties over the finite set of labels of the class variable.
Juan C. Alfaro +2 more
wiley +1 more source
Molecular Oncology, EarlyView.Large multidimensional digital images of cancer tissue are becoming prolific, but many challenges exist to automatically extract relevant information from them using computational tools. We describe publicly available resources that have been developed jointly by expert and non‐expert computational biologists working together during a virtual hackathon
Sandhya Prabhakaran +16 more
wiley +1 more source
A Python package for fast GPU‐based proton pencil beam dose calculation
Journal of Applied Clinical Medical Physics, EarlyView.Abstract Purpose Open‐source GPU‐based Monte Carlo (MC) proton dose calculation algorithms provide high speed and unparalleled accuracy but can be complex to integrate with new applications and remain slower than GPU‐based pencil beam (PB) methods, which sacrifice some physical accuracy for sub‐second plan calculation.
Mahasweta Bhattacharya +4 more
wiley +1 more source
International Journal for Numerical and Analytical Methods in Geomechanics, Volume 47, Issue 2, Page 145-186, 10 February 2023., 2023 Abstract A two‐phase velocity‐pressure stabilized formulation is proposed for the numerical analysis of mechanized excavations in partially saturated soft soils using the Particle Finite Element Method (PFEM). The fully coupled formulation is based on the theory of porous media in association with the Soil Water Characteristic Curve and the porosity ...
Abdiel Ramon Leon Bal, Günther Meschke
wiley +1 more source
Journal of Applied Clinical Medical Physics, EarlyView.Abstract Purpose In radiation oncology, the integration and registration of multiple imaging modalities is a crucial aspect of the diagnosis and treatment planning process. These images are often inherently registered, a useful feature in most cases, but possibly a hindrance when registration modifications are required.
Brian M. Anderson, Casey Bojechko
wiley +1 more source
Optimal deployment of indoor wireless local area networks
Networks, Volume 81, Issue 1, Page 23-50, January 2023., 2023 Abstract We present a two‐phase methodology to address the problem of optimally deploying indoor wireless local area networks. In the first phase, we use Helmholtz's equation to simulate electromagnetic fields in a typical environment such as an office floor.
Antoine Oustry +4 more
wiley +1 more source
Advanced Engineering Materials, EarlyView.The MaterialDigital initiative drives the digital transformation of material science by promoting findable, accessible, interoperable, and reusable principles and enhancing data interoperability. This article explores the role of scientific workflows, highlights challenges in their adoption, and introduces the Workflow Store as a key tool for sharing ...
Simon Bekemeier +37 more
wiley +1 more source
Autonomous Control of Extrusion Bioprinting Using Convolutional Neural Networks
Advanced Functional Materials, EarlyView.This work presents a novel computer vision system for high‐fidelity monitoring of extrusion‐based bioprinting and a correction system utilizing convolutional neural networks for error mitigation. This system has demonstrated high detection accuracy and extrusion correction abilities that advance the state of the art toward accelerated printing ...
Daniel Kelly +4 more
wiley +1 more source
3D Printed Materials with Nanovoxelated Elastic Moduli
Advanced Materials, EarlyView.A novel 3D printing method enables the fabrication of materials with precisely controlled mechanical properties at nanoscale resolution. A volume‐conserving photoresist combined with the free and open‐source software, OpenScribe, achieves mechanical transitions over 770 nanometers ‐ representing a 130‐fold improvement over existing approaches.
Peter L. H. Newman +6 more
wiley +1 more source
Optimizing Metamaterial Inverse Design with 3D Conditional Diffusion Model and Data Augmentation
Advanced Materials Technologies, EarlyView.A generative AI model, the 3D conditional diffusion model (3D‐CDM), is introduced to enhance the inverse design of voxel‐based metamaterials. A data augmentation technique based on topological perturbation expands the dataset, further improving generation quality and accuracy.
Xiaoyang Zheng +2 more
wiley +1 more source