Results 1 to 10 of about 427,046 (249)

Training calibration-based counterfactual explainers for deep learning models in medical image analysis

open access: yesScientific Reports, 2022
The rapid adoption of artificial intelligence methods in healthcare is coupled with the critical need for techniques to rigorously introspect models and thereby ensure that they behave reliably.
Jayaraman J. Thiagarajan   +3 more
doaj   +1 more source

A Convolutional Neural Network Approach to the Classification of Engineering Models

open access: yesIEEE Access, 2021
This paper presents a deep learning approach for the classification of Engineering (CAD) models using Convolutional Neural Networks (CNNs). Owing to the availability of large annotated datasets and also enough computational power in the form of GPUs ...
Bharadwaj Manda   +2 more
doaj   +1 more source

Larger cells have relatively smaller nuclei across the Tree of Life

open access: yesEvolution Letters, 2021
Larger cells have larger nuclei, but the precise relationship between cell size and nucleus size remains unclear, and the evolutionary forces that shape this relationship are debated.
Martino E. Malerba, Dustin J. Marshall
doaj   +1 more source

Mapping the correlations and gaps in studies of complex life histories

open access: yesEcology and Evolution, 2023
For species with complex life histories, phenotypic correlations between life‐history stages constrain both ecological and evolutionary trajectories.
Emily L. Richardson, Dustin J. Marshall
doaj   +1 more source

Metabolic phenotype mediates the outcome of competitive interactions in a response‐surface field experiment

open access: yesEcology and Evolution, 2021
Competition and metabolism should be linked. Intraspecific variation in metabolic rates and, hence, resource demands covary with competitive ability.
Lukas Schuster   +2 more
doaj   +1 more source

Carry‐over effects and fitness trade‐offs in marine life histories: The costs of complexity for adaptation

open access: yesEvolutionary Applications, 2023
Most marine organisms have complex life histories, where the individual stages of a life cycle are often morphologically and ecologically distinct. Nevertheless, life‐history stages share a single genome and are linked phenotypically (by “carry‐over ...
Dustin J. Marshall, Tim Connallon
doaj   +1 more source

3D printing and assembling of frame modules using printable strain-hardening cement-based composites (SHCC)

open access: yesMaterials & Design, 2022
Despite all their advantages, load-bearing concrete shell structures with double curvatures are not frequently in use. The main reason is the complexity of their construction.
Egor Ivaniuk   +5 more
doaj   +1 more source

Feature-aware unsupervised lesion segmentation for brain tumor images using fast data density functional transform

open access: yesScientific Reports, 2023
We demonstrate that isomorphically mapping gray-level medical image matrices onto energy spaces underlying the framework of fast data density functional transform (fDDFT) can achieve the unsupervised recognition of lesion morphology.
Shin-Jhe Huang   +3 more
doaj   +1 more source

Metabolic rate, context‐dependent selection, and the competition‐colonization trade‐off

open access: yesEvolution Letters, 2020
Metabolism is linked with the pace‐of‐life, co‐varying with survival, growth, and reproduction. Metabolic rates should therefore be under strong selection and, if heritable, become less variable over time.
Amanda K. Pettersen   +3 more
doaj   +1 more source

DETECTION OF PLANAR POINTS FOR BUILDING EXTRACTION FROM LIDAR DATA BASED ON DIFFERENTIAL MORPHOLOGICAL AND ATTRIBUTE PROFILES [PDF]

open access: yesISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2013
This paper considers a new method for building-extraction from LiDAR data. This method uses multi-scale levelling schema or MSLS-segmentation based on differential morphological profiles for removing non-building points from LiDAR data during the data ...
D. Mongus   +3 more
doaj   +1 more source

Home - About - Disclaimer - Privacy