angela bernardini

Dr. angela bernardini


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 June 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
MZMaialen Zabalza Zudaire
Maialen Zabalza Zudaire
ABangela bernardini
angela bernardini
Many visual applications require high-resolution images for an adequate interpretation of the data stored within them. In remote sensing, the appearance of satellites such as Sentinel or Landsat has facilitated the access to data thanks to their free offer of multispectral images. However, the spatial resolution of these satellites is insufficient for many tasks. Therefore, the objective of this work is to apply deep learning techniques to increase the resolution of the Sentinel-2 Read-Green-Blue-NIR (RGBN) bands from the original 10 m to 2.5 m. This means multiplying the number of pixels in the resulting image by 4, improving the perception and visual quality. In this work, we implement a state-of-the-art residual learning-based model called Super-Resolution Residual Network (SRResNet), which we train using PlanetScope-Sentinel pairs of images. Our model, named SARNet (Spectral Attention Residual Network), incorporates Residual Channel Attention Blocks (RCAB) to improve the performance of the network and the visual quality of the results. The experiments we have carried out show that SARNet offers better results than other state-of-the-art methods.

19 July 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
EEEsús Esarte
Esús Esarte
Jesús M. BlancoJesús M. Blanco
Jesús M. Blanco
ABangela bernardini
angela bernardini
RSRamon Sancibrian
Ramon Sancibrian
The primary wick in a loop heat pipe device is a key component that is central to the operation of the device. Both high permeability and capillary pumping capacity, two properties highly dependent on wick structure, are strongly desirable for a satisfactory thermal performance. In this paper, selective laser melting (SLM), a three-dimensional (3D) printing technology, is used to create a primary wick for an 80 W heat transfer application. The permeability and capillarity values of this wick, experimentally measured, are compared with those built with the most widely used technologies nowadays, such as powder sintering and meshes. In this study, the SLM scaffold is shown to satisfy the minimum values required by the application in terms of capillarity and permeability: 0.031 mm/s and 4 × 10−12 m2, respectively. Our comparative study revealed that the wick produced with the SLM technology presented higher values of permeability, by two orders of magnitude, and slightly higher capillary figures than those corresponding to powder sintering for such application. However, it had capillary values well below those of a stainless-steel mesh. The hydraulic behavior of the SLM wick was better than that of the sintered copper powder, because it not only met the above-mentioned specifications, but it also improved its performance.

16 January 2023 in IEEE Transactions on Fuzzy Systems
Verified
Journal Article
Closed access
MFMikel Ferrero-Jaurrieta
Mikel Ferrero-Jaurrieta
ZTZdenko Takáč
Zdenko Takáč
IRIosu Rodriguez-Martinez
Iosu Rodriguez-Martinez
Cedric Marco-DetchartCedric Marco-Detchart
Cedric Marco-Detchart
ABangela bernardini
angela bernardini
Humberto BustinceHumberto Bustince
Humberto Bustince
Restricted equivalence functions are well-known functions to compare two numbers in the interval between 0 and 1. Despite the numerous works studying the properties of restricted equivalence functions and their multiple applications as support for different similarity measures, an extension of these functions to an n-dimensional space is absent from the literature. In this paper, we present a novel contribution to the restricted equivalence function theory, allowing to compare multivalued elements. Specifically, we extend the notion of restricted equivalence functions from $L$ to $L^{n}$ and present a new similarity construction on $L^{n}$ . Our proposal is tested in the context of color image anisotropic diffusion as an example of one of its many applications.