Zobrazeno 1 - 10
of 21
pro vyhledávání: '"David Buldain"'
Publikováno v:
Sensors, Vol 22, Iss 2, p 586 (2022)
Household appliances, climate control machines, vehicles, elevators, cash counting machines, etc., are complex machines with key contributions to the smart city. Those devices have limited memory and processing power, but they are not just actuators;
Externí odkaz:
https://doaj.org/article/fddfc88598814776b3e3d7274fedf96e
Publikováno v:
Sensors, Vol 19, Iss 22, p 5004 (2019)
This paper aims to design and implement a system capable of distinguishing between different activities carried out during a tennis match. The goal is to achieve the correct classification of a set of tennis strokes. The system must exhibit robustnes
Externí odkaz:
https://doaj.org/article/c7c651e63a844f25b7a445f20b287c72
Publikováno v:
Energies, Vol 12, Iss 13, p 2485 (2019)
This paper examines the recent advances made in the field of Deep Learning (DL) methods for the automated identification of Partial Discharges (PD). PD activity is an indication of the state and operational conditions of electrical equipment systems.
Externí odkaz:
https://doaj.org/article/c09868d545574e98bfbec86927781411
Autor:
Jorge Torres Ruiz, Julio David Buldain
Publikováno v:
Jornada de Jóvenes Investigadores del I3A. 9
We have studied if a small neural network proposed for EEG analysis can be applied to ECG analysis, trying to generate a model capable to clasifying ECG signals and suitable for being embebed into wearable devices.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f70056313f9b055b5ff74bfb4c04cd4d
https://doi.org/10.26754/jjii3a.20215969
https://doi.org/10.26754/jjii3a.20215969
Publikováno v:
Jornada de Jóvenes Investigadores del I3A. 8
Nuestro objetivo principal consiste en desarrollar un modelo neuronal convolucional que pueda ser usado como etapa de entrada para clasificadores, extrayéndo las características más relevantes de una señal biomédica y eliminando la necesidad de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bcb6b3f015fbea7dd95d595fed21d0f6
https://doi.org/10.26754/jjii3a.4891
https://doi.org/10.26754/jjii3a.4891
Publikováno v:
Electronics
Volume 9
Issue 12
Electronics, Vol 9, Iss 2035, p 2035 (2020)
Zaguán. Repositorio Digital de la Universidad de Zaragoza
instname
Zaguán: Repositorio Digital de la Universidad de Zaragoza
Universidad de Zaragoza
Volume 9
Issue 12
Electronics, Vol 9, Iss 2035, p 2035 (2020)
Zaguán. Repositorio Digital de la Universidad de Zaragoza
instname
Zaguán: Repositorio Digital de la Universidad de Zaragoza
Universidad de Zaragoza
Smart IoT sensors are characterized by their ability to sense and process signals, producing high-level information that is usually sent wirelessly while minimising energy consumption and maximising communication efficiency. Systems are getting smart
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8c9f0456fc8e490303470d831e6d1547
Publikováno v:
Zaguán. Repositorio Digital de la Universidad de Zaragoza
instname
instname
This work proposes a methodology to automate the recognition of Partial Discharges (PD) sources in Electrical Distribution Networks using a Deep Neural Network (DNN) model called Convolutional Autoencoder (CAE), which is able to automatically extract
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9f0d1a1e3c1fa4700f8522571156fd5c
http://zaguan.unizar.es/record/108362
http://zaguan.unizar.es/record/108362
Publikováno v:
Jornada de Jóvenes Investigadores del I3A. 7
Our main goal was studying the effectiveness of transfer learning using 2D CNNs. For this task, we generated spectrograms from ECG segments that were fed to a CNN to automatically extract features. These features are classified by a MLP into arrhythm
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e7eb24e15f43b38cfccf281a9535f9b0
https://doi.org/10.26754/jji-i3a.003522
https://doi.org/10.26754/jji-i3a.003522
Publikováno v:
Distributed Computing and Artificial Intelligence, 15th International Conference ISBN: 9783319946481
DCAI
DCAI
Mostly all works dealing with ECG signal and Convolutional Network approach use 1D CNNs and must train them from scratch, usually applying a signal preprocessing, such as noise reduction, R-peak detection or heartbeat detection. Instead, our approach
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::529f8c1cd8c824ea092ca16774a732b9
https://doi.org/10.1007/978-3-319-94649-8_15
https://doi.org/10.1007/978-3-319-94649-8_15
Publikováno v:
Studies in Computational Intelligence ISBN: 9783319233918
This paper presents a new algorithm , Magnitude Sensitive Image Compression (MSIC), as a reliable and efficient approach for selective image compression. The algorithm uses MSCL neural networks (in direct and masked versions). These kind of neural ne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cfe419f9248433fe91974d283780dd03
https://doi.org/10.1007/978-3-319-23392-5_23
https://doi.org/10.1007/978-3-319-23392-5_23