Zobrazeno 1 - 10
of 212
pro vyhledávání: '"Díaz Redondo, Rebeca P."'
Autor:
Fernández-Piñeiro, Pablo, Ferández-Veiga, Manuel, Díaz-Redondo, Rebeca P., Fernández-Vilas, Ana, González-Soto, Martín
In prototype-based federated learning, the exchange of model parameters between clients and the master server is replaced by transmission of prototypes or quantized versions of the data samples to the aggregation server. A fully decentralized deploym
Externí odkaz:
http://arxiv.org/abs/2411.09267
Autor:
Cajaraville-Aboy, Diego, Fernández-Vilas, Ana, Díaz-Redondo, Rebeca P., Fernández-Veiga, Manuel
Federated Learning (FL) emerges as a distributed machine learning approach that addresses privacy concerns by training AI models locally on devices. Decentralized Federated Learning (DFL) extends the FL paradigm by eliminating the central server, the
Externí odkaz:
http://arxiv.org/abs/2409.17754
Continual learning (CL) poses the important challenge of adapting to evolving data distributions without forgetting previously acquired knowledge while consolidating new knowledge. In this paper, we introduce a new methodology, coined as Tabular-data
Externí odkaz:
http://arxiv.org/abs/2407.09039
Autor:
González-Soto, Martín, Díaz-Redondo, Rebeca P., Fernández-Veiga, Manuel, Rodríguez-Castro, Bruno, Fernández-Vilas, Ana
Publikováno v:
Computer Networks. Volume 239, 2024
Decentralised machine learning has recently been proposed as a potential solution to the security issues of the canonical federated learning approach. In this paper, we propose a decentralised and collaborative machine learning framework specially or
Externí odkaz:
http://arxiv.org/abs/2312.12190
Autor:
Troncoso-Pastoriza, Francisco, Eguía-Oller, Pablo, Díaz-Redondo, Rebeca P., Granada-Álvarez, Enrique
Publikováno v:
Sustainable cities and society, 2018, vol. 36, p. 59-70
In this paper we introduce a method that supports the detection, identification and localization of lamps in a building, with the main goal of automatically feeding its energy model by means of Building Information Modeling (BIM) methods. The propose
Externí odkaz:
http://arxiv.org/abs/2401.05390
Autor:
Troncoso-Pastoriza, Francisco, Eguía-Oller, Pablo, Díaz-Redondo, Rebeca P., Granada-Álvarez, Enrique, Erkoreka, Aitor
Publikováno v:
Sensors, 2019, vol. 19, no 7, p. 1516
Computer vision is used in this work to detect lighting elements in buildings with the goal of improving the accuracy of previous methods to provide a precise inventory of the location and state of lamps. Using the framework developed in our previous
Externí odkaz:
http://arxiv.org/abs/2312.11380
Autor:
Troncoso-Pastoriza, Francisco, Eguía-Oller, Pablo, Díaz-Redondo, Rebeca P., Granada-Álvarez, Enrique
Publikováno v:
Automation in Construction, 2019, vol. 106, p. 102852
This paper introduces a complete method for the automatic detection, identification and localization of lighting elements in buildings, leveraging the available building information modeling (BIM) data of a building and feeding the BIM model with the
Externí odkaz:
http://arxiv.org/abs/2312.11375
Autor:
Cerezo-Costas, Héctor, Vilas, Ana Fernández, Martín-Vicente, Manuela, Díaz-Redondo, Rebeca P.
Publikováno v:
Expert Systems with Applications, 2018, vol. 95, p. 32-42
Citizens are actively interacting with their surroundings, especially through social media. Not only do shared posts give important information about what is happening (from the users' perspective), but also the metadata linked to these posts offer r
Externí odkaz:
http://arxiv.org/abs/2312.11076
Autor:
Díaz-Redondo, Rebeca P., Garcia-Rubio, Carlos, Vilas, Ana Fernández, Campo, Celeste, Rodriguez-Carrion, Alicia
Publikováno v:
Future Generation Computer Systems, 2020, vol. 109, p. 83-94
Undoubtedly, Location-based Social Networks (LBSNs) provide an interesting source of geo-located data that we have previously used to obtain patterns of the dynamics of crowds throughout urban areas. According to our previous results, activity in LBS
Externí odkaz:
http://arxiv.org/abs/2312.08092
Publikováno v:
IEEE Access, 2020, vol. 8, p. 85616-85638
Recently, Deep Learning (DL) approaches have been applied to solve the Sentiment Classification (SC) problem, which is a core task in reviews mining or Sentiment Analysis (SA). The performances of these approaches are affected by different factors. T
Externí odkaz:
http://arxiv.org/abs/2312.17253