Generative adversarial networks for generating synthetic features for Wi-Fi signal quality.

Wireless networks are among the fundamental technologies used to connect people. Considering the constant advancements in the field, telecommunication operators must guarantee a high-quality service to keep their customer portfolio. To ensure this high-quality service, it is common to establish part...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mauro Castelli, Luca Manzoni, Tatiane Espindola, Aleš Popovič, Andrea De Lorenzo
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/2a8ccd2c1f07470991cfd28226ca5725
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2a8ccd2c1f07470991cfd28226ca5725
record_format	dspace
spelling	oai:doaj.org-article:2a8ccd2c1f07470991cfd28226ca57252021-12-02T20:16:13ZGenerative adversarial networks for generating synthetic features for Wi-Fi signal quality.1932-620310.1371/journal.pone.0260308https://doaj.org/article/2a8ccd2c1f07470991cfd28226ca57252021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0260308https://doaj.org/toc/1932-6203Wireless networks are among the fundamental technologies used to connect people. Considering the constant advancements in the field, telecommunication operators must guarantee a high-quality service to keep their customer portfolio. To ensure this high-quality service, it is common to establish partnerships with specialized technology companies that deliver software services in order to monitor the networks and identify faults and respective solutions. A common barrier faced by these specialized companies is the lack of data to develop and test their products. This paper investigates the use of generative adversarial networks (GANs), which are state-of-the-art generative models, for generating synthetic telecommunication data related to Wi-Fi signal quality. We developed, trained, and compared two of the most used GAN architectures: the Vanilla GAN and the Wasserstein GAN (WGAN). Both models presented satisfactory results and were able to generate synthetic data similar to the real ones. In particular, the distribution of the synthetic data overlaps the distribution of the real data for all of the considered features. Moreover, the considered generative models can reproduce the same associations observed for the synthetic features. We chose the WGAN as the final model, but both models are suitable for addressing the problem at hand.Mauro CastelliLuca ManzoniTatiane EspindolaAleš PopovičAndrea De LorenzoPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 11, p e0260308 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Mauro Castelli Luca Manzoni Tatiane Espindola Aleš Popovič Andrea De Lorenzo Generative adversarial networks for generating synthetic features for Wi-Fi signal quality.
description	Wireless networks are among the fundamental technologies used to connect people. Considering the constant advancements in the field, telecommunication operators must guarantee a high-quality service to keep their customer portfolio. To ensure this high-quality service, it is common to establish partnerships with specialized technology companies that deliver software services in order to monitor the networks and identify faults and respective solutions. A common barrier faced by these specialized companies is the lack of data to develop and test their products. This paper investigates the use of generative adversarial networks (GANs), which are state-of-the-art generative models, for generating synthetic telecommunication data related to Wi-Fi signal quality. We developed, trained, and compared two of the most used GAN architectures: the Vanilla GAN and the Wasserstein GAN (WGAN). Both models presented satisfactory results and were able to generate synthetic data similar to the real ones. In particular, the distribution of the synthetic data overlaps the distribution of the real data for all of the considered features. Moreover, the considered generative models can reproduce the same associations observed for the synthetic features. We chose the WGAN as the final model, but both models are suitable for addressing the problem at hand.
format	article
author	Mauro Castelli Luca Manzoni Tatiane Espindola Aleš Popovič Andrea De Lorenzo
author_facet	Mauro Castelli Luca Manzoni Tatiane Espindola Aleš Popovič Andrea De Lorenzo
author_sort	Mauro Castelli
title	Generative adversarial networks for generating synthetic features for Wi-Fi signal quality.
title_short	Generative adversarial networks for generating synthetic features for Wi-Fi signal quality.
title_full	Generative adversarial networks for generating synthetic features for Wi-Fi signal quality.
title_fullStr	Generative adversarial networks for generating synthetic features for Wi-Fi signal quality.
title_full_unstemmed	Generative adversarial networks for generating synthetic features for Wi-Fi signal quality.
title_sort	generative adversarial networks for generating synthetic features for wi-fi signal quality.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/2a8ccd2c1f07470991cfd28226ca5725
work_keys_str_mv	AT maurocastelli generativeadversarialnetworksforgeneratingsyntheticfeaturesforwifisignalquality AT lucamanzoni generativeadversarialnetworksforgeneratingsyntheticfeaturesforwifisignalquality AT tatianeespindola generativeadversarialnetworksforgeneratingsyntheticfeaturesforwifisignalquality AT alespopovic generativeadversarialnetworksforgeneratingsyntheticfeaturesforwifisignalquality AT andreadelorenzo generativeadversarialnetworksforgeneratingsyntheticfeaturesforwifisignalquality
_version_	1718374513973919744

Generative adversarial networks for generating synthetic features for Wi-Fi signal quality.

Ejemplares similares