Improved Accuracy in Predicting the Best Sensor Fusion Architecture for Multiple Domains

Multi-sensor fusion intends to boost the general reliability of a decision-making procedure or allow one sensor to compensate for others’ shortcomings. This field has been so prominent that authors have proposed many different fusion approaches, or “architectures” as we call them when they are struc...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Erik Molino-Minero-Re, Antonio A. Aguileta, Ramon F. Brena, Enrique Garcia-Ceja
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	sensor fusion classification SFFS metadata statistical signature Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/cddfed978c2a4404aaeb353f60d9926c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:cddfed978c2a4404aaeb353f60d9926c
record_format	dspace
spelling	oai:doaj.org-article:cddfed978c2a4404aaeb353f60d9926c2021-11-11T19:03:01ZImproved Accuracy in Predicting the Best Sensor Fusion Architecture for Multiple Domains10.3390/s212170071424-8220https://doaj.org/article/cddfed978c2a4404aaeb353f60d9926c2021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7007https://doaj.org/toc/1424-8220Multi-sensor fusion intends to boost the general reliability of a decision-making procedure or allow one sensor to compensate for others’ shortcomings. This field has been so prominent that authors have proposed many different fusion approaches, or “architectures” as we call them when they are structurally different, so it is now challenging to prescribe which one is better for a specific collection of sensors and a particular application environment, other than by trial and error. We propose an approach capable of predicting the best fusion architecture (from predefined options) for a given dataset. This method involves the construction of a meta-dataset where statistical characteristics from the original dataset are extracted. One challenge is that each dataset has a different number of variables (columns). Previous work took the principal component analysis’s first <i>k</i> components to make the meta-dataset columns coherent and trained machine learning classifiers to predict the best fusion architecture. In this paper, we take a new route to build the meta-dataset. We use the Sequential Forward Floating Selection algorithm and a <i>T</i> transform to reduce the features and match them to a given number, respectively. Our findings indicate that our proposed method could improve the accuracy in predicting the best sensor fusion architecture for multiple domains.Erik Molino-Minero-ReAntonio A. AguiletaRamon F. BrenaEnrique Garcia-CejaMDPI AGarticlesensor fusionclassificationSFFSmetadatastatistical signatureChemical technologyTP1-1185ENSensors, Vol 21, Iss 7007, p 7007 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	sensor fusion classification SFFS metadata statistical signature Chemical technology TP1-1185
spellingShingle	sensor fusion classification SFFS metadata statistical signature Chemical technology TP1-1185 Erik Molino-Minero-Re Antonio A. Aguileta Ramon F. Brena Enrique Garcia-Ceja Improved Accuracy in Predicting the Best Sensor Fusion Architecture for Multiple Domains
description	Multi-sensor fusion intends to boost the general reliability of a decision-making procedure or allow one sensor to compensate for others’ shortcomings. This field has been so prominent that authors have proposed many different fusion approaches, or “architectures” as we call them when they are structurally different, so it is now challenging to prescribe which one is better for a specific collection of sensors and a particular application environment, other than by trial and error. We propose an approach capable of predicting the best fusion architecture (from predefined options) for a given dataset. This method involves the construction of a meta-dataset where statistical characteristics from the original dataset are extracted. One challenge is that each dataset has a different number of variables (columns). Previous work took the principal component analysis’s first <i>k</i> components to make the meta-dataset columns coherent and trained machine learning classifiers to predict the best fusion architecture. In this paper, we take a new route to build the meta-dataset. We use the Sequential Forward Floating Selection algorithm and a <i>T</i> transform to reduce the features and match them to a given number, respectively. Our findings indicate that our proposed method could improve the accuracy in predicting the best sensor fusion architecture for multiple domains.
format	article
author	Erik Molino-Minero-Re Antonio A. Aguileta Ramon F. Brena Enrique Garcia-Ceja
author_facet	Erik Molino-Minero-Re Antonio A. Aguileta Ramon F. Brena Enrique Garcia-Ceja
author_sort	Erik Molino-Minero-Re
title	Improved Accuracy in Predicting the Best Sensor Fusion Architecture for Multiple Domains
title_short	Improved Accuracy in Predicting the Best Sensor Fusion Architecture for Multiple Domains
title_full	Improved Accuracy in Predicting the Best Sensor Fusion Architecture for Multiple Domains
title_fullStr	Improved Accuracy in Predicting the Best Sensor Fusion Architecture for Multiple Domains
title_full_unstemmed	Improved Accuracy in Predicting the Best Sensor Fusion Architecture for Multiple Domains
title_sort	improved accuracy in predicting the best sensor fusion architecture for multiple domains
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/cddfed978c2a4404aaeb353f60d9926c
work_keys_str_mv	AT erikmolinominerore improvedaccuracyinpredictingthebestsensorfusionarchitectureformultipledomains AT antonioaaguileta improvedaccuracyinpredictingthebestsensorfusionarchitectureformultipledomains AT ramonfbrena improvedaccuracyinpredictingthebestsensorfusionarchitectureformultipledomains AT enriquegarciaceja improvedaccuracyinpredictingthebestsensorfusionarchitectureformultipledomains
_version_	1718431670875455488

Improved Accuracy in Predicting the Best Sensor Fusion Architecture for Multiple Domains

Ejemplares similares