Matching sensor ontologies with unsupervised neural network with competitive learning

Sensor ontologies formally model the core concepts in the sensor domain and their relationships, which facilitates the trusted communication and collaboration of Artificial Intelligence of Things (AIoT). However, due to the subjectivity of the ontology building process, sensor ontologies might be de...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xingsi Xue, Haolin Wang, Wenyu Liu
Formato:	article
Lenguaje:	EN
Publicado:	PeerJ Inc. 2021
Materias:	Artificial intelligence of things Sensor ontology matching Unsupervised neural network Competitive learning Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/fac2aca02dcf4cc4b81aa96734f5c603
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fac2aca02dcf4cc4b81aa96734f5c603
record_format	dspace
spelling	oai:doaj.org-article:fac2aca02dcf4cc4b81aa96734f5c6032021-11-21T15:05:10ZMatching sensor ontologies with unsupervised neural network with competitive learning10.7717/peerj-cs.7632376-5992https://doaj.org/article/fac2aca02dcf4cc4b81aa96734f5c6032021-11-01T00:00:00Zhttps://peerj.com/articles/cs-763.pdfhttps://peerj.com/articles/cs-763/https://doaj.org/toc/2376-5992Sensor ontologies formally model the core concepts in the sensor domain and their relationships, which facilitates the trusted communication and collaboration of Artificial Intelligence of Things (AIoT). However, due to the subjectivity of the ontology building process, sensor ontologies might be defined by different terms, leading to the problem of heterogeneity. In order to integrate the knowledge of two heterogeneous sensor ontologies, it is necessary to determine the correspondence between two heterogeneous concepts, which is the so-called ontology matching. Recently, more and more neural networks have been considered as an effective approach to address the ontology heterogeneity problem, but they require a large number of manually labelled training samples to train the network, which poses an open challenge. In order to improve the quality of the sensor ontology alignment, an unsupervised neural network model is proposed in this work. It first models the ontology matching problem as a binary classification problem, and then uses a competitive learning strategy to efficiently cluster the ontologies to be matched, which does not require the labelled training samples. The experiment utilizes the benchmark track provided by the Ontology Alignment Evaluation Initiative (OAEI) and multiple real sensor ontology alignment tasks to test our proposal’s performance. The experimental results show that the proposed approach is able to determine higher quality alignment results compared to other matching strategies under different domain knowledge such as bibliographic and real sensor ontologies.Xingsi XueHaolin WangWenyu LiuPeerJ Inc.articleArtificial intelligence of thingsSensor ontology matchingUnsupervised neural networkCompetitive learningElectronic computers. Computer scienceQA75.5-76.95ENPeerJ Computer Science, Vol 7, p e763 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Artificial intelligence of things Sensor ontology matching Unsupervised neural network Competitive learning Electronic computers. Computer science QA75.5-76.95
spellingShingle	Artificial intelligence of things Sensor ontology matching Unsupervised neural network Competitive learning Electronic computers. Computer science QA75.5-76.95 Xingsi Xue Haolin Wang Wenyu Liu Matching sensor ontologies with unsupervised neural network with competitive learning
description	Sensor ontologies formally model the core concepts in the sensor domain and their relationships, which facilitates the trusted communication and collaboration of Artificial Intelligence of Things (AIoT). However, due to the subjectivity of the ontology building process, sensor ontologies might be defined by different terms, leading to the problem of heterogeneity. In order to integrate the knowledge of two heterogeneous sensor ontologies, it is necessary to determine the correspondence between two heterogeneous concepts, which is the so-called ontology matching. Recently, more and more neural networks have been considered as an effective approach to address the ontology heterogeneity problem, but they require a large number of manually labelled training samples to train the network, which poses an open challenge. In order to improve the quality of the sensor ontology alignment, an unsupervised neural network model is proposed in this work. It first models the ontology matching problem as a binary classification problem, and then uses a competitive learning strategy to efficiently cluster the ontologies to be matched, which does not require the labelled training samples. The experiment utilizes the benchmark track provided by the Ontology Alignment Evaluation Initiative (OAEI) and multiple real sensor ontology alignment tasks to test our proposal’s performance. The experimental results show that the proposed approach is able to determine higher quality alignment results compared to other matching strategies under different domain knowledge such as bibliographic and real sensor ontologies.
format	article
author	Xingsi Xue Haolin Wang Wenyu Liu
author_facet	Xingsi Xue Haolin Wang Wenyu Liu
author_sort	Xingsi Xue
title	Matching sensor ontologies with unsupervised neural network with competitive learning
title_short	Matching sensor ontologies with unsupervised neural network with competitive learning
title_full	Matching sensor ontologies with unsupervised neural network with competitive learning
title_fullStr	Matching sensor ontologies with unsupervised neural network with competitive learning
title_full_unstemmed	Matching sensor ontologies with unsupervised neural network with competitive learning
title_sort	matching sensor ontologies with unsupervised neural network with competitive learning
publisher	PeerJ Inc.
publishDate	2021
url	https://doaj.org/article/fac2aca02dcf4cc4b81aa96734f5c603
work_keys_str_mv	AT xingsixue matchingsensorontologieswithunsupervisedneuralnetworkwithcompetitivelearning AT haolinwang matchingsensorontologieswithunsupervisedneuralnetworkwithcompetitivelearning AT wenyuliu matchingsensorontologieswithunsupervisedneuralnetworkwithcompetitivelearning
_version_	1718418863644737536

Matching sensor ontologies with unsupervised neural network with competitive learning

Ejemplares similares