Abstract
Sensor networks are a concept that has become very popular in data acquisition and processing for multiple applications in different fields such as industrial, medicine, home automation, environmental detection, etc. Today, with the proliferation of small communication devices with sensors that collect environmental data, semantic Web technologies are becoming closely related with sensor networks. The linking of elements from Semantic Web technologies with sensor networks has been called Semantic Sensor Web and has among its main features the use of ontologies. One of the key challenges of using ontologies in sensor networks is to provide mechanisms to integrate and exchange knowledge from heterogeneous sources (that is, dealing with semantic heterogeneity). Ontology alignment is the process of bringing ontologies into mutual agreement by the automatic discovery of mappings between related concepts. This paper presents a system for ontology alignment in the Semantic Sensor Web which uses fuzzy logic techniques to combine similarity measures between entities of different ontologies. The proposed approach focuses on two key elements: the terminological similarity, which takes into account the linguistic and semantic information of the context of the entity's names, and the structural similarity, based on both the internal and relational structure of the concepts. This work has been validated using sensor network ontologies and the Ontology Alignment Evaluation Initiative (OAEI) tests. The results show that the proposed techniques outperform previous approaches in terms of precision and recall.
Highlights
The increasing miniaturization of computers raises the idea of developing extremely small, inexpensive computers that communicate wirelessly and are organized independently
We present a general experiment with real sensor network ontologies, and another experiment framed in the forest fire control scenario
We aim to provide mechanisms to address the problem of semantic heterogeneity caused by the use of different ontologies in the field of sensor networks
Summary
The increasing miniaturization of computers raises the idea of developing extremely small, inexpensive computers that communicate wirelessly and are organized independently. A sensor network is a network of tiny computers (nodes) equipped with sensors which collaborate on a common task [1]. Sensor networks are a relatively new concept in data acquisition and processing for multiple applications in different fields such as industry, medicine, home automation, military environments, environmental detection, etc. Their main features (to be small, cheap, autonomous, easy to deploy, self-configurable and able to perform efficient energy management) have made sensor networks a very active research field, in which systems as diverse as Berkeley Motes [2], Pico-Radio [3], Smart-Dust [4] and WINS [5] have been developed.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
