دانلود رایگان مقاله آنتولوژی انرژی الکتریکی سطح بالا با ویژگی های وزنی

Abstract

One of the significant application areas of domain ontologies is known to be text analysis applications like information extraction and text classification systems, and semantic portals. In this paper, we present a high-level ontology for the electrical energy domain. This domain ontology has weighted attributes to cover the inherent fuzziness in the textual representations of its concepts. Additionally, we have included in the ontology the necessary attributes to align the ontology concepts to on-line collaborative knowledge bases like Wikipedia and linked open data sources like DBpedia, other attributes to facilitate its use in multilingual applications, and concepts to hold the named entities in the domain. The ultimate ontology is aligned with the previously proposed ontologies for the energy-related subdomains after extending the latter ones with weighted attributes. We make the ultimate form of the electrical energy ontology, as well as the extended versions of the domain ontologies for the subdomains, available for research purposes. Also included in the paper are sample text analysis applications which mainly exploit the weighted attributes within the ontology.

5. Conclusion

In this paper, we propose a high-level domain ontology with weighted attributes for the electrical energy domain which is a significant engineering field with several plausible application areas. We describe the procedures to determine the ontology concepts and to extend the ontology with weighted attributes, mainly based on the Wikipedia articles and disambiguation pages. The existing domain ontologies which have been previously proposed for the subdomains of electrical energy, including a power quality ontology and a wind energy ontology, are also interlinked (aligned) with the ultimate ontology. Finally, two text analysis applications are implemented in which the proposed electrical energy ontology and linked ontologies are employed as the sources of semantic information. The proposed ontology is a high-level one with significant coverage and has weighted attributes to handle fuzziness, multilinguality, and links to other domain ontologies as well as to other semantic information sources like Wikipedia and linked open data sources like DBpedia. Directions of future work based on the current study include automatic extension of this ontology using Wikipedia articles and other textual Web-based information sources, in addition to linking it with other existing ontologies for significant subdomains such as the smart grid, and also with related portals like reegle and OpenEI. Further applications can be implemented based on the ontologies and evaluated on larger data sets. Another prospective future study is to automatically turn the electrical energy ontology into a multilingual resource with more coverage, supporting several other languages, by automatic processing of the Wikipedia article pages for different languages.