Häfner, Polina; Häfner, Victor; Wicaksono, Hendro; Ovtcharova, Jivka Semi-automated ontology population from building construction drawings Inproceedings 5th International Conference on Knowledge Engineering and Ontology Development, KEOD 2013; Vilamoura, Algarve; Portugal; 19 September 2013 - 22 September 2013, pp. 379-386, INSTICC, Lissabon, Lissabon, 2013, ISBN: 978-989856581-5. Abstract | Links | BibTeX | Tags: Ontology, ontology population, pattern recognition @inproceedings{Häfner2013,
title = {Semi-automated ontology population from building construction drawings},
author = {Polina Häfner and Victor Häfner and Hendro Wicaksono and Jivka Ovtcharova},
url = {https://publikationen.bibliothek.kit.edu/1000040883},
isbn = {978-989856581-5},
year = {2013},
date = {2013-09-06},
booktitle = {5th International Conference on Knowledge Engineering and Ontology Development, KEOD 2013; Vilamoura, Algarve; Portugal; 19 September 2013 - 22 September 2013},
pages = {379-386},
publisher = {INSTICC, Lissabon},
address = {Lissabon},
abstract = {Ontologies have been applied as knowledge representation in different domains including intelligent building management. One of the challenges in using ontologies is the population with building specific information, such as the building elements and the energy consuming devices.The population usually has to be done manually, thus it requires an extensive work. This is due to the lack of semantic information in the existing building drawings. The building drawings only contain geometrical information. However, it is possible that we understand the semantics of the drawings, if we have the knowledge in interpreting the semantics of the symbols, shapes and other geometric information. In this paper we introduce a tool to extract the semantic information from CAD drawings and populate the ontology using the extracted semantic information in a semi-automatic way. We extract the drawing primitives from CAD files, perform the pattern matching and classification algorithms to extract the semantic information and enrich them with geometric data like object world positions and bounding boxes. The resulting semantic information is then mapped to the corresponding ontology classes of a T-Box ontology. Finally individuals of the corresponding classes are created to populate the ontology.},
keywords = {Ontology, ontology population, pattern recognition},
pubstate = {published},
tppubtype = {inproceedings}
}
Ontologies have been applied as knowledge representation in different domains including intelligent building management. One of the challenges in using ontologies is the population with building specific information, such as the building elements and the energy consuming devices.The population usually has to be done manually, thus it requires an extensive work. This is due to the lack of semantic information in the existing building drawings. The building drawings only contain geometrical information. However, it is possible that we understand the semantics of the drawings, if we have the knowledge in interpreting the semantics of the symbols, shapes and other geometric information. In this paper we introduce a tool to extract the semantic information from CAD drawings and populate the ontology using the extracted semantic information in a semi-automatic way. We extract the drawing primitives from CAD files, perform the pattern matching and classification algorithms to extract the semantic information and enrich them with geometric data like object world positions and bounding boxes. The resulting semantic information is then mapped to the corresponding ontology classes of a T-Box ontology. Finally individuals of the corresponding classes are created to populate the ontology. |