File(s) under permanent embargo
Mapping evolution of dynamic web ontologies
journal contribution
posted on 2023-05-19, 14:03 authored by Khattak, AM, Pervez, Z, Khan, WA, Khan, AM, Latif, K, Lee, SYInformation on the web and web services that are revised by stakeholders is growing incredibly. The presentation of this information has shifted from a representational model of web information with loosely clustered terminology to semi-formal terminology and even to formal ontology. Mediation (i.e., mapping) is required for systems and services to share information. Mappings are established between ontologies in order to resolve terminological and conceptual incompatibilities. Due to new discoveries in the field of information sharing, the body of knowledge has become more structured and refined. The domain ontologies that represent bodies of knowledge need to be able to accommodate new information. This allows for the ontology to evolve from one consistent state to another. Changes in resources cause existing mappings between ontologies to be unreliable and stale. This highlights the need for mapping evolution (regeneration) as it would eliminate the discrepancies from the existing mappings. In order to re-establish the mappings between dynamic ontologies, the existing systems require a complete mapping process to be restructured, and this process is time consuming. This paper proposes a mapping reconciliation approach between the updated ontologies that has been found to take less time to process compared to the time of existing systems when only the changed resources are considered and also eliminates the staleness of the existing mappings. The proposed approach employs the change history of ontology in order to store the ontology change information, which helps to drastically reduce the reconciliation time of the mappings between dynamic ontologies. A comprehensive evaluation of the performance of the proposed system on standard data sets has been conducted. The experimental results of the proposed system in comparison with six existing mapping systems are provided in this paper using 13 different data sets, which support our claims.
History
Publication title
Information SciencesVolume
303Pagination
101-119ISSN
0020-0255Department/School
School of EngineeringPublisher
Elsevier Science IncPlace of publication
360 Park Ave South, New York, USA, Ny, 10010-1710Rights statement
Copyright 2015 Elsevier Inc.Repository Status
- Restricted