Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/463282Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Kamsuriah bt Ahmad, Prof. Madya Dr. | |
| dc.contributor.author | Majid Razmjoo (P53658) | |
| dc.date.accessioned | 2023-09-25T09:20:46Z | - |
| dc.date.available | 2023-09-25T09:20:46Z | - |
| dc.date.issued | 2014-04-03 | |
| dc.identifier.other | ukmvital:75257 | |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/463282 | - |
| dc.description | The Semantic web is a web of data that can be processed directly by machines. It enables automated agents to access the web more intelligently and perform tasks on behalf of users. Ontology is a formal, explicit specification of a shared conceptualization in terms of classes, attributes and relations. Different ontologies in a same domain are designed by different experts therefore it causes the semantic heterogeneity problem. For example, two hotels namely domains A and B, which have their own ontologies to represent their meaning and each of them uses their own classes, relations and attributes features. Interoperability between these ontologies are challenging problem in semantic web when the ontology needs to map with each other. The process of ontology mapping is to find semantic correspondences between similar elements in two different ontologies. There are many automatic approaches exist to map these ontologies however; the mapping result still can be improved in terms of its accuracy. Therefore the main aim of this research is to propose a new method to improve the accuracy in the mapping result. The proposed method used a new lexical similarity measurement trough cosine similarity and Jaro-Winkler distance. A tool is developed based on this proposed method. The methodology used in this study consists of four phases: First, two different ontologies are parsed to perform pre-processing of removing stop words and tokenizing. Second, lexical similarity between elements are calculated based on new similarity measure which convert all lexical information of entity's using word pool and find similarity between them by using cosine similarity and Jaro-Winkler Distance. Third, structural similarity for nodes is calculated and finally, the equality mapping between each pair of elements is considered based on the calculated similarities. The proposed method is tested by using Ontology Alignment Evaluation Initiative (OAEI) 2011 datasets in terms of precision, recall, and f-measure to test the accuracy of the mapping result. The result is compared with the result of other ontology mapping method. Obtained results demonstrate that the proposed method has 7% f-Measure improvement on OAEI 301 to 304 datasets when compare to other ontology mapping tools result.,Master/Sarjana | |
| dc.language.iso | eng | |
| dc.publisher | UKM, Bangi | |
| dc.relation | Faculty of Science and Technology / Fakulti Sains dan Teknologi | |
| dc.rights | UKM | |
| dc.subject | Ontology mapping | |
| dc.title | An ontology mapping method in semantic web using cosine similarity and jaro-wrinkler distance | |
| dc.type | theses | |
| dc.format.pages | 108 | |
| dc.identifier.callno | TK5105.88815.R339 2014 tesis | |
| dc.identifier.barcode | 001213 | |
| dc.identifier.barcode | 003147 (2014 | |
| Appears in Collections: | Faculty of Science and Technology / Fakulti Sains dan Teknologi | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ukmvital_75257+Source01+Source010.PDF Restricted Access | 1.85 MB | Adobe PDF |  View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.