Affiliations 

  • 1 Department of Computer, Islamic Azad University, Mobarakeh Branch, Esfahan, Iran; Faculty of Computing, Universiti Teknologi Malaysia (UTM), Johor, Malaysia
  • 2 Advanced Informatics School (AIS), Universiti Teknologi Malaysia (UTM), Kuala Lumpur, Malaysia
  • 3 Faculty of Computing, Universiti Teknologi Malaysia (UTM), Johor, Malaysia
PLoS One, 2014;9(8):e104735.
PMID: 25157872 DOI: 10.1371/journal.pone.0104735

Abstract

In this paper, a Semantic Web service matchmaker called UltiMatch-NL is presented. UltiMatch-NL applies two filters namely Signature-based and Description-based on different abstraction levels of a service profile to achieve more accurate results. More specifically, the proposed filters rely on semantic knowledge to extract the similarity between a given pair of service descriptions. Thus it is a further step towards fully automated Web service discovery via making this process more semantic-aware. In addition, a new technique is proposed to weight and combine the results of different filters of UltiMatch-NL, automatically. Moreover, an innovative approach is introduced to predict the relevance of requests and Web services and eliminate the need for setting a threshold value of similarity. In order to evaluate UltiMatch-NL, the repository of OWLS-TC is used. The performance evaluation based on standard measures from the information retrieval field shows that semantic matching of OWL-S services can be significantly improved by incorporating designed matching filters.

* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.