Browsing by Author "Khedr, Ayman E"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Cross Language Information Retrieval Model For Discovering WSDL Documents Using Arabic Language Query
    (SCIENCE & INFORMATION SAI ORGANIZATION LTD, 2013-08) Alsheref, Fahad Kamal; Khedr, Ayman E; Sultan, Torkey I
    Web service discovery is the process of finding a suitable Web service for a given user's query through analyzing the web service's WSDL content and finding the best match for the user's query. The service query should be written in the same language of the WSDL, for example English. Cross Language Information Retrieval techniques does not exist in the web service discovery process. The absence of CLIR methods limits the search language to the English language keywords only, which raises the following question "How do people that do not know the English Language find a web service, This paper proposes the application of CLIR techniques and IR methods to support Bilingual Web service discovery process the second language that proposed here is Arabic. Text mining techniques were applied on WSDL content and user's query to be ready for CLIR methods. The proposed model was tested on a curated catalogue of Life Science Web Services http://www.biocatalogue.org/ and used for solving the research problem with 99.87 % accuracy and 95.06 precision
  • Thumbnail Image
    Item
    A proposed configurable approach for recommendation systems via data mining techniques
    (TAYLOR & FRANCIS LTD, 2018) El-Shewy, Samir; Hegazy, Abd El-Fatah; Idrees, Amira M; Khedr, Ayman E
    This study presents a configurable approach for recommendations which determines the suitable recommendation method for each field based on the characteristics of its data, the method includes determining the suitable technique for selecting a representative sample of the provided data. Then selecting the suitable feature weighting measure to provide a correct weight for each feature based on its effect on the recommendations. Finally, selecting the suitable algorithm to provide the required recommendations. The proposed configurable approach could be applied on different domains. The experiments have revealed that the approach is able to provide recommendations with only 0.89 error rate percentage.