Service identification using k-NN machine learning

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    Web service categorization is a daunting task since it requires semantic descriptions of those services which are not provided to the majority of those websites. The proposal of a Semantic based automated service discovery requires a request from the user that can be analyzed which then provides the user with a list of related webs services based on the request that instigated the search. The problem with these service categorizations listed in the Universal description Discovery and Integration (UDDI) is the way the information is related to one another. The relations follow a syntactic method. Semantic based service descriptions is necessary for accurate web categorization. With the help of machine learning we can also predict the user’s service request automatically based on previous searches and also select the best web service for a particular request that the user has made using a k-nearest neighbor algorithm. By doing this we can distinguish between the various types of user requests, provide services that are suitable for that particular request as well as suggest other services that might potentially suit the needs of the user.

     

     


  • Keywords


    UDDI; Web Service; Clustering; Machine Learning; K-Nearest Neighbor.

  • References


      [1] Jian Ma, Wei Xu, Y.-H. S. E. T. S. W. and Liu, O. (2012). “An ontology based mining system.” IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICSâ˘A ˇ TPART A: SYSTEMS AND HUMANS, 42.

      [2] Aviv Segev, M. and Quan Z. Sheng, M. (2012). “Bootstrapping Ontologies for web services.” IEEE TRANSACTIONS ON SERVICES COMPUTING, five.

      [3] Tamer Ahmed Farrag, A. I. S. and Ali, H. A. (2013). “Toward SWSs discovery: Mapping from WSDL to OWL-S based on ontology search and standardization engine.” IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 25(5).

      [4] Danushka Bollegala, Y. M. and Ishizuka, M. (2011). “Automatic discovery of personal name aliases from the web.” IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 23.

      [5] Abinayal, G. and Jaishanthu, B. (2014). “Equipped search results using machine learning from web databases.” ICICES.

      [6] Marouane Kessentini, Hanzhang Wang, J. T. D. and Ouni, A. (2009). “Improving web services design quality using heuristic search and machine learning.” IEEE 24th International Conference on Web Services, 40, 883–891.

      [7] Jian Wang, Panpan GAO, P. G. Y. M. K. P. C. K. H. (2017). “A web service discovery approach based on common topic group’s extraction.” IEEE.

      [8] Rupasingha A. H. M. Rupasingha, I. P. and Kumara, B. T. G. S. (2015). “Calculating web service similarity using ontology learning with machine learning.” IEEE.

      [9] Aabhas V. Paliwal, Basit Shafiq, M. J. V. H. X. N. A. (2012). “Semantic based automated service discovery.” IEEE.

      [10] Payal A. Jadhav, D. P. N. C. and Wagh, K. P. (2016). “Integrating performance of web service engine with machine learning approach.” IEEE.

      [11] S. Ganesh Kumar, K Vivekanandan(2017) , “Intelligent Model View Controller Based Semantic Web Services call through Mishmash Text Featuring Technique” in Journal of Computational and Theoretical Nanoscience.


 

View

Download

Article ID: 13035
 
DOI: 10.14419/ijet.v7i2.4.13035




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.