Skip to the content

Viability of implementing data mining algorithms as a web service

Stent, C, Howard, N, Saraee, M and Thompson, E 2005, Viability of implementing data mining algorithms as a web service , in: International Symposium on Web Services and Applications, 20-23 June 2005, Las Vegas, USA.

[img]
Preview
PDF - Accepted Version
Download (56kB) | Preview
    [img] Microsoft Word - Accepted Version
    Restricted to Repository staff only

    Download (63kB) | Request a copy

      Abstract

      This paper describes an experiment into the viability of implementing data mining algorithms within a W3C standards compliant web service. The experiment shows that it can be done by the successful deployment of a prototype based on an implementation of the K-means clustering algorithm. The prototype produced demonstrates how the concept of a data-mining web-service can be a reliable and effective data-mining tool especially in environments where raw processing power is a valuable commodity. The slim-client to fat-server model is demonstrated effectively showing how a user armed with a simple web browser can potentially harness super computing power. In addition the foundation for the development of an advanced data-mining framework is presented which can include the implementation of any number of data mining techniques. The paper also seeks to highlight some ideas for future research and development of more sophisticate web services that are more scalable to suit both very specific tasks and very large datasets

      Item Type: Conference or Workshop Item (Paper)
      Themes: Media, Digital Technology and the Creative Economy
      Schools: Colleges and Schools > College of Science & Technology > School of Computing, Science and Engineering > Data Mining and Pattern Recognition Research Centre
      Journal or Publication Title: Proceedings of The 2005 International Symposium on Web Services and Applications, ISWS 2005, Las Vegas, Nevada, USA, June 27-30, 2005},
      Publisher: CSREA Press
      Refereed: Yes
      Related URLs:
      Depositing User: Dr Mo Saraee
      Date Deposited: 26 Oct 2011 12:19
      Last Modified: 20 Aug 2013 18:16
      URI: http://usir.salford.ac.uk/id/eprint/18668

      Actions (login required)

      Edit record (repository staff only)

      Downloads per month over past year

      View more statistics