Title: SMINER - a platform for data mining based on service-oriented architecture

Authors: Ahmed A.A. Esmin; Denilson Alves Pereira; Marluce Rodrigues Pereira; Deivison Luiz Araújo

Addresses: Department of Computer Science, Federal University of Lavras – UFLA, Campus Universitário – P.O. Box 3037, 37200-000, Lavras, MG, Brazil ' Department of Computer Science, Federal University of Lavras – UFLA, Campus Universitário – P.O. Box 3037, 37200-000, Lavras, MG, Brazil ' Department of Computer Science, Federal University of Lavras – UFLA, Campus Universitário – P.O. Box 3037, 37200-000, Lavras, MG, Brazil ' Department of Computer Science, Federal University of Lavras – UFLA, Campus Universitário – P.O. Box 3037, 37200-000, Lavras, MG, Brazil

Abstract: Data mining is a process to discover useful patterns in large volumes of data through the application of appropriated algorithms, tools, and techniques. However, building scalable, extensible, and easy-to-use data mining systems has proved to be a very difficult task. This paper presents the web platform called SMINER, which aims at interoperability and facility of integration in the development of data mining applications. The platform is based on the paradigm of service-oriented architecture (SOA) using the web services standard for extensibility and interoperability. This platform is composed of two main components: 1) web services, which implement data mining algorithms; 2) a user web interface, which can be used for modelling applications that use the services of the platform. Experimental results demonstrate that our SOA-based platform makes it easy to construct a flexible and scalable data mining system.

Keywords: service-oriented architecture; SOA; web services: data mining; interoperability; integration; extensibility; modelling.

DOI: 10.1504/IJBIDM.2013.055783

International Journal of Business Intelligence and Data Mining, 2013 Vol.8 No.1, pp.1 - 18

Received: 31 Oct 2012
Accepted: 27 Dec 2012
Published online: 28 Jun 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article