Date on Master's Thesis/Doctoral Dissertation

12-2004

Document Type

Master's Thesis

Degree Name

M.S.

Department

Computer Engineering and Computer Science

Committee Chair

Kumar, Anup

Subject

Data mining

Abstract

With the increasing computational power and the decreasing cost of high bandwidth networks resulted in Distibuted Systems. Distributed Data Mining is being used to analyze and monitor data in distributed systems. In the past, distributed technologies like Java RMI, CORBA were used for data mining but the result was a more tightly coupled system. Using web services a loosely coupled, interoperable distributed computing framework can be built. The topic of this thesis is to investigate the use of web service in distributed data mining. This thesis involves the design, development and implementation of distributed data mining using web services as well as an in-depth look at technical aspects and future implication of such framework. A working framework will be created allowing a user to dynamically locate and run mining algorithms on data services or vice versa. The algorithm and data will be deployed as web services. The created web services will be registered at public registry servers. Two distributed data mining architectures will be presented, Data to Algorithm and Algorithm to Data. Finally, performance of the both the architectures will be compared with varying data using different public registry servers.

Share

COinS