![](bgb.png)
map and then predict the type and pattern of the new user. The goal of predicting the
new user is to determine the required reservation services. Connected home machine
devices scenario is adopted to demonstrate the idea of classifying Users according to
the devices usage.
Job schedule will be used to complete the scenario of services reservation, and
then manage the load. SOM technique is also used to do the middleware self-
management process. Other types of machine learning (like SVM [16, 17]) will be test
in the future to do the classification process. For the future, this environment will be
developed to be as a web services that can be added to OGSA middleware services.
The idea of autonomic monitor will be develop in the future stages to predict the
type of data that is needed by the autonomic services. Also, it will be used to reduce
the amount of unnecessary data that is transfer from the target to the log file system
References
1. V. Berstis, Fundamentals of Grid Computing, 2002.
2. M. Y. Chen, E. Kıcıman, E. Fratkin, A. Fox, and E. Brewer, Pinpoint: Problem
Determination in Large, Dynamic Internet Services, 2002.
3. M. LaMonica. IBM draws self-management blueprint, April 2003.
4. M. Chen, A. X. Zheng, J. Lloyd, M. I. Jordan and E. Brewer, Failure Diagnosis Using
Decision Trees. 2004.
5. G. Candea, M. Delgado, M. Chen and A. Fox, Automatic Failure-Path Inference: A Generic
Introspection Technique for Internet Applications, June 2003.
6. M. Y. Chen, A. Accardi, E. Kıcıman, J. Lloyd, D. Patterson, A. Fox and E. Brewer, Path-
Based Failure and Evolution Management, 2003
7. U. Heuser, J. Goppert, W. Rosenstiel and A. Stevens, Classification of Human Brain Waves
using Self-Organizing Maps, August 1996
8. N. N. Schraudolph and T. J. Sejnowski, Competitive Anti-Hebbian Learning of Invariants,
1992.
9. R. H. White, Competitive Hebbian Learning 2: an Introduction, 1992.
10. J. Vesanto, Using SOM in Data Mining. Licentiate’s thesis. Thesis for the degree of
Licentiate of Science in Technology, Supervisors: Professor Olli Simula, Professor Samuel
Kaski, Espoo, Finland 17th April 2000.
11. R. Pollock, T. Lane and M. Watts, A Kohonen Self-Organizing Map for the functional
classification of proteins based on one-dimensional sequence information, 2001.
12. E. Bingham, J. Kuusisto and K. Lagus, ICA and SOM in Text Document Analysis, August,
2002.
13. Haynos, J.U.a.M., A visual tour of Open Grid Services Architecture, August 2003.
14. J. Vesanto, J. Himberg, E. Alhoniemi and J. Parhankangas, Self-Organizing Map in Matlab:
the SOM Toolbox. In proceedings of the Matlab DSP Conference 1999, Espoo, Finland, pp.
35-40, 1999.
15. T. Joachims, Text Categorization with Support Vector Machine: Learning With Many
Relevant Features. ECML-98. 10th European Conference on Machine Learning,
Heidelberg, Germany, 1998.
16. C. Hsu, C. Chang, and C. Lin, A Practical Guide to Support Vector Classification, 2003.
17. D. Arnaud, Study of a document classification framework using Self-Organizing Maps,
October 1, 2003
18. T. Kohonen, The Self-Organizing Map (SOM). October, 2000.
http://www.cis.hut.fi/projects/somtoolbox/theory/somalgorithm.shtml
19.
http://www.cs.toronto.edu/~delve/methods/knn-class-1/knn-class-1.html
99