Wrappers for web access logs feature selection

ABSTRACT

The Web Usage Mining (WUM), a rather recent research field, corresponds to the process of knowledge discovery from databases (KDD) applied to the Web usage data. The quantity of the Web usage data to be analyzed and its poor quality (in particular the abundance of features to be analyzed) are the main problems in WUM.

Considering the characteristics of Web log data and functions of every phase included in data preprocessing, this paper establishes a Web log data preprocessing algorithm based on feature selection. The implemented Wrapper Evaluation feature selection method use a Best First Search and a Greedy Stepwise Search and evaluate each of the attribute subsets according to Support Vector Machine learning scheme.

References

1. Chang-bin, J., Li, C. 2010. Web Log Data Preprocessing Based on Collaborative Filtering, 2010 Second International Workshop on Education Technology and Computer Science, Wuhan, China, ISBN: 978-1-4244-6388-6, pp. 118--121.
2. Alam Ansari, S., Chattopadhayay, A., Das, S. 2010. A Kernel level VFS logger for building efficient file system Intrusion Detection System, Second International Conference on Computer and Network Technology, Bangkok, Thailand, ISBN: 978-0-7695-4042-9, pp.273--279, ACM doi 10.1109/ICCNT.2010.47.
3. Hernandez, P., Garrigos, I., and Mazon, J.-N. 2010. Modeling Web logs to enhance the analysis of Web usage data, 2010 Workshops on Database and Expert Systems Applications, Bilbao, Spain, ISBN: 978-0-7695-4174-7, pp. 297--301, ACM doi 10.1109/DEXA.2010.65.
4. Witten, I. H. and Frank, E. 2005. Data Mining, Practical Machine Learning Tools and Techniques, Morgan Kaufmann Publishers, Elsevier Inc., pp. 290.
5. Mitchell, T. 1997. Machine Learning, The McGraw-Hill Companies, Inc., pp. 52--78.
6. Sun, Y., Todorovic, S. and Goodison, S. 2010. Local-Learning-Based Feature Selection for High-Dimensional Data Analysis, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 32, No. 9, September 2010, pp. 1610--1626.
7. Kohavi, R. 1995. Wrappers for Performance Enhancement and Oblivious Decision Graphs, PhD thesis, Stanford University.
8. Arlot, S., Celisse. 2010. A., A survey of cross-validation procedures for model selection, Statistics Surveys, Vol. 4 (2010) 40--79, ISSN: 1935--7516, pp.52.
9. Vapnik, V N. 2000. The nature of statistical learning theory, New York: Springer-Verlag.
10. Joachims, I. 1998. Text categorization with Support Vector Machines: Learning with many relevant features, Proceedings of the European Conference on Machine Learning, Berlin: Springer.
11. Yang, X., Guan, H., Tang, F., You, I., Guo, M., Shen, Y. 2011. Improvements on Sequential Minimal Optimization Algorithm for Support Vector Machine based on Semi-sparse Algorithm, 2011 Fifth International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing, ISBN: 978-1-61284-733-7, Seoul, Korea, pp. 192--199.
12. Lu, K., Wang, L. 2011. A Novel Nonlinear Combination Model Based on Support Vector Machine for Rainfall Prediction, 2011 Fourth International Joint Conference on Computational Sciences and Optimization, Kunming, Yunnan, China, ISBN: 978-1-4244-9712-6, pp. 1343--1346.
13. Zhu, F., Ye, N., Pan, D., Ding, W. 2011. Incremental Support Vector Machine Learning: an Angle Approach, 2011 Fourth International Joint Conference on Computational Sciences and Optimization, Kunming, Yunnan, China, ISBN: 978-1-4244-9712-6, pp. 288--292.
14. Morariu, D., Vintan, L., Tresp, V. 2006. Feature Selection Methods for an Improved SVM Classifier, Proceedings of 14th International Conference on of Intelligent Systems (ICIS06), ISSN: 1305--5313 Volume 14,(pp. 83--89), Prague.
15. J. Quinlan, 1993. C4.5: Programs for Machine Learning, Morgan Kaufmann.
16. Han, J., Kamber, M., Data Mining: Concepts and Techniques, Second Edition, Morgan Kaufmann Press, Elsevier Inc., San Francisco, 2006, pp. 402.

Index Terms

• Information systems

  • World Wide Web

    • Web applications

    • Web services