INCREASE PERFORMANCE BY COMBINING MODELS OF ANALYSIS ON REAL DATA

Dumitru Dan Burdescu, Marian Cristian Mihăescu

Abstract

In this paper we investigate several state-of-the-art methods of combining models of analysis. Data is obtained from an e-Learning platform and is represented by user’s activities like downloading course materials, taking tests and exams, communicating with professors and secretaries and other. Combining multiple models of analysis may have as result important information regarding the performance of the e-Learning platform regarding student’s learning performance or capability of the platform to classify students according to accumulated knowledge. This information may be valuable in adjusting platform’s structure, like number or difficulty of questions, to increase performance from presented points of view.

References

  1. Olivia Parr Rud, “Data Mining Cookbook - Modeling Data for Marketing, Risk, and Customer Relationship Management”, Wiley Computer Publishing, 2001.
  2. Jiawei Han, Micheline Kamber “Data Mining - Concepts and Techniques” Morgan Kaufmann Publishers, 2001.
  3. Ian H. Witten, Eibe Frank “Data Mining - Practical Machine Learning Tools and Techniques with Java Implementations” Morgan Kaufmann Publishers, 2000.
  4. R. Agrawal and R. Srikant, “Fast algorithms for mining association rules,” Proc. of the 20th VLDB Conference, pp. 487-499, Santiago, Chile, 1994.
  5. Nasraoui O., Joshi A., and Krishnapuram R., “Relational Clustering Based on a New Robust Estimator with Application to Web Mining,” Proc. Intl. Conf. North American Fuzzy Info. Proc. Society (NAFIPS 99), New York, June 1999.
  6. B. Mobasher, N. Jain, E-H. Han, and J. Srivastava “Web mining: Pattern discovery from World Wide Web transactions,” Technical Report 96-050, Universityof Minnesota, Sep, 1996.
  7. R. Quinlan. C4.5: Programs for Machine Learning, Morgan Kaufmann Publishers, San Mateo, CA, 1993.
  8. Schapire, R.E., Y. Freund, P. Bartlet, and W.S. Lee, “Boosting the margin: A new explanation for the effectiveness of voting methods”, Proc. Fourteenth International Conference on Machine Learning, Nashville, San Francisco, 1997.
  9. Wolpert, D.H., “Stacked generalization”, Neural Networks, 1992.
  10. http://stat257.central.ucv.ro/
  11. B. Cestnik, “Estimating probabilities: A Crucial Task in Machine Learning”, Proc. of European Conference on Artificial Inteligence, 1990.
  12. Ting, K.M. and Witten, I.H., “Stacked generalization: when does it work?” Proc International Joint Conference on Artificial Intelligence, pp. 866-871, Japan, August, 1997.
  13. Leo Breiman, “Stacked regression”, Machine Learning, Vol. 24, pp. 49-64, 1996.
  14. Michael LeBlanc, Robert Tibshirani, “Combining Estimates in Regression and Classification”, Technical Report 9318, Department of Statistics, University of Toronto, Canada, 1993.
Download


Paper Citation


in Harvard Style

Dan Burdescu D. and Cristian Mihăescu M. (2007). INCREASE PERFORMANCE BY COMBINING MODELS OF ANALYSIS ON REAL DATA . In Proceedings of the Second International Conference on Software and Data Technologies - Volume 1: ICSOFT, ISBN 978-989-8111-05-0, pages 255-258. DOI: 10.5220/0001331802550258


in Bibtex Style

@conference{icsoft07,
author={Dumitru Dan Burdescu and Marian Cristian Mihăescu},
title={INCREASE PERFORMANCE BY COMBINING MODELS OF ANALYSIS ON REAL DATA},
booktitle={Proceedings of the Second International Conference on Software and Data Technologies - Volume 1: ICSOFT,},
year={2007},
pages={255-258},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001331802550258},
isbn={978-989-8111-05-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Software and Data Technologies - Volume 1: ICSOFT,
TI - INCREASE PERFORMANCE BY COMBINING MODELS OF ANALYSIS ON REAL DATA
SN - 978-989-8111-05-0
AU - Dan Burdescu D.
AU - Cristian Mihăescu M.
PY - 2007
SP - 255
EP - 258
DO - 10.5220/0001331802550258