Top-k Parametrized Boost

  • Turki Turki
  • Muhammad Ihsan
  • Nouf Turki
  • Jie Zhang
  • Usman Roshan
  • Zhi Wei
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8891)

Abstract

Ensemble methods such as AdaBoost are popular machine learning methods that create highly accurate classifier by combining the predictions from several classifiers. We present a parametrized method of AdaBoost that we call Top-k Parametrized Boost. We evaluate our and other popular ensemble methods from a classification perspective on several real datasets. Our empirical study shows that our method gives the minimum average error with statistical significance on the datasets.

Keywords

Ensemble methods AdaBoost statistical significance 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Maclin, R., Opitz, D.: Popular ensemble methods: An empirical study. arXiv preprint arXiv:1106.0257 (2011)Google Scholar
  2. 2.
    Freund, Y., Schapire, R.E.: A desicion-theoretic generalization of on-line learning and an application to boosting. In: Vitányi, P.M.B. (ed.) EuroCOLT 1995. LNCS, vol. 904, pp. 23–37. Springer, Heidelberg (1995)CrossRefGoogle Scholar
  3. 3.
    Tan, P.N., Steinbach, M., Kumar, V.: Introduction to Data Mining, 1st edn. Addison-Wesley Longman Publishing Co., Inc., Boston (2005)Google Scholar
  4. 4.
    Mohri, M., Rostamizadeh, A., Talwalkar, A.: Foundations of machine learning. MIT press (2012)Google Scholar
  5. 5.
    Japkowicz, N., Shah, M.: Evaluating Learning Algorithms. Cambridge University Press (2011)Google Scholar
  6. 6.
    Asuncion, A., Newman, D.J.: UCI machine learning repository (2007)Google Scholar
  7. 7.
    Breiman, L.: Random forests. Machine Learning 45, 5–32 (2001)CrossRefMATHGoogle Scholar
  8. 8.
    Kanji, G.K.: 100 statistical tests. Sage (2006)Google Scholar
  9. 9.
    Liaw, A., Wiener, M.: Classification and regression by randomforest. R News 2, 18–22 (2002)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Turki Turki
    • 1
    • 4
  • Muhammad Ihsan
    • 2
  • Nouf Turki
    • 3
  • Jie Zhang
    • 4
  • Usman Roshan
    • 4
  • Zhi Wei
    • 4
  1. 1.Computer Science DepartmentKing Abdulaziz UniversityJeddahSaudi Arabia
  2. 2.Department of Electrical EngineeringStanford UniversityStanfordUnited States
  3. 3.King Abdulaziz UniversityJeddahSaudi Arabia
  4. 4.Department of Computer Science, New Jersey Institute of TechnologyUniversity HeightsNewarkUSA

Personalised recommendations