Heuristic based Improvements for Effective Random Forest Classifier

@inproceedings{Kulkarni2013HeuristicBI,
  title={Heuristic based Improvements for Effective Random Forest Classifier},
  author={Vrushali Y. Kulkarni and Dr Kaushal K. Sinha and Asshu Singh and Farah D. Shaikh and Mehul Mittal},
  year={2013}
}
Random Forest is an ensemble supervised machine learning technique. Based on bagging and random feature selection, number of decision trees (base classifiers) is generated and majority voting is taken for classification. In this paper, we are presenting some heuristic based improvements towards effective learning of Random Forest classifier. These efforts include disjoint partitions of datasets for learning of base trees, reducing depth of base trees by avoiding repetitive selection of… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 11 REFERENCES

Dynamic Random Forests

  • Pattern Recognition Letters
  • 2012
VIEW 1 EXCERPT

Pruning of Random Forest classifiers: A survey and future directions

  • 2012 International Conference on Data Science & Engineering (ICDSE)
  • 2012
VIEW 1 EXCERPT

Search for the smallest Random Forest

Heping Zhang, Minghui Wang
  • Statistics and Its Interface Volume
  • 2009
VIEW 1 EXCERPT

Decastecker, “Limiting the number of trees in Random Forest

P. Latinne, C. O. Debeir
  • 2001
VIEW 1 EXCERPT

Bagging predictors

  • Machine Learning
  • 1996
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…