Rapid and brief communication: FuzzyBagging: A novel ensemble of classifiers

作者: Loris Nanni , Alessandra Lumini

DOI: 10.1016/J.PATCOG.2005.10.002

关键词: Probabilistic classificationRandom subspace methodCascading classifiersEnsemble learningClassifier (UML)Margin classifierArtificial intelligenceTraining setMachine learningComputer scienceQuadratic classifierPattern recognition

摘要: In this work, a new method for the creation of classifier ensembles is introduced. The patterns are partitioned into clusters to group together similar patterns, training set built using that belong cluster. Each sets used train classifier. We show approach here presented, called FuzzyBagging, obtains performance better than Bagging.

参考文章(4)
C. L. Blake, UCI Repository of machine learning databases www.ics.uci.edu/〜mlearn/MLRepository.html. ,(1998)
Yves Grandvalet, Bagging Equalizes Influence Machine Learning. ,vol. 55, pp. 251- 270 ,(2004) , 10.1023/B:MACH.0000027783.34431.42
Leo Breiman, Bagging predictors Machine Learning archive. ,vol. 24, pp. 123- ,(1996) , 10.1023/A:1018054314350