Ensemble methods

Ensemble methods include four strategies which can obtain samples of ensemble individual learners

There are four ensemble strategies--- random selecting samples, Bagging strategy, Random subspace method, Rotation forest method. They are ensemble methods which can obtain the samples of individual learner. Bagging method is a classical ensemble strategy proposed by Leo Breiman in Ref [L.Breiman. Bagging Predictors. Machine learning, vol.24(2), pp.123-140, 1996.]. Random subspace method is proposed by Tin Kam Ho in Ref [Ho T.K.. The Random Subspace Method for Constructing Decision Forests. IEEE Transactions on pattern analysis and Machine Intelligence, vol.20(8), pp.832-844, 1998.]. Rotation forest method is better than bagging, random subspace, adaboost methods and so on, which is proposed by Juan J. Rodriguez and Ludmila I. Kuncheva in Ref [J.J. Rodriguez, L.I. Kuncheva. Rotation Forest: A New Classifier Ensemble Method. IEEE transactions on Pattern Analysis and Machine Intelligence, vol.28(10), pp.1619-1630, October, 2006.].