An Ensemble Method of Adaptive Multiple Classifiers

With AdaBoost being constructed, base classifiers are more and more concentrating on instances which are difficult to classify. And base classifiers are only favourite to these instances. After a base classifier is constructed, it´s voting weight for final decision is determined and be the same to all test instances no matter which class a test instance belongs to. Considering these problems, the paper proposes an improved AdaBoost algorithm called AMC (An Ensemble Method of Adaptive Multiple Classifiers), which gains training set with stratified weighted sampling at first and then combines base classifiers with adaptive weight. Experiment shows the AMC has a higher accuracy to the given data set and produces higher value of recall rate and precision.