Multiple Classifiers Combination Based on Specialists´ FIelds

This paper proposes a new method to combine the predictions of different classifiers in order to improve the error rate of a single classifier. The method consists of training different classifiers plus an integration mechanism that for a given case (to be classified) selects the best classifier (the Specialist) that should classify it. The idea of our model is derived from diagnosing flow in hospital. At first, n methods are adopted to train single classifier and gain n classifiers, and every classifier is called as Specialist. Then using the training set to test every Specialist, we gain n Specialists¿ fields according the result of classification of every Specialist. For an unknown sample, we assign it to which Specialist¿s field it belongs to, and select the Specialist on that field to classify this sample. We use UCI standard datasets to test our model, according to experiments our algorithm leads to less error and better performance than other algorithms.