An Ensemble Classification Algorithm Based on Information Entropy for Data Streams

Data stream mining has attracted much attention from scholars. In recent researches, ensemble classification has been wide aplied in concept drift detection; however, most of them regard classification accuracy as a criterion for judging whether concept drift happens or not. Information entropy is an important and effective method for measuring uncertainty. Based on the information entropy theory, a new algorithm using information entropy to evaluate a classification result is developed. It utilizes the methods of ensemble learning and the weight of each classifier is decided by the entropy of the result produced by an ensemble classifiers system. When the concept in data stream changes, the classifiers whose weight are below a predefined threshold will be abandoned to adapt to a new concept. In the experimental analysis, the proposed algorithm and six comparision algorithms are executed on six experimental data sets. The results show that the proposed method can not only handle concept drift effectively, but also have a better performance than the comparision algorithms.