Feature Selection for Classifying Data Stream Based on Maximum Entropy

Feature select ion is an important problem in the fields of machine learning and pat tern recognition. Data stream data classification with high dimensional and sparse, and the dimension of the need for compression, feature selection methods suitable for data stream classification study of very value of this area is currently a lack of in-depth study. This paper summarizes the current data flow classification feature selection research, analysis of the characteristics of different methods. Based on the principle of maximum entropy, naive Bayes with the technology on the data stream tuple feature selection attributes, divided into two different subsets of the merits, so as to enhance the work of C4.5 classifier results, the experiment proved not only StreamMEFS classification of time-saving, but also to improve the quality of the classification.