Hybrid Ensemble Classifier for Stream Data

Data streams are continuous, unbounded, usually come with high speed and have a data distribution that often changes with time. It has different issues such as memory, time, Data Processing Model. There is need of handling data streams because of its changing nature, and the data stream may be labeled or it may be unlabelled. Classification is supervised it can only handle labeled data Thus, In this Paper a Hybrid Ensemble Classifier is proposed in which clustering and classifier are brought together. In this proposed method classification and clustering are combined. The clustering is used at this point because clustering can handle unlabelled data streams also. In this method Data stream is given as input then, with the help of windowing technique the large data stream is divided into small parts. This Paper describes new Hybrid Ensemble Classifier that will definitely improve the performance in terms of accuracy.