Incremental classification using Feature Tree

In recent years, stream data have become an immensely growing area of research for the database, computer science and data mining communities. Stream data is an ordered sequence of instances. In many applications of data stream mining data can be read only once or a small number of times using limited computing and storage capabilities. Some of the issues occurred in classifying stream data that have significant impact in algorithm development are size of database, online streaming, high dimensionality and concept drift. The concept drift occurs when the properties of the historical data and target variable change over time abruptly in such a case that the predictions will become inaccurate as time passes. In this paper the framework of incremental classification is proposed to solve the issues for the classification of stream data. The Trie structure based incremental feature tree, Trie structure based incremental FP (Frequent Pattern) growth tree and tree based incremental classification algorithm are introduced in the proposed