ABSTRACT
Data stream mining is an important issue because it is the basis for numerous applications, such as network traffic, web searches, sensor network processing, and so on. Data stream mining aims to determine the patterns or structures of continuous data. Such patterns of structures may be used later to infer possible events that could occur. Data streams exhibit unique dynamics in that such data can be read only once. This feature presents a limitation to numerous traditional strategies from analyzing data streams because such techniques always assume that all data could be stored in limited storage. Thus, data stream mining could be considered as the performance of computations on a large amount of data or even unlimited data. In this chapter, we will introduce the basic concepts and main strategies that can be employed to address the aforementioned challenge.
