数据流变化检测研究综述

Survey on change detection over data stream

数据流是一种动态数据,它在某种因素的驱动下可能会随时间发生变化,而这种变化往往隐含着现实世界的某种事件。如何及时、准确地发现数据流中的变化已成为数据流挖掘的一个研究热点,并且在实际中有非常广泛的应用。描述了数据流变化及变化检测的核心任务,归纳了变化检测的通用框架,分析评价了目前已知的数据流变化检测方法及其技术特点,最后展望了数据流变化检测技术的发展方向。

Data stream is a type of dynamic data, which is driven by some hidden contexts and may change with time. Generally speaking, the change implies some event in the real world. To detect change over data stream timely and accurately has a quite wide range of practical applications, and has been one of the hot topics in data stream mining. In this paper, a comprehensive survey on data stream change detection was presented, and the key task of change detection was introduced. An inductive unifying framework of change detection process was also given. Besides, a variety of already existing change detection approaches and their features were reviewed and evaluated in detail. Finally, the research outlook of data stream change detection was discussed.