一种与缓冲区紧耦合的环形循环滑动窗口的数据流抽取算法  

An Algorithm for Data Stream Sampling Based on Ring Circular Sliding Window Tightly-Coupled with Buffer

作　　者：詹英[1] 吴春明[2] 王宝军[1] 

机构地区：[1]浙江交通职业技术学院 [2]浙江大学系统工程研究所

出　　处：《电子学报》2011年第4期894-898,共5页Acta Electronica Sinica

基　　金：浙江省自然科学基金(No.Y1101133);浙江省教育厅项目(No.Y201018946)

摘　　要：许多应用领域产生数据流的流量不断增大,需要挖掘系统提供更有效的数据流抽取策略来应对数据处理能力与流速之间的矛盾.本文构造了基于环形缓冲区循环的逻辑滑动窗口(环形循环滑动窗口),将环形缓冲区和环形循环滑动窗口紧耦合,提出了基于环形循环滑动窗口的数据流抽取算法.实验表明这是适合数据流流动和方便数据流挖掘的数据流抽取模型,能够提升数据流抽取速度和保证数据流的挖掘持续正常实施.Stream data are generated unboundedly,coping with the conflicts commendably between data processing power and flow velocity may require mining system to provide a more effective solution for Data Stream Sampling.This paper proposed a logical sliding window named ring circular sliding window based on a ring buffer and these two elements were tightly coupled.Then an algorithm for data stream sampling based on ring circular sliding window was proposed.Experimental results show that it is a data stream sampling model which is proper for the migration and mining of data stream,and can achieve further improvement on the speed of data stream sampling and ensure normal execution of data stream mining.

关 键 词：数据流 环形循环滑动窗口 环形缓冲区 多线程 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]