流数据中一种高效剪枝的频繁序列挖掘算法

序列模式挖掘就是在时序数据库中挖掘相对时间或其他模式出现频率高的模式.序列模式发现是最重要的数据挖掘任务之一,并有着广阔的应用前景.针对静态数据库,序列模式挖掘已经被深入的研究.近年来,出现了一种新的数据形式:数据流.针对基于数据流的序列模式挖掘的研究还不是十分深入.提出一个有效的基于数据流的挖掘频繁序列模式的算法SSPM,利用到2个数据结构(F-list和Tatree)来处理基于数据流的序列模式挖掘的复杂性问题.SSPM的优点是可以最大限度地降低负正例的产生,实验表明SSPM具有较高的准确率.

Efficient Pruning Algorithm for Mining Frequent Sequential Pattern Based on Stream Data

Sequential pattern mining is to mine patterns that are frequent relative to time or other patterns in sequence database.It is one of the most important tasks of data mining and will have broad applications.In the recent years,a new form of data called data stream has emerged,but the studies of sequential pattern mining based on data streams is not very deep.In this paper,an effective method is introduced for mining sequential patterns from data streams,the SSPM(stream sequential pattern mining)method.Two data structures(F-list and Ta-tree)are used to handle the complexity of mining frequent sequential patterns in data streams.The excellence of the algorithm is that the reduction of the number of false positive can be maximized.Experimental results show that SSPM has higher accuracy.