数据流中异常模式的提取与趋势监测

Extraction and Trend Detection of Unusual Patterns over Data Streams

研究的重点是数据流环境中异常模式的提取与趋势监测 主要贡献包括 :①提出了一个进行异常模式发现的度量框架———强度比率 ,为异常模式挖掘提供了度量标准 ;②在基于异常模式求取的基础上 ,提出了利用回归分析方法———最小二乘法进行异常模式趋势监测 实验结果表明 ,提出的异常模式度量和求取算法是合理的 ,提出的趋势监测方法是有效的。

In this paper, emphasis is put on a hot topic abnormal behavior analysis, named unusual pattern extraction and trend detection Contributions of this paper include: (1) A new framework ratio of feature strength for unusual pattern extraction is proposed, which provides a standard for unusual pattern mining; (2) Based on the extraction of unusual pattern, a method for trend detection of unusual pattern is also proposed by using least square regression method The performance study shows that the framework of unusual pattern measurement and algorithm is reasonable, and the proposed trend detection method is executable and efficient