Efficient and flexible algorithms for monitoring distance-based outliers over data streams

作者：

Highlights：

• We prove a linear space lower bound.

• A novel continuous algorithm is presented, which has two versions (COD).

• To support different views of outliers, we propose an extension (ACOD).

• We also propose algorithms based on micro-clusters (MCOD/AMCOD).

• Performance evaluation results based on both real-life and synthetic data.

摘要

Highlights•We prove a linear space lower bound.•A novel continuous algorithm is presented, which has two versions (COD).•To support different views of outliers, we propose an extension (ACOD).•We also propose algorithms based on micro-clusters (MCOD/AMCOD).•Performance evaluation results based on both real-life and synthetic data.

论文关键词：Stream data mining,Outlier detection

论文评审过程：Received 1 April 2014, Revised 22 April 2015, Accepted 7 July 2015, Available online 4 August 2015, Version of Record 27 August 2015.

论文官网地址：https://doi.org/10.1016/j.is.2015.07.006