Fast online computation of the Qn estimator with applications to the detection of outliers in data streams

作者：

Highlights：

• We present FQN, a novel algorithm for online computation of the Qn estimator.

• We compare FQN to the state of the art algorithm by Nunkesser et al..

• We show that FQN outperforms the competing algorithm with regard to speed.

• We show that FQN is fully independent of the input distribution.

• The Qn estimator can be used for outlier detection.

摘要

•We present FQN, a novel algorithm for online computation of the Qn estimator.•We compare FQN to the state of the art algorithm by Nunkesser et al..•We show that FQN outperforms the competing algorithm with regard to speed.•We show that FQN is fully independent of the input distribution.•The Qn estimator can be used for outlier detection.

论文关键词：Data streams,Sliding window model,Qn estimator,Outliers

论文评审过程：Received 9 January 2020, Revised 28 March 2020, Accepted 31 July 2020, Available online 8 August 2020, Version of Record 11 August 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113831