Proposal of a new stability concept to detect changes in unsupervised data streams
作者：
Highlights：
• We propose a new stability concept for unsupervised data streams.
• The concept is based on ideas from time series analysis.
• A stable algorithm is introduced for change detection in unsupervised streams.
• Experiments provide insights on how the stability concept work in several scenarios.
• Results show our change detection algorithm correctly detects changes on a stream.
摘要
•We propose a new stability concept for unsupervised data streams.•The concept is based on ideas from time series analysis.•A stable algorithm is introduced for change detection in unsupervised streams.•Experiments provide insights on how the stability concept work in several scenarios.•Results show our change detection algorithm correctly detects changes on a stream.
论文关键词：Data streams,Unsupervised change detection,Surrogate stability,Surrogate data
论文评审过程：Available online 21 June 2014.
论文官网地址：https://doi.org/10.1016/j.eswa.2014.06.031
