A new framework for mining weighted periodic patterns in time series databases
作者：
Highlights：
• Developing a new weight-based framework for periodic pattern mining.
• Devising an efficient weighted periodic pattern mining algorithm with suffix trie.
• Different pruning strategies are introduced to accelerate the performance.
• Capable of mining symbol, partial, full-cycle periodicity in a single run.
• The results on real datasets show efficiency and effectiveness of our approach.
摘要
•Developing a new weight-based framework for periodic pattern mining.•Devising an efficient weighted periodic pattern mining algorithm with suffix trie.•Different pruning strategies are introduced to accelerate the performance.•Capable of mining symbol, partial, full-cycle periodicity in a single run.•The results on real datasets show efficiency and effectiveness of our approach.
论文关键词：Data mining,Time series databases,Periodic pattern,Weighted pattern,Suffix tree,Flexible pattern
论文评审过程：Received 10 August 2016, Revised 3 January 2017, Accepted 16 February 2017, Available online 20 February 2017, Version of Record 9 March 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.02.028
