Fault-tolerant tile mining

作者：

Highlights：

• A new interestingness measure for data mining is proposed.

• Theoretical properties on the new problem are presented.

• Efficient branch-and-bound algorithms are developed.

• Extensive experimental studies on both synthetic and real datasets are conducted.

摘要

•A new interestingness measure for data mining is proposed.•Theoretical properties on the new problem are presented.•Efficient branch-and-bound algorithms are developed.•Extensive experimental studies on both synthetic and real datasets are conducted.

论文关键词：Itemset mining,Fault-tolerant,Optimization,Exact algorithm

论文评审过程：Received 19 May 2017, Revised 12 January 2018, Accepted 2 February 2018, Available online 8 February 2018, Version of Record 15 February 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.02.007