Automatic ensemble feature selection using fast non-dominated sorting
作者:
Highlights:
• We proposed ATFS, an ensemble feature selection method, which uses non-dominated sorting as combination method.
• ATFS finds the threshold value automatically and selects informative features for each dataset.
• We proposed SLI, a new filter method based on interference between class labels, with capability of dealing with high dimensional datasets.
摘要
•We proposed ATFS, an ensemble feature selection method, which uses non-dominated sorting as combination method.•ATFS finds the threshold value automatically and selects informative features for each dataset.•We proposed SLI, a new filter method based on interference between class labels, with capability of dealing with high dimensional datasets.
论文关键词:Ensemble feature selection,Fast non-dominated sorting,Automatic threshold
论文评审过程:Received 22 January 2020, Revised 19 February 2021, Accepted 1 March 2021, Available online 12 March 2021, Version of Record 19 March 2021.
论文官网地址:https://doi.org/10.1016/j.is.2021.101760