Hybrid fast unsupervised feature selection for high-dimensional data
作者：
Highlights：
• Propose a new hybrid feature selection algorithm based on BACO and clustering.
• Modify linear binary ant system to reduce the search space complexity.
• Inject mutation to increase randomness of search space.
• Feature clustering to decrease the challenges of processing high-dimensional dataset.
• Experiment the method in several real-world social datasets and obtain more efficiency.
摘要
•Propose a new hybrid feature selection algorithm based on BACO and clustering.•Modify linear binary ant system to reduce the search space complexity.•Inject mutation to increase randomness of search space.•Feature clustering to decrease the challenges of processing high-dimensional dataset.•Experiment the method in several real-world social datasets and obtain more efficiency.
论文关键词：Feature selection,High-dimensional data,Binary ant system,Clustering,Mutation
论文评审过程：Received 8 March 2018, Revised 28 December 2018, Accepted 4 January 2019, Available online 16 January 2019, Version of Record 28 January 2019.
论文官网地址：https://doi.org/10.1016/j.eswa.2019.01.016
