An unsupervised method to determine the optimal number of independent components

作者：

Highlights：

• A new approach to find the optimal number of independent components is presented.

• This approach uses the JADE algorithm to calculate the independent components.

• The method is tested using synthetic mixed signals.

摘要

•A new approach to find the optimal number of independent components is presented.•This approach uses the JADE algorithm to calculate the independent components.•The method is tested using synthetic mixed signals.

论文关键词：Distance correlation,ICA,JADE algorithm,Linear correlation,Optimal number of independent components

论文评审过程：Received 20 October 2016, Revised 17 January 2017, Accepted 18 January 2017, Available online 20 January 2017, Version of Record 28 January 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.01.015