Feature selection with limited bit depth mutual information for portable embedded systems

作者：

Highlights：

• Development and commercialization of IoT devices is growing expansively.

• Increased interest in implementing ML algorithms with reduced precision parameters.

• Selecting the relevant features becomes indispensable to analyze the human behavior.

• Mutual information using reduced precision parameters within a FS procedure.

摘要

•Development and commercialization of IoT devices is growing expansively.•Increased interest in implementing ML algorithms with reduced precision parameters.•Selecting the relevant features becomes indispensable to analyze the human behavior.•Mutual information using reduced precision parameters within a FS procedure.

论文关键词：Reduced precision,Mutual information,Feature selection,Portable embedded systems,Internet of things,Edge computing

论文评审过程：Received 9 October 2019, Revised 24 March 2020, Accepted 5 April 2020, Available online 10 April 2020, Version of Record 24 April 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.105885