Personal sleep pattern visualization using sequence-based kernel self-organizing map on sound data

作者：

Highlights：

• A novel approach to discover the sleep pattern through analyzing the sleep-related sound events based on kernelized sequence-based self-organizing map algorithms is proposed.

• Compare to traditional method for sleep analysis like PSG, this method is more economical and easier to apply.

• The consistency of this method with the medical evidence from PSG proves its reliability.

• Relationship between sleep related sound events and sleep stages is confirmed.

摘要

•A novel approach to discover the sleep pattern through analyzing the sleep-related sound events based on kernelized sequence-based self-organizing map algorithms is proposed.•Compare to traditional method for sleep analysis like PSG, this method is more economical and easier to apply.•The consistency of this method with the medical evidence from PSG proves its reliability.•Relationship between sleep related sound events and sleep stages is confirmed.

论文关键词：Sleep pattern,Sound data,Self-organizing map,Pairwise F-measure,Polysomnography,Sleep stage

论文评审过程：Received 11 November 2016, Revised 29 June 2017, Accepted 29 June 2017, Available online 11 July 2017, Version of Record 7 September 2017.

论文官网地址：https://doi.org/10.1016/j.artmed.2017.06.012