eduzhai > Applied Sciences > Engineering >

Automate Obstructive Sleep Apnea Diagnosis Using Convolutional Neural Networks

  • Save

... pages left unread,continue reading

Document pages: 10 pages

Abstract: Identifying sleep problem severity from overnight polysomnography (PSG)recordings plays an important role in diagnosing and treating sleep disorderssuch as the Obstructive Sleep Apnea (OSA). This analysis traditionally is doneby specialists manually through visual inspections, which can be tedious,time-consuming, and is prone to subjective errors. One of the solutions is touse Convolutional Neural Networks (CNN) where the convolutional and poolinglayers behave as feature extractors and some fully-connected (FCN) layers areused for making final predictions for the OSA severity. In this paper, a CNNarchitecture with 1D convolutional and FCN layers for classification ispresented. The PSG data for this project are from the Cleveland Children sSleep and Health Study database and classification results confirm theeffectiveness of the proposed CNN method. The proposed 1D CNN model achievesexcellent classification results without manually preprocesssing PSG signalssuch as feature extraction and feature reduction.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×