*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title: Automatic Spectral-temporal Modality based EEG Sleep Staging
Committee:
Dr. Clements, Advisor
Dr. Barnes, Chair
Dr. Romberg
Abstract: The objective of the proposed research is to investigate a method for sleep state classification using a modality based sparse denoising approach. This method is designed to identify and enhance global structure in dense spectrograms from single channel EEG recordings by viewing the spectrum as a collection of temporal-spectral regions with a roughly block-constant representation organized in an irregular grid. This signal model permits recovering this global structure in the presence of frequent artifacts and high levels of noise. Unlike prior work, this method does not impose a model of fixed frequency bands within the analysis, but it adapts to different global structures in each subject's recording. The goal of this investigation is to further investigate the relative performance of this approach under increased noise and across different datasets when compared to previously published methods.
