Skip to content

TAMU-ESP/Data-Driven-Guided-Attention-for-Deep-Learning-Optimization

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 

Repository files navigation

Data-Driven Guided Attention for Analysis of Physiological Waveforms with Deep Learning

This respository hosts the research for the manuscript entitled, "Data-Driven Guided Attention for Analysis of Physiological Waveforms with Deep Learning". The repo is organized as follows:

  • Data Annotation - Hosts the files necessary for annotating the fiducial points for both the Bio-Z and MIMIC PPG modalities with Boosted-SpringDTW.
  • DDGA - Hosts the files necessary for running DDGA for the Personalized experiments and the Interpolation and Extrapolation experiments.
  • DDGA/Personalized/ - These experiments train on a given subjects data and test on the same subjects data.
  • DDGA/Interploation and Extrapolation/ - These experiments train on specific ranges of a person's BP data and tests on the remaining BP ranges.

DDGA/Personalized/ and DDGA/Interploation and Extrapolation/ contain the DDGA codes for each evaluated DL type for predicting DBP/SBP separately, for both Bio-Z and MIMIC.

About

Open-source code for CHIL 2022 submission.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages