8000 GitHub - root292/SACD: A cross-modal distillation method based on infrared video and EEG signals · GitHub
[go: up one dir, main page]

Skip to content
root292Public
forked from SPIresearch/SACD

About

A cross-modal distillation method based on infrared video and EEG signals

Resources

Stars

0 stars

Watchers

0 watching

Forks

 
 

Latest commit

 

History

43 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 

Repository files navigation

SACD

PyTorch implementation on: Seeing your sleep stage: cross-modal distillation from EEG to infrared video.
(A cross-modal distillation method based on infrared video and EEG signals)

Introduction

We propose a novel cross-modal methodology (SACD) to solve the previous barriers, enabling point-of-care sleep stage monitoring at home.

To enable the developments of point-of-care healthcare research and distillation methods from clinical to visual modality, to our best knowledge, we are the first to collect a large-scale cross-modal distillation dataset, namely $S^3VE$.

Getting Started

Requirmenets:

  • python >= 3.6.10
  • pytorch >= 1.1.0
  • FFmpeg, FFprobe
  • Numpy
  • Sklearn
  • Pandas
  • openpyxl
  • mne=='0.20.7'

Prepare datasets:

Download $S^3VE$ datasets:

Note: If you need our dataset for relevant research, please send us an email with your Institution, Email and Use Purpose. We will provide you with the Baidu Cloud extraction code after review. Our email address is: 715129324@qq.com

Data Preparation on S^3VE (example):

Acknowledgement

This repository is partially built with two open-source implementation: (1) 3D-ResNets-PyTorch is used in video data preparation;

(2) Attnsleep is used for EEG feature extraction.

About

A cross-modal distillation method based on infrared video and EEG signals

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages

0