Skip to content

This repository contains the tensorflow implementation for our ICONIP-2018 paper: "Continuous Convolutional Neural Network with 3D Input for EEG-Based Emotion Recognition" (To appear...)

Notifications You must be signed in to change notification settings

ynulonger/DE_CNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Code for ICONIP 2018 submission

This repository contains the tensorflow implementation for our ICONIP-2018 paper: "Continuous Convolutional Neural Network with 3D Input for EEG-Based Emotion Recognition"

About the paper

Instructions

  • Before running the code, please download the DEAP dataset, unzip it and place it into the right directory. The dataset can be found here.
  • Please run the get_1D_data.py to compute the Differential Entropy for each original .mat file. DE features of each .mat file will be stored in 1D_dataset folder.
  • 1D_to_3D.py is used to transform the 1-dimentional data into 3-dimentional format, which will be used to train the proposed model.
  • Using cnn.py to train and test the model (10-fold cross-validation), result of each fold will be saved in a .xls file (you can find these .xls files in ./result folder).
  • count_accuracy.py is used to summarize the final accuracy of the model. The generated .xls files can be found in ./result/summary folder.

Requirements

  • Pyhton 3
  • scipy
  • numpy
  • pandas
  • sk-learn
  • tensorflow (1.4 version)
  • import xlrd
  • import xlwt

If you have any questions, please contact [email protected]

About

This repository contains the tensorflow implementation for our ICONIP-2018 paper: "Continuous Convolutional Neural Network with 3D Input for EEG-Based Emotion Recognition" (To appear...)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published