# Subject-Invariant-SSVEP-GAN
[![Arxiv](https://img.shields.io/badge/ArXiv-2112.06567-orange.svg)](https://arxiv.org/abs/2007.11544)
[![PyPI pyversions](https://img.shields.io/pypi/pyversions/pykeen)](https://img.shields.io/pypi/pyversions/pykeen)
[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
Code to accompany our International Conference on Pattern Recognition (ICPR) paper entitled -
[Leveraging Synthetic Subject Invariant EEG Signalsfor Zero Calibration BCI](https://arxiv.org/pdf/2007.11544.pdf).
The code is structured as follows:
- `CNN_Subject_Classification.py ` contains code for subject-biometric classification network;
- `CNN_Subject_softmax.py ` contains code for Softmax probability values taken for the generated data;
- `SIS-GAN.py ` Our proposed SIS-GAN based model for generating subject invariant SSVEP-based EEG data;
- `CNN_pretrainsubject.py ` contains code for pre-training subject-biometric classification network;
- `CNN_SSVEP_Classification.py ` our SSVEP classification network;
- `models.py ` contains all the related models;
## Dependencies and Requirements
The code has been designed to support python 3.7+ only. The dependencies for the project can be installed via pip using the requirements.txt as follows:
```shell
$ pip install -r requirements.txt
```
## How to Use
The ```sample_data``` folder contains randomly generated data that is used to represent the shape of the input data. It is important to note this is not the real EEG data.
First, create the pretrain subject weight. This can be done by using the ```CNNN_pretrainsubject.py```.
Then, train SIS-GAN in ```SIS-GAN.py```by using the pretrain subject weight as a frozen network.
Lastly, evaluate the performance of the generated synthetic data by using ```CNN_SSVEP_classification```.
Model configurations are controlled by using yaml files that can be found in the config directory. This can be changed to customise the model accordingly.
## Cite
Please cite the associated paper for this work if you use this code:
```
@inproceedings{aznan2021leveraging,
title={Leveraging Synthetic Subject Invariant EEG Signals for Zero Calibration BCI},
author={Aznan, Nik Khadijah Nik and Atapour-Abarghouei, Amir and Bonner, Stephen and Connolly, Jason D and Breckon, Toby P},
booktitle={2020 25th International Conference on Pattern Recognition (ICPR)},
pages={10418--10425},
year={2021},
organization={IEEE}
}
```
没有合适的资源?快使用搜索试试~ 我知道了~
SSVEP-GAN-CNN
共43个文件
npy:18个
ds_store:10个
py:7个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
5星 · 超过95%的资源 2 下载量 27 浏览量
2023-06-03
13:07:41
上传
评论 1
收藏 2.71MB ZIP 举报
温馨提示
Code to accompany our International Conference on Pattern Recognition (ICPR) paper entitled - Leveraging Synthetic Subject Invariant EEG Signalsfor Zero Calibration BCI. The code is structured as follows: CNN_Subject_Classification.py contains code for subject-biometric classification network; CNN_Subject_softmax.py contains code for Softmax probability values taken for the generated data; SIS-GAN.py Our proposed SIS-GAN based model for generating subject invariant SSVEP-based EEG data; C
资源推荐
资源详情
资源评论
收起资源包目录
Subject-Invariant-SSVEP-GAN-master.zip (43个子文件)
Subject-Invariant-SSVEP-GAN-master
.flake8 456B
src
utils.py 3KB
CNN_SSVEP_Classification.py 4KB
CNN_Subject_softmax.py 2KB
models.py 9KB
SIS-GAN.py 10KB
CNN_pretrainsubject.py 4KB
CNN_Subject_Classification.py 6KB
LICENSE 1KB
sample_data
Real
.DS_Store 6KB
S01
.DS_Store 6KB
data
.DS_Store 6KB
data_01.npy 352KB
data_00.npy 352KB
label
.DS_Store 6KB
label_01.npy 368B
label_00.npy 368B
S02
.DS_Store 6KB
data
.DS_Store 6KB
data_01.npy 352KB
data_00.npy 352KB
label
.DS_Store 6KB
label_01.npy 368B
label_00.npy 368B
S03
data
data_01.npy 352KB
data_00.npy 352KB
label
label_01.npy 368B
label_00.npy 368B
Fake
.DS_Store 6KB
S01
.DS_Store 6KB
data
data.npy 352KB
label
label.npy 368B
S02
.DS_Store 6KB
data
data.npy 352KB
label
label.npy 368B
S03
data
data.npy 352KB
label
label.npy 368B
requirements.txt 500B
.gitignore 3KB
README.md 2KB
config
loo_SSVEP_class.yaml 373B
loo_pretrain_subject.yaml 377B
loo_SISGAN.yaml 750B
共 43 条
- 1
资源评论
- 2301_798720282024-03-20超赞的资源,感谢资源主分享,大家一起进步!
- 2301_792463822023-10-16超赞的资源,感谢资源主分享,大家一起进步!
大大U
- 粉丝: 721
- 资源: 138
下载权益
C知道特权
VIP文章
课程特权
开通VIP
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功