<p align="center">
<img src="MixNet_overview_new.jpg" width="100%" height="100%">
</p>
### MixNet: Joining Force of Classical and Modern Approaches toward The Comprehensive Pipeline in Motor Imagery EEG Classification
Python API and the novel algorithm for motor imagery EEG recognition named MixNet. The API benefits BCI researchers ranging from beginners to experts. We demonstrate examples of using the API for loading benchmark datasets, preprocessing, training, and validating SOTA models, including MixNet. In summary, the API allows the researchers to construct the pipeline to benchmark the newly proposed models and very recently developed SOTA models.
---
## Getting started
### Dependencies
- Python==3.8.10
- tensorflow-gpu==2.7.0
- tensorflow-addons==0.16.1
- scikit-learn>=1.2.2
- wget>=3.2
- h5py==3.5.0
- pandas>=2.0
1. Create `conda` environment with dependencies
```bash
wget https://github.com/Max-Phairot-A/MixNet/blob/main/environment.yml
conda env create -f environment.yml
conda activate mixnet
```
### Installation:
1. Using pip
```bash
pip install mixnet-eeg
```
<!-- 2. Using the released python wheel
```bash
wget https://github.com/IoBT-VISTEC/MIN2Net/releases/download/v1.0.0/min2net-1.0.0-py3-none-any.whl
pip install min2net-1.0.0-py3-none-any.whl
``` -->
### Citation
To read & cite [our paper](https://ieeexplore.ieee.org/document/10533256)
P. Autthasan, R. Chaisaen, H. Phan, M. D. Vos and T. Wilaiprasitporn, "MixNet: Joining Force of Classical and Modern Approaches toward The Comprehensive Pipeline in Motor Imagery EEG Classification," in IEEE Internet of Things Journal, doi: 10.1109/JIOT.2024.3402254.
```
@ARTICLE{10533256,
author={Autthasan, Phairot and Chaisaen, Rattanaphon and Phan, Huy and Vos, Maarten De and Wilaiprasitporn, Theerawit},
journal={IEEE Internet of Things Journal},
title={MixNet: Joining Force of Classical and Modern Approaches Toward the Comprehensive Pipeline in Motor Imagery EEG Classification},
year={2024},
volume={11},
number={17},
pages={28539-28554},
keywords={Electroencephalography;Task analysis;Feature extraction;Measurement;Internet of Things;Multitasking;Motors;Adaptive gradient blending;brain-computer interface (BCI);deep learning (DL);motor imagery (MI);multitask learning},
doi={10.1109/JIOT.2024.3402254}}
```
### License
Copyright © 2021-All rights reserved by [INTERFACES (BRAIN lab @ IST, VISTEC, Thailand)](https://www.facebook.com/interfaces.brainvistec).
Distributed by an [Apache License 2.0](https://github.com/Max-Phairot-A/MixNet/blob/main/LICENSE).
Raw data
{
"_id": null,
"home_page": "https://github.com/Max-Phairot-A/MixNet",
"name": "mixnet-eeg",
"maintainer": null,
"docs_url": null,
"requires_python": "<=3.10.4,>=3.7",
"maintainer_email": null,
"keywords": "Brain-computer Interfaces, BCI, Deep learning, DLMotor Imagery, MI, Multi-task Learning, Deep Metric Learning, DML, Autoencoder, AE, Adaptive Gradient Blending, EEG Classifier",
"author": "Phairot Autthasan",
"author_email": "phairot.a_s17@vistec.ac.th",
"download_url": "https://files.pythonhosted.org/packages/30/5f/2be303a132a17dc73370a6ae662b445f5815735cbac6f28a968dd15eb34d/mixnet-eeg-1.0.2.tar.gz",
"platform": null,
"description": "<p align=\"center\"> \n<img src=\"MixNet_overview_new.jpg\" width=\"100%\" height=\"100%\"> \n</p>\n\n### MixNet: Joining Force of Classical and Modern Approaches toward The Comprehensive Pipeline in Motor Imagery EEG Classification\n\nPython API and the novel algorithm for motor imagery EEG recognition named MixNet. The API benefits BCI researchers ranging from beginners to experts. We demonstrate examples of using the API for loading benchmark datasets, preprocessing, training, and validating SOTA models, including MixNet. In summary, the API allows the researchers to construct the pipeline to benchmark the newly proposed models and very recently developed SOTA models.\n\n---\n\n## Getting started\n\n### Dependencies\n\n- Python==3.8.10\n- tensorflow-gpu==2.7.0\n- tensorflow-addons==0.16.1\n- scikit-learn>=1.2.2\n- wget>=3.2\n- h5py==3.5.0\n- pandas>=2.0\n\n1. Create `conda` environment with dependencies\n```bash\nwget https://github.com/Max-Phairot-A/MixNet/blob/main/environment.yml\nconda env create -f environment.yml\nconda activate mixnet\n```\n\n### Installation:\n\n1. Using pip\n\n ```bash\n pip install mixnet-eeg\n ```\n<!-- 2. Using the released python wheel\n\n ```bash\n wget https://github.com/IoBT-VISTEC/MIN2Net/releases/download/v1.0.0/min2net-1.0.0-py3-none-any.whl\n pip install min2net-1.0.0-py3-none-any.whl\n ``` -->\n\n### Citation\n\nTo read & cite [our paper](https://ieeexplore.ieee.org/document/10533256)\n\nP. Autthasan, R. Chaisaen, H. Phan, M. D. Vos and T. Wilaiprasitporn, \"MixNet: Joining Force of Classical and Modern Approaches toward The Comprehensive Pipeline in Motor Imagery EEG Classification,\" in IEEE Internet of Things Journal, doi: 10.1109/JIOT.2024.3402254.\n\n```\n@ARTICLE{10533256,\n author={Autthasan, Phairot and Chaisaen, Rattanaphon and Phan, Huy and Vos, Maarten De and Wilaiprasitporn, Theerawit},\n journal={IEEE Internet of Things Journal}, \n title={MixNet: Joining Force of Classical and Modern Approaches Toward the Comprehensive Pipeline in Motor Imagery EEG Classification}, \n year={2024},\n volume={11},\n number={17},\n pages={28539-28554},\n keywords={Electroencephalography;Task analysis;Feature extraction;Measurement;Internet of Things;Multitasking;Motors;Adaptive gradient blending;brain-computer interface (BCI);deep learning (DL);motor imagery (MI);multitask learning},\n doi={10.1109/JIOT.2024.3402254}}\n```\n\n### License\nCopyright © 2021-All rights reserved by [INTERFACES (BRAIN lab @ IST, VISTEC, Thailand)](https://www.facebook.com/interfaces.brainvistec).\nDistributed by an [Apache License 2.0](https://github.com/Max-Phairot-A/MixNet/blob/main/LICENSE).\n\n\n",
"bugtrack_url": null,
"license": "Apache Software License",
"summary": "MixNet: Joining Force of Classical and Modern Approaches toward The Comprehensive Pipeline in Motor Imagery EEG Classification",
"version": "1.0.2",
"project_urls": {
"Bug Tracker": "https://github.com/Max-Phairot-A/MixNet/issues",
"Documentation": "https://github.com/Max-Phairot-A/MixNet",
"Download": "https://github.com/Max-Phairot-A/MixNet/releases",
"Homepage": "https://github.com/Max-Phairot-A/MixNet",
"Source Code": "https://github.com/Max-Phairot-A/MixNet"
},
"split_keywords": [
"brain-computer interfaces",
" bci",
" deep learning",
" dlmotor imagery",
" mi",
" multi-task learning",
" deep metric learning",
" dml",
" autoencoder",
" ae",
" adaptive gradient blending",
" eeg classifier"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "5f43176cdf68f621535e67ce1a0cf58ffcbb1401444a8e02b785d7572519e69d",
"md5": "6b419708cc48e2d8d03453ab10625b70",
"sha256": "e0ce8989c0b968eb71d5f62f17049f80a962131fbdb1dba1c5a5ee843757400e"
},
"downloads": -1,
"filename": "mixnet_eeg-1.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "6b419708cc48e2d8d03453ab10625b70",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<=3.10.4,>=3.7",
"size": 98409,
"upload_time": "2024-09-05T05:44:51",
"upload_time_iso_8601": "2024-09-05T05:44:51.539585Z",
"url": "https://files.pythonhosted.org/packages/5f/43/176cdf68f621535e67ce1a0cf58ffcbb1401444a8e02b785d7572519e69d/mixnet_eeg-1.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "305f2be303a132a17dc73370a6ae662b445f5815735cbac6f28a968dd15eb34d",
"md5": "ba2d1263ed338f7a2cf68db24e699823",
"sha256": "03e6451b6c6ea0cc005d106d434304e8cc304c9b0005d37a34b5a992ea54e214"
},
"downloads": -1,
"filename": "mixnet-eeg-1.0.2.tar.gz",
"has_sig": false,
"md5_digest": "ba2d1263ed338f7a2cf68db24e699823",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<=3.10.4,>=3.7",
"size": 41050,
"upload_time": "2024-09-05T05:44:53",
"upload_time_iso_8601": "2024-09-05T05:44:53.935157Z",
"url": "https://files.pythonhosted.org/packages/30/5f/2be303a132a17dc73370a6ae662b445f5815735cbac6f28a968dd15eb34d/mixnet-eeg-1.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-05 05:44:53",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Max-Phairot-A",
"github_project": "MixNet",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "mixnet-eeg"
}
JSON
