# LATSS
A subject-independent motor imagery classification model.
## Description
Label Alignment - Tangent Space Mapping - SVM, or LATSS for short, is a subject-independent motor imagery classification model that utilizes advanced domain adaptation techniques to improve the generalization of the model across subjects.
## Installation
```bash
$ pip install latss
```
## Usage
Training and predicting with the LATSS model is simple. Here's an example of how to use it:
```python
from latss import LATSS
# Load source data
source_data = ...
# Initialize the model
model = LATSS(source_data=source_data)
# Calibrate and train the model
# Note: calibration_data must be an annotated mne.io.Raw object
calibration_data = ...
event_id = {
'left_hand': 1,
'right_hand': 2,
}
acc = model.calibrate(calibration_data, event_id=event_id)
# Predict on new data
# Note: new_data must be a mne.io.Raw object as well
new_data = ...
prediction = model.predict(new_data)
```
Source data can be any [mne.Epochs](https://mne.tools/stable/generated/mne.Epochs.html) object or a dictionary with the following structure:
```python
{
'data': np.array, # shape: (n_trials, n_channels, n_samples)
'labels': np.array, # shape: (n_events, 3)
}
```
## License
`latss` was created by Zeyad Ahmed. It is licensed under the terms
of the MIT license.
## Credits
The LATSS model was inspired by the work of He et al. [1], while introducing some key modifications and improvements.
[1] H. He and D. Wu, "Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach," in IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 28, no. 5, pp. 1091-1108, May 2020, doi: [10.1109/TNSRE.2020.2980299](https://doi.org/10.1109/TNSRE.2020.2980299).
Raw data
{
"_id": null,
"home_page": null,
"name": "latss",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "motor imagery, EEG, label alignment",
"author": null,
"author_email": "Zeyad Ahmed <zeyadmansour2@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/b6/10/610fff866ac9321f8df52c1b305f4f7e103912c13db3f416f9e77fb0fff8/latss-0.1.4.tar.gz",
"platform": null,
"description": "# LATSS\n\nA subject-independent motor imagery classification model.\n\n## Description\n\nLabel Alignment - Tangent Space Mapping - SVM, or LATSS for short, is a subject-independent motor imagery classification model that utilizes advanced domain adaptation techniques to improve the generalization of the model across subjects.\n\n## Installation\n\n```bash\n$ pip install latss\n```\n\n## Usage\n\nTraining and predicting with the LATSS model is simple. Here's an example of how to use it:\n\n```python\nfrom latss import LATSS\n\n# Load source data\nsource_data = ...\n\n# Initialize the model\nmodel = LATSS(source_data=source_data)\n\n# Calibrate and train the model\n# Note: calibration_data must be an annotated mne.io.Raw object\ncalibration_data = ...\nevent_id = {\n 'left_hand': 1,\n 'right_hand': 2,\n }\nacc = model.calibrate(calibration_data, event_id=event_id)\n\n# Predict on new data\n# Note: new_data must be a mne.io.Raw object as well\nnew_data = ...\nprediction = model.predict(new_data)\n```\n \n \nSource data can be any [mne.Epochs](https://mne.tools/stable/generated/mne.Epochs.html) object or a dictionary with the following structure:\n```python\n{\n 'data': np.array, # shape: (n_trials, n_channels, n_samples)\n 'labels': np.array, # shape: (n_events, 3)\n}\n```\n\n\n## License\n\n`latss` was created by Zeyad Ahmed. It is licensed under the terms\nof the MIT license.\n\n## Credits\n\nThe LATSS model was inspired by the work of He et al. [1], while introducing some key modifications and improvements.\n\n[1] H. He and D. Wu, \"Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach,\" in IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 28, no. 5, pp. 1091-1108, May 2020, doi: [10.1109/TNSRE.2020.2980299](https://doi.org/10.1109/TNSRE.2020.2980299).\n\n",
"bugtrack_url": null,
"license": "MIT License",
"summary": "Unlocking subject-independent motor imagery decoding with label alignment.",
"version": "0.1.4",
"project_urls": {
"Homepage": "https://pypi.org/project/latss/",
"Repository": "https://github.com/zeyadmohaymen/latss.git"
},
"split_keywords": [
"motor imagery",
" eeg",
" label alignment"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "b878b1e20ad31a0c931a5b741122ac39cc6e505ed3486519dd2003f1231f3f15",
"md5": "35d6bb78675908e11831ce9b0b636d98",
"sha256": "dba6d4e6db328a3e233b1ce0552ebcc48f1b8636c6d90e7b93f6a75b74a0b7f0"
},
"downloads": -1,
"filename": "latss-0.1.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "35d6bb78675908e11831ce9b0b636d98",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 15110,
"upload_time": "2024-06-07T11:19:43",
"upload_time_iso_8601": "2024-06-07T11:19:43.320751Z",
"url": "https://files.pythonhosted.org/packages/b8/78/b1e20ad31a0c931a5b741122ac39cc6e505ed3486519dd2003f1231f3f15/latss-0.1.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "b610610fff866ac9321f8df52c1b305f4f7e103912c13db3f416f9e77fb0fff8",
"md5": "1767e508117799209b188cead04641e7",
"sha256": "e0085759bfad8dc714d8021ba0c73e45f5efdc830683763e6577b9ddd0b6921e"
},
"downloads": -1,
"filename": "latss-0.1.4.tar.gz",
"has_sig": false,
"md5_digest": "1767e508117799209b188cead04641e7",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 15472,
"upload_time": "2024-06-07T11:19:44",
"upload_time_iso_8601": "2024-06-07T11:19:44.978682Z",
"url": "https://files.pythonhosted.org/packages/b6/10/610fff866ac9321f8df52c1b305f4f7e103912c13db3f416f9e77fb0fff8/latss-0.1.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-06-07 11:19:44",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "zeyadmohaymen",
"github_project": "latss",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "pyriemann",
"specs": []
},
{
"name": "scipy",
"specs": [
[
">=",
"1.10.1"
]
]
},
{
"name": "mne",
"specs": []
},
{
"name": "mne_icalabel",
"specs": []
},
{
"name": "onnxruntime",
"specs": []
}
],
"lcname": "latss"
}
JSON
