EEG-Classification

EEG-Classification is a machine learning project focused on analyzing and classifying electroencephalogram (EEG) signals. The repository provides a series of Jupyter Notebooks for feature extraction, signal preprocessing, model training, and result visualization. The project aids research in neuroscience, brain-computer interfaces, and clinical diagnostics through advanced classification methods for EEG data.

Repository Structure

• Jupyter Notebooks
  • 1.1 EEG classification.ipynb
  • 2.1 EEG classification.ipynb
  • 3.1 EEG classification.ipynb
  • 4.1 EEG classification.ipynb
  • 4.2 EEG classification.ipynb
• Data and Archive
  • eeg_dataset/: EEG data used for experiments
  • archive/: Archived results and supplementary files

Key Features

• Preprocessing and cleaning of EEG signals
• Feature engineering and extraction
• Classical machine learning models and deep learning classifiers
• Visualizations of EEG signals and classification outcomes
• Modular notebook workflow for reproducible research

Getting Started

1. Clone the repository:

   git clone https://github.com/shashi9170/EEG-Classification.git

2. Install required dependencies:
   • You will need Python, Jupyter Notebook, and relevant ML/DL libraries (e.g., scikit-learn, tensorflow/pytorch, numpy, matplotlib, etc.).
3. Open and run the Jupyter Notebooks in sequence.
4. Place your EEG data in the eeg_dataset directory if using your own dataset.

Applications

• Brain-computer interface research
• Clinical diagnostics (e.g., detecting epilepsy, sleep disorders)
• Cognitive neuroscience
• Automated analysis of brain activity

If you use this repository in your work or publication, please consider citing or referencing it. For questions, feel free to open an issue or contact the maintainer.