NeuroWave is a collection of EEG signal processing scripts focused on applying different types of filters to raw EEG data. The goal is to demonstrate how various filtering techniques can be used to remove noise, extract meaningful frequency bands, and prepare signals for further analysis (e.g., feature extraction, classification, or brain-computer interface applications).
Implementation of different filtering techniques, including:
Smoothing filters:
- Band Pass Filter
- Average Filter
- Gaussian Filter
- Median Filter
Frequency analysis:
- Fast Fourier Transform (FFT)
- Wavelet Transform
- Hilbert Transform
Muscle artefacts removal (component decomposition):
- Independent Component Analysis (ICA)
- Wavelet Decomposition
- Empirical Mode Decomposition (EMD)
- Canonical Correlation Analysis(CCA)
And also:
- Visualization of signals before and after filtering
- Real-time signal processing in morning and evening EEG datasets
- matplotlib
- pandas
- scipy
- pywt
- mne
- scikit-learn
- PyEMD
- pyts
- Clone the repository:
git clone https://github.com/parvanehyaghoubi/NeuroWave.git
cd NeuroWaveThis project is licensed under the MIT License. See the LICENSE file for details.
For any inquiries, please contact:
