SSVEP EEG Classification and Visualization

Overview

This project involves working with a 12-class Steady-State Visual Evoked Potentials (SSVEP) EEG dataset to implement and visualize classification methods. It explores Canonical Correlation Analysis (CCA) for feature extraction and classification of EEG signals, with practical applications in Brain-Computer Interfaces (BCI).

Dataset

• Description: The dataset consists of EEG recordings for 12 different SSVEP stimuli flickering at specific frequencies. Each trial records responses from 8 EEG channels for 4 seconds.
• Source: GitHub Repository
• Reference Paper: Masaki Nakanishi, Yijun Wang, Yu-Te Wang, and Tzyy-Ping Jung, "A Comparison Study of Canonical Correlation Analysis Based Methods for Detecting Steady-State Visual Evoked Potentials," PLoS One, vol.10, no.10, e140703, 2015.

Features

1. Implementation of Canonical Correlation Analysis (CCA) for EEG classification.
2. Frequency domain visualization of EEG signals to highlight SSVEP responses.
3. Custom preprocessing pipelines to clean and prepare EEG signals for analysis.

@Ibn Sina Summer School – Decoding the brain using BCI at Arabs in Neuroscience

Contributors

Mariam Ahmed

Youssef Ashraf