This repository contains the code for an EEG Classification project, focused on classifying subjects based on their EEG recordings before and during the performance of mental arithmetic tasks. The goal is to distinguish between good and bad counters, providing insights into cognitive processes during arithmetic activities. The project utilizes a 2D Convolutional Neural Network (CNN) model for classification.
- Python
- Jupyter Notebook
- Google Colab
- TensorFlow: Open-source machine learning library.
- Keras: Deep learning framework for building and training neural networks.
- NumPy: Library for numerical computing in Python.
- Pandas: Data manipulation and analysis library.
- Matplotlib: Data visualization library.
- Scikit-learn: Machine learning tools and algorithms.
-
Exploratory Data Analysis (EDA):
- Conducted visualizations and in-depth EDA on the EEG dataset to understand its characteristics.
-
Data Preprocessing:
- Preprocessed EEG data, including cleaning, normalization, and extraction of relevant features.
-
Model Training:
- Implemented a 2D CNN model to classify subjects into good and bad counters based on their EEG recordings.
-
Model Evaluation:
- Evaluated the model's performance using standard classification metrics such as accuracy.