This repository contains all the resources and code for the project on detecting attention levels during coding tasks using EEG signals. The project employs deep learning techniques to extract features and patterns that indicate attention levels, and it includes feature extraction and Convolutional Neural Network (CNN) modeling.
The project may not seem complete. I am still struggling to understand the biological basis for interpretation. But over time and working on it further for thesis, I will get there! I made use of mne docs for a lot of the plotting; as well as chatGPT in the report to convert my texts to sound more "professional".
The project aims to understand the relationship between EEG signals and attention levels during coding tasks. By leveraging deep learning models, the project provides insights into cognitive states and their correlation with different coding activities.
The code is provided in a Jupyter Notebook (EEG_Internship.ipynb
) and includes the tutorial provided, some feature extraction, and modeling steps. You can run the notebook in Google Colab.
A detailed report on the project is available in PDF format, generated from LaTeX in Overleaf. The report includes the background, plan, process, and results of the project. You can find the report here.
The presentation file (EEG_Internship.pptx
) provides a visual summary of the internship project; it covers the main aspects of the project in a concise manner.
- Clone the repository:
git clone https://github.com/Ozziekins/EEG_Internship.git
- Navigate to the repository folder:
cd EEG_Internship
- Download the data files from the folder:
data
- Open the Jupyter Notebook in colab:
EEG_Internship.ipynb
- Create the directory and upload all the files in data folder into:
Data/SampleData
- Run the cells to reproduce the results.