Published a research paper named "Machine Learning Models for Accurate EEG-Based Eye State Detection" at Scopus Index.
This repository contains code and resources for predicting eye states (open or closed) based on EEG (Electroencephalogram) data using machine learning algorithms. The project aims to provide a practical solution for eye state detection, which can have various applications, including driver drowsiness detection, human-computer interaction, and medical research.
We used a publicly available EEG dataset, which you can find [here]. The dataset contains EEG recordings of eye states, and it has been preprocessed for our machine learning experiments.
We have implemented and trained various machine learning models for eye state prediction, including but not limited to:
- Random Forest
- XG Boost
- Catboost
- Light GBM