Originally created during Neurohackathon 2024, later enhanced and optimized as part of the Machine Learning Course.
This project is a Brain-Computer Interface (BCI) system designed to detect and warn users of the potential risk of epileptic seizures. Using advanced signal processing techniques and machine learning algorithms, the system analyzes EEG (Electroencephalography) data to identify patterns associated with seizure onset. The goal is to provide timely alerts, enabling individuals with epilepsy and their relatives to take preventive measures and improve their quality of life.
- Predicts and detects epileptic seizures using real-time EEG data with a BCI.
- Provides timely alerts to users or their close ones.
- Achieved 99.75% accuracy by experimenting with various models and techniques: KNN, SVM, Logistic Regression, RNN, Dynamic Time Warping, Random Forest, Decision Tree, XGBoost, and Naive Bayes.
- Igor Jakus
- Hubert Berlicki
- Kyrylo Goroshenko
- Lidia Podoluk
- Detailed presentation:
presentation.pdf - Dataset and research paper