There are 4 repositories under seizure-prediction topic.
The project is about applying CNNs to EEG data from CHB-MIT to predict seizure
Seizure prediction from EEG data using machine learning. 3rd place solution for Kaggle/Uni Melbourne seizure prediction competition.
solution for the American Epilepsy Society Seizure Prediction Challenge
This repository contains the trained deep learning models for the detection and prediction of Epileptic seizures.
EEG wearable device using CNN for seizure prediction
Predict seizures from EEGs using two models of spiking neural networks
Epilepsy Prediction with CNN-BiLSTM | BSc dissertation project
1st place algorithm from Melbourne-University AES-MathWorks-NIH Seizure Prediction Challenge
Code and data of the paper "Interpretable EEG seizure prediction using a multiobjective evolutionary algorithm", published by Scientific Reports in 2022.
2nd place algorithm for Melbourne-University AES-MathWorks-NIH Seizure Prediction Challenge
Forecasting seizures with multiple models, including artificial neural networks
Kaggle - Melbourne University AES/MathWorks/NIH Seizure Prediction 2016 competition - predict seizures in long-term human intracranial EEG recordings
3rd place algorithm of the Melbourne-University AES-MathWorks-NIH Seizure Prediction Challenge
on-line seizure prediction by evolve neuro-fuzzy model based on SOP and SPH
This project focuses on predicting epileptic seizures using EEG signals and ensemble learning techniques. It aims to provide accurate and timely predictions to help individuals with epilepsy manage their condition more effectively.
Epileptic EEG detection using the linear prediction error energy
The codebase for a research project that uses common spatial patterns (CSP) filters to search for waveforms in epileptic Electrocorticographic (ECoG) signals that are discriminative of the preictal and interictal state.
Epilepsey and Insomnia Detection Using EEG signals
Code and data of the paper "A personalized and evolutionary algorithm for interpretable EEG epilepsy seizure prediction", published by Scientific Reports in 2021.
The code for the paper "The goal of explaining black boxes in EEG seizure prediction is not to explain models’ decisions", published in Epilepsia Open (https://doi.org/10.1002/epi4.12748). It concerns explainability methods on Machine Learning for EEG seizure prediction.
Seizure prediction contains innovative methods using adaptive filtering for detecting epileptic seizures based on energy signals
Real-time Forecasting Epileptic Seizure using EEG
In this research project we used a shift-invariant k-means algorithm to learn a preictal and interictal codebook of prototypical waveforms that can be used to summarize the occurrence of recurrent waveforms and to classify between preictal and interictal segments. We use the common spatial patterns (CSP) method to spatially filter the multichannel ECoG segments before doing the waveform learning.
based on kaggle's Melbourne University AES/MathWorks/NIH competition
Computational Artificial Intelligence Projects (Seizure Detection) - Fall-2022
Thesis project: "On the clinical acceptance of EEG seizure prediction methodologies". Explainability of seizure prediction models.
American Epilepsy Society Seizure Prediction Challenge.