stevenlol / classification_of_epileptic_seizure_using_eeg_scalp_and_intracranial

Classification_of_Epileptic_seizure_using_EEG_scalp_and_Intracranial

#Introduction Epilepsy is a neurological disorder that affects people of all ages all over the world. This disorder is characterized by recurrent seizures, which are clinical manifestations of sudden and brief electrical shocks of a group of brain cells. Different brain areas may be the source of these seizures. Approximately, 0.5–1.5% of the world's population suffers from epilepsy.It is one of the most common chronic diseases that there are: 0.5% of all human beings suffer from epilepsy, which means that in the U.K. alone around 300 000 to 600 000 people are affected.

classifying the Epileptic seizure

The aim of the study is to classify Seizure disorder patients as high or low risk and partial or generalized using EEG scans and patient medical history from a high di-mensional dataset using machine learning approach to aid early treatment, thus reducing morbidity in remote places where neurologists are not easily accessible. The risk of developing epilepsy is more common in elderly than the young, causing premature mortality.There are no anti-epileptic drugs that can cure seizure disorder. Seizure Analyses are primarily performed on EEG and MRI. An epileptic seizure can be classified into partial and generalized seizure. Partial seizure starts in one area of the brain while generalized seizure occurs in both hemispheres of the brain

The term "epilepsy" is derived from the Greek word "epilambanein", which means "to seize upon", "to attack". Thus epilepsy is a seizure or rather a disease which causes seizures to occur. As, however, there are many very different types of seizure, it is better to speak of epilepsy.

Research on Autoclassification

The aim of the reseach is to make the use of logic gates on multiple datasets of lobes in the hemispere

Dataset Description

This database available from the Children’s Hospital Boston, consists of EEG recordings from pediatric subjects with intractable seizures. Subjects were monitored for up to several days following withdrawal of anti-seizure medication in order to characterize their seizures and assess their candidacy for surgical intervention.

The sampling rate of the data was 173.61 Hz. The time series have the spectral bandwidth of the acquisition system, which is 0.5 Hz to 85 Hz. The dataset consists of five sets: Set B, Set C and Set E.

Prerequistive

Python module with many functions for time series analysis, including brain physiological signals

1. Clone the repo via HTTPS: $ pip install MNE(for EEG,MEG,ECoG) $ python setup.py install $ python setup.py install --user

2. pip supports installing from a GitHub repo Follow the [https://github.com/mne-tools/mne-python] For Documentation follow the [https://www.martinos.org/mne/stable/documentation.html]