Skip to content

This project uses EEG data to detect schizophrenia, achieving a robust classifier with LGBM, boasting a ROC AUC of 95.96% and an accuracy of 90%

Notifications You must be signed in to change notification settings

numanwaziri/EEG-Schizophrenia-Detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 

Repository files navigation

EEG Schizophrenia Detection

This repository contains the code for a project on Schizophrenia Detection using EEG data. The goal is to analyze EEG data and develop a model for detecting schizophrenia based on the provided datasets.

Import Note: The majority of the logic, preprocessing, and analysis are implemented in the util module. Refer to the util module for detailed functions and processing steps.

Data

Code in this repository assumes that all data is locally downloaded and unzipped into a dataset folder. The dataset folder should include directories for each of the 81 subjects' data.

Note: No raw data or output files are included in this repository due to size constraints.

Project Result:

In the domain of traditional models, the Light Gradient Boosting Machine (LGBM) proved to be a robust classifier, surpassing others in this project with a ROC AUC of 95.96% and an accuracy of 90%.

Project Report

The detailed project report can be found here.

About

This project uses EEG data to detect schizophrenia, achieving a robust classifier with LGBM, boasting a ROC AUC of 95.96% and an accuracy of 90%

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published