Classification of Brain waves using EEG Signals with Deep learning

6,000.00

Detection of Normality and Abnormality using Brainwaves with EG signals

Platform : Python

Delivery Duration : 3 – 5 hour

Online Demo : 1 – 2 hour

100 in stock

SKU: Detection Of Disease Using EEG Signal Categories: ,

Description

Abstract

Medical Field is working on developing and predicting brain disease using a lot of equipment. In this project, AI with Deep learning is applied to predict the abnormality in brain waves of EEG signals. Brain wave acquisition is done by using EEG headsets such as Neurosky Mindwave mobile and Brainsense. It has 3 classes such as Normal, Abnormal and Blink. Since the waves are obtained from the prefrontal lobe of the brain. It can also sense the eye blinks. In the EEG wave, the deflection can be viewed. The classification is done by CNN – Convolutional Neural Network.


Existing system

  • In the existing system, Brain wave acquisition is highly expensive and to find a neurologist to predict the state from the data.
  • No AI-based application is deployed to predict the state

Proposed system

  • In this project, brainwave is classified using Deep learning 
  • Datasets are created using EEG Headset such as Brainsense/Mindwave mobile.
  • It contains 3 classes such as Normal, Abnormal and Blink

Sample Dataset

Classification of Brain waves using EEG Signals with Deep learning     Classification of Brain waves using EEG Signals with Deep learning  Classification of Brain waves using EEG Signals with Deep learning


Libraries used

  • Keras
  • Scipy
  • PIL
  • Numpy
  • cv2

Result

In this project, Deep learning (CNN) applied for more than 300 images of 3 different classes, results in the accuracy of 99.7% accuracy.

Reviews

There are no reviews yet.

Be the first to review “Classification of Brain waves using EEG Signals with Deep learning”

Your email address will not be published. Required fields are marked *

4 × 4 =

This site uses Akismet to reduce spam. Learn how your comment data is processed.