Brain Stroke Detection Using ANN Based On EEG Signals Using CNN ‎Path

Abstract

Brain stroke occurs because of a blockage in the artery, which delivers oxygenated blood to the brain. Acute Ischemic Stroke (AIS) is mostly occurred brain stroke. Early detection of brain stroke can be life-saving for patients. Electroencephalography is a technique to analyze electrical activities present in the different parts of the human brain, and using visual trace, it records these activities. EEG provides cost-effective, portable, high-frequency and accurate measurement as compared to other brain wave activity monitoring tools. EEG is used to diagnose AIS. In the proposed research, the convolutional neural network is applied for the classification of stroke severity. In this algorithm, the power spectral density (PSD) of EEG signals is calculated based on the extracted features from the artificial neural network. The feature map was then trained to classify the data into four instances based on the severity of the brain stroke. The effectiveness of the suggested algorithm is examined by comparing it with several similar algorithms., and it is observed that the accuracy of the proposed algorithm is 98.3% and which is better than the existing algorithm for brain stroke detection.