ARTIFICIAL NEURAL NETWORK BASED BRAIN DISORDER DIAGNOSTIC SYSTEM
ARTIFICIAL NEURAL NETWORK BASED BRAIN DISORDER DIAGNOSTIC SYSTEM This invention relates to a method for empirical risk assessment of brain disorder using a neural network diagnostic system. The said method comprises the steps of magneto-encephalography (MEG) measurement of resting-state MEG signals...
Saved in:
Main Authors | , , , , , , , , , , , |
---|---|
Format | Patent |
Language | English |
Published |
09.09.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | ARTIFICIAL NEURAL NETWORK BASED BRAIN DISORDER DIAGNOSTIC SYSTEM This invention relates to a method for empirical risk assessment of brain disorder using a neural network diagnostic system. The said method comprises the steps of magneto-encephalography (MEG) measurement of resting-state MEG signals using a MEG scanner, data pre-processing of the MEG signals measured, developing network architecture, made of a convolution neural network, model training and testing, by evaluating the performance of the developed network architecture based on the sample data and the open-access databases, nested cross validation, for classifying 10 patients with Alzheimer's disease, Epilepsy, and Parkinson's disease, decoding the disease labels, by using relative power of the MEG signals using a support vector machines (SVM) model. MEG Signals measurement. Data Pre-processing of the measured MEG Signals. Developing network architecture model. [ Model training and testing. [ Nested cross-validation of the trained and tested model, Decoding the disease labels. Figure 1. Flow Diagram of Artificial Neural Network Based Brain Disorder Diagnostic System |
---|---|
Bibliography: | Application Number: AU20210103997 |